CVPR2020论文列表（中英对照）

Conditional Channel Gated Networks for Task-Aware Continual Learning 用于任务感知持续学习的条件通道门控网络
Multimodal Categorization of Crisis Events in Social Media 社交媒体中危机事件的多模式分类
Counterfactual Vision and Language Learning 反事实视觉和语言学习
Gold Seeker Information Gain From Policy Distributions for Goal-Oriented Vision-and-Langauge 从面向目标的愿景和语言的政策分配中获取寻金者信息
Image2StyleGAN How to Edit the Embedded Images Image2StyleGAN 如何编辑嵌入的图像
Cross-Modal Deep Face Normals With Deactivable Skip Connections 具有可停用跳跃连接的跨模态深面法线
Hussein Correction Filter for Single Image Super-Resolution Robustifying Off-the-Shelf Deep Super-Resolvers用于单幅图像超分辨率鲁棒化现成深度超分辨率的 Hussein 校正滤波器
Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit 通过强制跨位特征一致性来实现对抗性鲁棒性
Deep White-Balance Editing 深度白平衡编辑
Towards Causal VQA Revealing and Reducing Spurious Correlations by Invariant 朝着因果 VQA 揭示和减少不变量的虚假相关性
Scale-Space Flow for End-to-End Optimized Video Compression 端到端优化视频压缩的尺度空间流
Camera On-Boarding for Person Re-Identification Using Hypothesis Transfer Learning 使用假设迁移学习进行人员重新识别的相机载入
Density-Based Clustering for 3D Object Detection in Point Clouds 用于点云中 3D 对象检测的基于密度的聚类
Non-Adversarial Video Synthesis With Learned Priors 具有学习先验的非对抗性视频合成
Fast Soft Color Segmentation 快速柔和的颜色分割
From Two Rolling Shutters to One Global Shutter 从两个卷帘门到一个全局快门
Active Speakers in Context 上下文中的活跃演讲者
From Paris to Berlin Discovering Fashion Style Influences Around the 从巴黎到柏林 发现各地的时尚风格影响
Disentangled Image Generation Through Structured Noise Injection 通过结构化噪声注入生成分离的图像
A Stochastic Conditioning Scheme for Diverse Human Motion Prediction 一种用于多种人体运动预测的随机调节方案
High-Resolution Daytime Translation Without Domain Labels 无域标签的高分辨率日间翻译
A Characteristic Function Approach to Deep Implicit Generative Modeling 深度隐式生成建模的特征函数方法
Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation 通过几何保留图像到图像转换的无监督多模态图像配准
Single-Stage Semantic Segmentation From Image Labels 图像标签的单阶段语义分割
UniPose Unified Human Pose Estimation in Single Images and Videos 单一图像和视频中的 UniPose 统一人体姿态估计
SAL Sign Agnostic Learning of Shapes From Raw Data 从原始数据中学习形状的 SAL 符号不可知论
Single-Step Adversarial Training With Dropout Scheduling 使用 Dropout 调度的单步对抗训练
TESA Tensor Element Self-Attention via Matricization 通过矩阵化的 TESA 张量元素自我注意
Bi3D Stereo Depth Estimation via Binary Classifications 通过二进制分类的 Bi3D 立体深度估计
Meshlet Priors for 3D Mesh Reconstruction 用于 3D 网格重建的 Meshlet 先验
Weakly-Supervised Domain Adaptation via GAN and Mesh Model for Estimating 通过 GAN 和网格模型进行弱监督域自适应估计
Explorable Super Resolution 可探索的超分辨率
Exploring Unlabeled Faces for Novel Attribute Discovery 探索未标记的面孔以发现新的属性
Adaptive Dilated Network With Self-Correction Supervision for Counting 具有自校正监督的自适应扩张网络计数
D3Feat Joint Learning of Dense Detection and Description of 3D Local FeaturesD3Feat 密集检测和 3D 描述的联合学习
Deep Facial Non-Rigid Multi-View Stereo 深层面部非刚性多视图立体
Learning to Forget for Meta-Learning 学习忘记元学习
Event Probability Mask EPM and Event Denoising Convolutional Neural Network 事件概率掩码 EPM 和事件去噪卷积神经网络
An Adaptive Neural Network for Unsupervised Mosaic Consistency Analysis in 用于无监督马赛克一致性分析的自适应神经网络
Novel Object Viewpoint Estimation Through Reconstruction Alignment 通过重建对齐的新目标视点估计
4D Visualization of Dynamic Events From Unconstrained Multi-View Videos 来自不受约束的多视图视频的动态事件的 4D 可视化
SAM The Sensitivity of Attribution Methods to Hyperparameters SAM 归因方法对超参数的敏感性
Height and Uprightness Invariance for 3D Prediction From a Single 单次 3D 预测的高度和垂直度不变性
MAGSAC a Fast Reliable and Accurate Robust Estimator MAGSAC 一种快速可靠且准确的稳健估计器
ScopeFlow Dynamic Scene Scoping for Optical Flow ScopeFlow 用于光流的动态场景范围
Improved Few-Shot Visual Classification 改进的 Few-Shot 视觉分类
Shape Reconstruction by Learning Differentiable Surface Representations 通过学习可微分表面表示进行形状重建
Context R-CNN Long Term Temporal Context for Per-Camera Object Detection Context R-CNN Long Term Temporal Context for Per-Camera Object Detection
SpeedNet Learning the Speediness in Videos SpeedNet 学习视频中的速度
Can Weight Sharing Outperform Random Architecture Search An Investigation With 权重共享能否胜过随机架构搜索？
PandaNet Anchor-Based Single-Shot Multi-Person 3D Pose Estimation PandaNet Anchor-Based Single-Shot Multi-Person 3D Pose Estimation
Uninformed Students Student-Teacher Anomaly Detection With Discriminative Latent Embeddings 具有判别性潜在嵌入的不知情学生师生异常检测
AOWS Adaptive and Optimal Network Width Search With Latency Constraints 具有延迟约束的 AOWS 自适应和最优网络宽度搜索
MINA Convex Mixed-Integer Programming for Non-Rigid Shape Alignment 用于非刚性形状对齐的 MINA 凸混合整数规划
Classifying Segmenting and Tracking Object Instances in Video with Mask 使用掩码对视频中的分割和跟踪对象实例进行分类
Making Better Mistakes Leveraging Class Hierarchies With Deep Networks 利用深度网络的类层次结构犯下更好的错误
DUNIT Detection-Based Unsupervised Image-to-Image Translation 基于 DUNIT 检测的无监督图像到图像转换
Normalizing Flows With Multi-Scale Autoregressive Priors 使用多尺度自回归先验规范化流
A Sparse Resultant Based Method for Efficient Minimal Solvers 一种高效最小求解器的基于稀疏结果的方法
Reinforced Feature Points Optimizing Feature Detection and Description for a 强化特征点优化特征检测和描述
Sketch Less for More On-the-Fly Fine-Grained Sketch-Based Image Retrieval 少写草图以获得更多即时基于细粒度草图的图像检索
Deep 3D Capture Geometry and Reflectance From Sparse Multi-View Images 从稀疏多视图图像中获取深度 3D 几何和反射率
ENSEI Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving ENSEI 通过频域同态卷积进行高效安全推理以保护隐私
Seeing Through Fog Without Seeing Fog Deep Multimodal Sensor Fusion 看透雾而不看雾 深度多模态传感器融合
Synchronizing Probability Measures on Rotations via Optimal Transport 通过最优传输同步旋转概率测度
Defending Against Universal Attacks Through Selective Feature Regeneration 通过选择性特征再生防御普遍攻击
Two-Shot Spatially-Varying BRDF and Shape Estimation 两次空间变化的 BRDF 和形状估计
DeepDeform Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised Data DeepDeform Learning Non-Rigid RGB-D Reconstruction with Semi-Supervised Data
Learning a Neural Solver for Multiple Object Tracking 学习用于多对象跟踪的神经求解器
Rethinking Zero-Shot Video Classification End-to-End Training for Realistic Applications 重新思考针对实际应用的零镜头视频分类端到端培训
Solving Jigsaw Puzzles With Eroded Boundaries 解决具有侵蚀边界的拼图游戏
3FabRec Fast Few-Shot Face Alignment by Reconstruction 3FabRec 重建快速少镜头面对齐
Neural Head Reenactment with Latent Pose Descriptors 具有潜在姿势描述符的神经头部重演
nuScenes A Multimodal Dataset for Autonomous Driving nuScenes 用于自动驾驶的多模式数据集
Generalizing Hand Segmentation in Egocentric Videos With Uncertainty-Guided Model Adaptation 通过不确定性引导的模型自适应在以自我为中心的视频中推广手部分割
Learning a Unified Sample Weighting Network for Object Detection 学习用于目标检测的统一样本加权网络
Reconstruct Locally Localize Globally A Model Free Method for Object 重构局部局部化全局对象的无模型方法
Rethinking Differentiable Search for Mixed-Precision Neural Networks 重新思考混合精度神经网络的可微搜索
ZeroQ A Novel Zero Shot Quantization Framework ZeroQ 一种新颖的零镜头量化框架
Appearance Shock Grammar for Fast Medial Axis Extraction From Real 从实数中快速提取中轴的外观冲击文法
Sign Language Transformers Joint End-to-End Sign Language Recognition and Translation 手语变形金刚联合端到端手语识别和翻译
D2Det Towards High Quality Object Detection and Instance Segmentation D2Det 迈向高质量目标检测和实例分割
Domain Balancing Face Recognition on Long-Tailed Domains 长尾域上的域平衡人脸识别
Few-Shot Video Classification via Temporal Alignment 通过时间对齐的少镜头视频分类
Prime Sample Attention in Object Detection 目标检测中的主要样本注意
Stereoscopic Flash and No-Flash Photography for Shape and Albedo Recovery 用于形状和反照率恢复的立体闪光和无闪光摄影
Scalable Uncertainty for Computer Vision With Functional Variational Inference 具有功能变分推理的计算机视觉的可扩展不确定性
Modeling the Background for Incremental Learning in Semantic Segmentation 为语义分割中的增量学习建模背景
What It Thinks Is Important Is Important Robustness Transfers Through 它认为重要的是重要的健壮性通过
Attention-Driven Cropping for Very High Resolution Facial Landmark Detection 用于超高分辨率面部地标检测的注意力驱动裁剪
Data Uncertainty Learning in Face Recognition 人脸识别中的数据不确定性学习
Synthetic Learning Learn From Distributed Asynchronized Discriminator GAN Without Sharing 综合学习从分布式异步鉴别器 GAN 中学习，无需共享
Weakly-Supervised Semantic Segmentation via Sub-Category Exploration 通过子类别探索的弱监督语义分割
Neural Topological SLAM for Visual Navigation 用于视觉导航的神经拓扑 SLAM
JA-POLS A Moving-Camera Background Model via Joint Alignment and Partially-Overlapping JA-POLS 通过关节对齐和部分重叠的运动相机背景模型
3D Sketch-Aware Semantic Scene Completion via Semi-Supervised Structure Prior 通过半监督结构先验完成 3D 草图感知语义场景完成
A Hierarchical Graph Network for 3D Object Detection on Point 用于点上 3D 对象检测的分层图网络
A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection 一种用于半监督阴影检测的多任务均值教师
A Neural Rendering Framework for Free-Viewpoint Relighting 用于自由视点重新照明的神经渲染框架
Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation 联合自监督时域自适应的动作分割
Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment 用于图像美学评估的自适应分数扩张卷积网络
AdderNet Do We Really Need Multiplications in Deep Learning AdderNet 我们真的需要深度学习中的乘法吗
Adversarial Robustness From Self-Supervised Pre-Training to Fine-Tuning 从自我监督预训练到微调的对抗鲁棒性
Auto-Tuning Structured Light by Optical Stochastic Gradient Descent 通过光学随机梯度下降自动调谐结构光
BANet Bidirectional Aggregation Network With Occlusion Handling for Panoptic Segmentation 用于全景分割的具有遮挡处理的 BANet 双向聚合网络
Better Captioning With Sequence-Level Exploration 使用序列级探索更好地字幕
BlendMask Top-Down Meets Bottom-Up for Instance Segmentation BlendMask 自上而下与自下而上的实例分割相遇
BSP-Net Generating Compact Meshes via Binary Space Partitioning BSP-Net 通过二进制空间分区生成紧凑网格
Camera Trace Erasing 相机痕迹擦除
Cops-Ref A New Dataset and Task on Compositional Referring Expression Cops-Ref 组合引用表达式的新数据集和任务
Counterfactual Samples Synthesizing for Robust Visual Question Answering 用于鲁棒视觉问答的反事实样本合成
Cross-View Tracking for Multi-Human 3D Pose Estimation at Over 100 多人 3D 姿势估计的交叉视图跟踪超过 100
Data-Efficient Semi-Supervised Learning by Reliable Edge Mining 可靠边缘挖掘的数据高效半监督学习
Domain Adaptive Image-to-Image Translation 域自适应图像到图像转换
DSGN Deep Stereo Geometry Network for 3D Object Detection 用于 3D 对象检测的 DSGN 深度立体几何网络
Dynamic Convolution Attention Over Convolution Kernels 卷积核上的动态卷积注意力
End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization 通过反向传播 PnP 优化实现端到端可学习几何视觉
Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning 具有层次图推理的细粒度视频文本检索
Frequency Domain Compact 3D Convolutional Neural Networks 频域紧凑型 3D 卷积神经网络
G2L-Net Global to Local Network for Real-Time 6D Pose Estimation 用于实时 6D 姿态估计的 G2L-Net 全局到本地网络
Harmonizing Transferability and Discriminability for Adapting Object Detectors 协调适应对象检测器的可迁移性和可辨别性
Image Search With Text Feedback by Visiolinguistic Attention Learning 视觉语言注意学习的文本反馈图像搜索
IMRAM Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text 用于跨模态图像文本的 IMRAM 迭代匹配与循环注意记忆
Intelligent Home 3D Automatic 3D-House Design From Linguistic Descriptions Only 智能家居 3D 自动 3D 房屋设计仅来自语言描述
Label Distribution Learning on Auxiliary Label Space Graphs for Facial 面部辅助标签空间图的标签分布学习
Learning a Weakly-Supervised Video Actor-Action Segmentation Model With a Wise 使用 Wise 学习弱监督视频演员-动作分割模型
Learning Canonical Shape Space for Category-Level 6D Object Pose and 学习类别级 6D 对象姿势的规范形状空间和
Memory Enhanced Global-Local Aggregation for Video Object Detection 用于视频对象检测的内存增强全局-局部聚合
MnasFPN Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile 用于移动目标检测的 MnasFPN 学习延迟感知金字塔架构
MonoPair Monocular 3D Object Detection Using Pairwise Spatial Relationships 使用成对空间关系的 MonoPair 单目 3D 对象检测
Network Adjustment Channel Search Guided by FLOPs Utilization Ratio FLOPs利用率引导的网络调整通道搜索
Norm-Aware Embedding for Efficient Person Search 用于高效人员搜索的规范感知嵌入
OASIS A Large-Scale Dataset for Single Image 3D in the OASIS 中单幅图像 3D 的大规模数据集
One-Shot Adversarial Attacks on Visual Tracking With Dual Attention 具有双重注意的视觉跟踪的一次性对抗性攻击
PuppeteerGAN Arbitrary Portrait Animation With Semantic-Aware Appearance Transformation 具有语义感知外观转换的 PuppeteerGAN 任意人像动画
Reusing Discriminators for Encoding Towards Unsupervised Image-to-Image Translation 重用鉴别器进行无监督图像到图像转换的编码
Salience-Guided Cascaded Suppression Network for Person Re-Identification 用于人员重新识别的显着性级联抑制网络
Say As You Wish Fine-Grained Control of Image Caption Generation 随心所欲 对图像标题生成进行细粒度控制
Selective Transfer With Reinforced Transfer Network for Partial Domain Adaptation 用于部分域适应的增强传输网络的选择性传输
Siamese Box Adaptive Network for Visual Tracking 用于视觉跟踪的连体框自适应网络
SLV Spatial Likelihood Voting for Weakly Supervised Object Detection 用于弱监督目标检测的 SLV 空间似然投票
State-Aware Tracker for Real-Time Video Object Segmentation 用于实时视频对象分割的状态感知跟踪器
Stochastic Sparse Subspace Clustering 随机稀疏子空间聚类
Unsupervised Learning of Intrinsic Structural Representation Points 内在结构表示点的无监督学习
CascadePSP Toward Class-Agnostic and Very High-Resolution Segmentation via Global and CascadePSP 通过全局和
Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness 使用具有不确定性感知的自适应薄体积表示的深度立体声
Explaining Knowledge Distillation by Quantifying the Knowledge 通过量化知识来解释知识蒸馏
HigherHRNet Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation HigherHRNet Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
Inter-Task Association Critic for Cross-Resolution Person Re-Identification Inter-Task Association Critic for Cross-Resolution Person Re-Identification
Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention 使用离散高斯混合似然和注意力学习图像压缩
Panoptic-DeepLab A Simple Strong and Fast Baseline for Bottom-Up Panoptic Panoptic-DeepLab 自下而上 Panoptic 的简单强大且快速的基线
RiFeGAN Rich Feature Generation for Text-to-Image Synthesis From Prior Knowledge RiFeGAN 基于先验知识的文本到图像合成的丰富特征生成
Skeleton-Based Action Recognition With Shift Graph Convolutional Network 基于骨架的动作识别与移位图卷积网络
Time Flies Animating a Still Image With Time-Lapse Video As 时光飞逝 使用延时视频为静止图像制作动画
Non-Local Neural Networks With Grouped Bilinear Attentional Transforms 具有分组双线性注意变换的非局部神经网络
Implicit Functions in Feature Space for 3D Shape Reconstruction and 特征空间中的隐式函数用于 3D 形状重建和
Towards Efficient Model Compression via Learned Global Ranking 通过学习的全球排名实现高效模型压缩
Agriculture-Vision A Large Aerial Image Database for Agricultural Pattern Analysis Agriculture-Vision 用于农业模式分析的大型航空影像数据库
Assessing Image Quality Issues for Real-World Problems 评估实际问题的图像质量问题
When to Use Convolutional Neural Networks for Inverse Problems 何时使用卷积神经网络解决逆问题
Evaluating Weakly Supervised Object Localization Methods Right 正确评估弱监督对象定位方法
Cars Cant Fly Up in the Sky Improving Urban-Scene Segmentation 汽车不能在天空中飞起来改善城市场景分割
Hi-CMD Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification 用于可见红外人员重新识别的 Hi-CMD 分层交叉模态解缠结
Scene-Adaptive Video Frame Interpolation via Meta-Learning 基于元学习的场景自适应视频帧插值
StarGAN v2 Diverse Image Synthesis for Multiple Domains StarGAN v2 多域的多样化图像合成
Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture 通过相关引导混合对损坏输出进行任务无关的鲁棒学习
Detecting Attended Visual Targets in Video 检测视频中有人参与的视觉目标
Effectively Unbiased FID and Inception Score and Where to Find 有效无偏的 FID 和初始分数以及在哪里可以找到
Deep Non-Line-of-Sight Reconstruction 深度非视线重建
Deep Global Registration 深度全球注册
High-Dimensional Convolutional Networks for Geometric Pattern Recognition 用于几何模式识别的高维卷积网络
Learning Geocentric Object Pose in Oblique Monocular Images 学习倾斜单目图像中的地心物体姿势
P-nets Deep Polynomial Neural Networks P-nets 深度多项式神经网络
Detection in Crowded Scenes One Proposal Multiple Predictions 拥挤场景中的检测一建议多重预测
A Context-Aware Loss Function for Action Spotting in Soccer Videos 用于足球视频中动作识别的上下文感知损失函数
Bodies at Rest 3D Human Pose and Shape Estimation From 静止的身体 3D 人体姿势和形状估计
Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors 使用影响函数和最近邻检测对抗样本
Editing in Style Uncovering the Local Semantics of GANs 风格编辑揭示 GAN 的局部语义
DoveNet Deep Image Harmonization via Domain Verification 通过域验证的 DoveNet 深度图像协调
Attention-Based Context Aware Reasoning for Situation Recognition 用于情境识别的基于注意力的上下文感知推理
Computing the Testing Error Without a Testing Set 在没有测试集的情况下计算测试误差
Meshed-Memory Transformer for Image Captioning 用于图像字幕的网状内存转换器
Context-Aware Human Motion Prediction 上下文感知人体运动预测
GanHand Predicting Human Grasp Affordances in Multi-Object Scenes GanHand 预测多对象场景中的人类掌握能力
Estimating Low-Rank Region Likelihood Maps 估计低秩区域似然图
Gradually Vanishing Bridge for Adversarial Domain Adaptation 对抗领域适应的逐渐消失的桥梁
Learning Dynamic Relationships for 3D Human Motion Prediction 学习用于 3D 人体运动预测的动态关系
Towards Discriminability and Diversity Batch Nuclear-Norm Maximization Under Label Insufficient 在标签不足的情况下实现可辨别性和多样性批量核范数最大化
Exploiting Joint Robustness to Adversarial Perturbations 利用联合鲁棒性应对对抗性扰动
High-Performance Long-Term Tracking With Meta-Updater 使用 Meta-Updater 进行高性能长期跟踪
Neural Point Cloud Rendering via Multi-Plane Projection 基于多平面投影的神经点云渲染
SG-NN Sparse Generative Neural Networks for Self-Supervised Scene Completion of 用于自监督场景完成的 SG-NN 稀疏生成神经网络
Probabilistic Regression for Visual Tracking 视觉跟踪的概率回归
Multi-Scale Fusion Subspace Clustering Using Similarity Constraint 使用相似性约束的多尺度融合子空间聚类
On the Detection of Digital Face Manipulation 论数字人脸处理的检测
Your Local GAN Designing Two Dimensional Local Attention Mechanisms for 你的本地 GAN 设计二维局部注意力机制
Sequential Mastery of Multiple Visual Tasks Networks Naturally Learn to 多个视觉任务的顺序掌握网络自然地学会
Lange Unsupervised Model Personalization While Preserving Privacy and Scalability An OpenLange 无监督模型个性化，同时保持隐私和可扩展性开放
RoboTHOR An Open Simulation-to-Real Embodied AI Platform RoboTHOR 一个开放的仿真到真实的体现 AI 平台
Optimal least-squares solution to the hand-eye calibration problem 手眼标定问题的最优最小二乘解
CvxNet Learnable Convex Decomposition CvxNet 可学习的凸分解
Detail-recovery Image Deraining via Context Aggregation Networks 通过上下文聚合网络进行细节恢复图像去雨
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning 通过 3D 模仿对比学习生成解开和可控的人脸图像
RetinaFace Single-Shot Multi-Level Face Localisation in the Wild 野外 RetinaFace 单次多级人脸定位
Semantic Image Manipulation Using Scene Graphs 使用场景图的语义图像处理
Guided Variational Autoencoder for Disentanglement Learning 用于解缠结学习的引导变分自动编码器
Learning Depth-Guided Convolutions for Monocular 3D Object Detection 学习用于单目 3D 目标检测的深度引导卷积
Minimal Solutions to Relative Pose Estimation From Two Views Sharing 从两个视图共享的相对姿态估计的最小解决方案
Robust Homography Estimation via Dual Principal Component Pursuit 基于双主成分追踪的鲁棒单应性估计
Learning to Observe Approximating Human Perceptual Thresholds for Detection of 学习观察近似人类感知阈值以检测
Deep Geometric Functional Maps Robust Feature Learning for Shape Correspondence 用于形状对应的深度几何功能图鲁棒特征学习
Benchmarking Adversarial Robustness on Image Classification 图像分类的对抗性鲁棒性基准测试
Bi-Directional Interaction Network for Person Search 人员搜索的双向交互网络
CentripetalNet Pursuing High-Quality Keypoint Pairs for Object Detection CentripetalNet 追求用于目标检测的高质量关键点对
Fashion Editing With Adversarial Parsing Learning 对抗性解析学习的时尚编辑
Instance Guided Proposal Network for Person Search 用于人员搜索的实例引导建议网络
Multi-Scale Boosted Dehazing Network With Dense Feature Fusion 具有密集特征融合的多尺度增强去雾网络
Robust Superpixel-Guided Attentional Adversarial Attack 强大的超像素引导注意力对抗攻击
Self-Robust 3D Point Recognition via Gather-Vector Guidance 通过聚集向量引导的自鲁棒 3D 点识别
What Can Be Transferred Unsupervised Domain Adaptation for Endoscopic Lesions 什么可以转移内窥镜病变的无监督域适应
HOPE-Net A Graph-Based Model for Hand-Object Pose Estimation HOPE-Net 一种基于图的手物体姿态估计模型
Unsupervised Magnification of Posture Deviations Across Subjects 跨受试者姿势偏差的无监督放大
The GAN That Warped Semantic Attribute Editing With Unpaired Data 使用不成对数据扭曲语义属性编辑的 GAN
Action Modifiers Learning From Adverbs in Instructional Videos 从教学视频中的副词学习动作修饰语
Associate-3Ddet Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection 用于 3D 点云对象检测的 Associate-3Ddet 感知到概念关联
Correlation-Guided Attention for Corner Detection Based Visual Tracking 基于角点检测的视觉跟踪的相关引导注意
Learning Invariant Representation for Unsupervised Image Restoration 无监督图像恢复的学习不变表示
SpineNet Learning Scale-Permuted Backbone for Recognition and Localization 用于识别和定位的 SpineNet Learning Scale-Permuted Backbone
Adversarial Camouflage Hiding Physical-World Attacks With Natural Styles 用自然风格隐藏物理世界攻击的对抗伪装
Cross-Spectral Face Hallucination via Disentangling Independent Factors 通过解开独立因素的交叉光谱面部幻觉
Varicolored Image De-Hazing 杂色图像去雾
Panoptic-Based Image Synthesis 基于全景的图像合成
Vec2Face Unveil Human Faces From Their Blackbox Features in Face Vec2Face 从他们的黑盒特征中揭示人脸
Watch Your Up-Convolution CNN Based Generative Deep Neural Networks Are 观看基于上卷积 CNN 的生成深度神经网络
Learning User Representations for Open Vocabulary Image Hashtag Prediction 学习用于开放词汇图像标签预测的用户表示
Counting Out Time Class Agnostic Video Repetition Counting in the 计数时间类不可知的视频重复计数
Structured Multi-Hashing for Model Compression 用于模型压缩的结构化多重哈希
Tangent Images for Mitigating Spherical Distortion 用于减轻球面失真的切线图像
Use the Force Luke Learning to Predict Physical Forces by 使用力卢克学习预测物理力
Smooth Shells Multi-Scale Shape Registration With Functional Maps 使用功能图进行平滑壳多尺度形状配准
Uncertainty-Aware CNNs for Depth Completion Uncertainty from Beginning to End 从头到尾深度完成不确定性的不确定性感知 CNN
Fast Sparse ConvNets 快速稀疏卷积网络
Meta-Learning of Neural Architectures for Few-Shot Learning 用于少量学习的神经架构元学习
3D-MPA Multi-Proposal Aggregation for 3D Semantic Instance Segmentation 用于 3D 语义实例分割的 3D-MPA 多建议聚合
Photometric Stereo via Discrete Hypothesis-and-Test Search 通过离散假设和测试搜索的光度立体
Oops Predicting Unintentional Action in Video 糟糕，预测视频中的无意动作
A Disentangling Invertible Interpretation Network for Explaining Latent Representations 用于解释潜在表示的解缠结可逆解释网络
Learning to Discriminate Information for Online Action Detection 学习区分在线动作检测的信息
Differentiable Adaptive Computation Time for Visual Reasoning 视觉推理的可微自适应计算时间
Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation 用于多人 3D 姿势估计的压缩体积热图
TRPLP - Trifocal Relative Pose From Lines at Points TRPLP - 点线的三焦相对位姿
Camouflaged Object Detection 伪装物体检测
Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector 使用 Attention-RPN 和多关系检测器的 Few-Shot 目标检测
FGN Fully Guided Network for Few-Shot Instance Segmentation FGN 完全引导网络，用于少量实例分割
GaitPart Temporal Part-Based Model for Gait Recognition GaitPart 基于时间部分的步态识别模型
Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation 使用类内鉴别器学习用于弱监督语义分割的整体对象
Learning Longterm Representations for Person Re-Identification Using Radio Signals 学习使用无线电信号重新识别人员的长期表示
Taking a Deeper Look at Co-Salient Object Detection 深入研究共显着目标检测
Connect-and-Slice An Hybrid Approach for Reconstructing 3D Objects Connect-and-Slice 一种用于重建 3D 对象的混合方法
Densely Connected Search Space for More Flexible Neural Architecture Search 用于更灵活的神经架构搜索的密集连接搜索空间
GraspNet-1Billion A Large-Scale Benchmark for General Object Grasping GraspNet-1Billion 通用对象抓取的大规模基准
Perceptual Quality Assessment of Smartphone Photography 智能手机摄影的感知质量评估
TPNet Trajectory Proposal Network for Motion Prediction 用于运动预测的 TPNet 轨迹提议网络
SCT Set Constrained Temporal Transformer for Set Supervised Action Segmentation 用于集监督动作分割的 SCT 集约束时间变换器
X3D Expanding Architectures for Efficient Video Recognition 用于高效视频识别的 X3D 扩展架构
Three-Dimensional Reconstruction of Human Interactions 人机交互的三维重构
ScrabbleGAN Semi-Supervised Varying Length Handwritten Text Generation ScrabbleGAN 半监督变长手写文本生成
Information-Driven Direct RGB-D Odometry 信息驱动的直接 RGB-D 里程计
How Much Time Do You Have Modeling Multi-Duration Saliency 您有多少时间建模多持续时间显着性
gDLS Generalized Pose-and-Scale Estimation Given Scale and Gravity Priors 给定尺度和重力先验的 gDLS 广义姿态和尺度估计
JL-DCF Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient 用于 RGB-D 显着性的 JL-DCF 联合学习和密集协作融合框架
Joint Texture and Geometry Optimization for RGB-D Reconstruction RGB-D 重建的联合纹理和几何优化
MCEN Bridging Cross-Modal Gap between Cooking Recipes and Dish Images MCEN 弥合烹饪食谱和菜肴图像之间的跨模式差距
Neural Implicit Embedding for Point Cloud Analysis 用于点云分析的神经隐式嵌入
Learning Generative Models of Shape Handles 学习形状手柄的生成模型
Wish You Were Here Context-Aware Human Generation 希望你在这里 具有上下文意识的人类一代
Music Gesture for Visual Sound Separation 用于视觉声音分离的音乐手势
AdversarialNAS Adversarial Neural Architecture Search for GANs AdversarialNAS 对抗性神经架构搜索 GAN
Discrete Model Compression With Resource Constraint for Deep Neural Networks 具有资源约束的深度神经网络离散模型压缩
Flow Contrastive Estimation of Energy-Based Models 基于能量的模型的流动对比估计
GraphTER Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding GraphTER 通过自动编码对图变换等变表示进行无监督学习
Learning to Optimize on SPD Manifolds 学习优化 SPD 歧管
Listen to Look Action Recognition by Previewing Audio 通过预览音频收听 Look 动作识别
MTL-NAS Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning 面向通用多任务学习的 MTL-NAS 任务不可知神经架构搜索
Multi-Modal Graph Neural Network for Joint Reasoning on Vision and 用于视觉和视觉联合推理的多模态图神经网络
Pose-Guided Visible Part Matching for Occluded Person ReID 被遮挡人员 ReID 的姿势引导可见部分匹配
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking 用于视觉跟踪的递归最小二乘估计器辅助在线学习
SketchyCOCO Image Generation From Freehand Scene Sketches 从手绘场景草图生成 SketchyCOCO 图像
VectorNet Encoding HD Maps and Agent Dynamics From Vectorized Representation VectorNet 从矢量化表示编码高清地图和代理动态
Satellite Image Time Series Classification With Pixel-Set Encoders and Temporal 使用像素集编码器和时间序列进行卫星图像时间序列分类
Actor-Transformers for Group Activity Recognition 用于群体活动识别的 Actor-Transformers
Video to Events Recycling Video Datasets for Event Cameras 视频到事件 为事件摄像机回收视频数据集
Averaging Essential and Fundamental Matrices in Collinear Camera Settings 在共线相机设置中平均基本矩阵和基本矩阵
Local Deep Implicit Functions for 3D Shape 3D 形状的局部深层隐式函数
Learning Representations by Predicting Bags of Visual Words 通过预测视觉词袋来学习表示
Learning Multiview 3D Point Cloud Registration 学习多视图 3D 点云配准
Eternal Sunshine of the Spotless Net Selective Forgetting in Deep 一尘不染的永恒阳光 选择性遗忘在深处
ReSprop Reuse Sparsified Backpropagation ReSprop 重用稀疏反向传播
A Quantum Computational Approach to Correspondence Problems on Point Sets 点集对应问题的一种量子计算方法
Geometrically Principled Connections in Graph Neural Networks 图神经网络中的几何原理连接
Learning Temporal Co-Attention Models for Unsupervised Video Action Localization 学习用于无监督视频动作定位的时间共同注意模型
Achieving Robustness in the Wild via Adversarial Mixing With Disentangled 通过对抗性混合与 Disentangled 实现野外鲁棒性
Dynamic Neural Relational Inference 动态神经关系推理
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching 高分辨率多视图立体和立体匹配的级联成本量
Image Processing Using Multi-Code GAN Prior 使用多码 GAN 先验的图像处理
Improving the Robustness of Capsule Networks to Image Affine Transformations 提高胶囊网络对图像仿射变换的鲁棒性
Spherical Space Domain Adaptation With Robust Pseudo-Label Loss 具有鲁棒伪标签损失的球面空间域自适应
Generative Hybrid Representations for Activity Forecasting With No-Regret Learning 无悔学习活动预测的生成混合表示
Minimal Solutions for Relative Pose With a Single Affine Correspondence 具有单个仿射对应的相对位姿的最小解
Through Fog High-Resolution Imaging Using Millimeter Wave Radar 使用毫米波雷达通过雾高分辨率成像
Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision 通过 Fisher 内核自我监督的有偏数据集的深度主动学习
FeatureFlow Robust Video Interpolation via Structure-to-Texture Generation 通过结构到纹理生成的 FeatureFlow 鲁棒视频插值
3D Packing for Self-Supervised Monocular Depth Estimation 用于自监督单目深度估计的 3D 打包
A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image 一种用于 4D 动态医学图像的时空体积插值网络
Attentive Weights Generation for Few Shot Learning via Information Maximization 通过信息最大化为少数镜头学习生成注意力权重
AugFPN Improving Multi-Scale Feature Learning for Object Detection AugFPN 改进用于目标检测的多尺度特征学习
Closed-Loop Matters Dual Regression Networks for Single Image Super-Resolution 闭环对单图像超分辨率的双回归网络很重要
Density-Aware Feature Embedding for Face Clustering 用于人脸聚类的密度感知特征嵌入
DMCP Differentiable Markov Channel Pruning for Neural Networks 神经网络的 DMCP 可微马尔可夫通道修剪
Hit-Detector Hierarchical Trinity Architecture Search for Object Detection Hit-Detector Hierarchical Trinity Architecture Search for Object Detection
Iterative Context-Aware Graph Inference for Visual Dialog 视觉对话的迭代上下文感知图推理
Learning Meta Face Recognition in Unseen Domains 在未知领域学习元人脸识别
Multi-Dimensional Pruning A Unified Framework for Model Compression 多维剪枝模型压缩的统一框架
Normalized and Geometry-Aware Self-Attention Network for Image Captioning 用于图像描述的归一化和几何感知自注意力网络
On Positive-Unlabeled Classification in GAN 关于 GAN 中的正无标签分类
Online Knowledge Distillation via Collaborative Learning 通过协作学习进行在线知识提炼
Organ at Risk Segmentation for Head and Neck Cancer Using 头颈癌的高危器官分割使用
SiamCAR Siamese Fully Convolutional Classification and Regression for Visual Tracking 用于视觉跟踪的 SiamCAR Siamese 全卷积分类和回归
When NAS Meets Robustness In Search of Robust Architectures Against 当 NAS 在寻找稳健架构时遇到稳健性
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement 低光图像增强的零参考深度曲线估计
PatchVAE Learning Local Latent Codes for Recognition PatchVAE 学习本地潜在代码进行识别
Rethinking Depthwise Separable Convolutions How Intra-Kernel Correlations Lead to Improved 重新思考深度可分离卷积内核内相关性如何导致改进
DeepCap Monocular Human Performance Capture Using Weak Supervision 使用弱监督的 DeepCap 单目人体性能捕获
HOnnotate A Method for 3D Annotation of Hand and Object HOnnotate 一种对手和物体进行 3D 标注的方法
GhostNet More Features From Cheap Operations GhostNet 来自廉价操作的更多功能
Joint Training of Variational Auto-Encoder and Latent Energy-Based Model 变分自编码器与基于潜在能量的模型的联合训练
Learning the Redundancy-Free Features for Generalized Zero-Shot Object Recognition 学习用于广义零样本目标识别的无冗余特征
Neuromorphic Camera Guided High Dynamic Range Imaging 神经形态摄像机引导的高动态范围成像
OccuSeg Occupancy-Aware 3D Instance Segmentation OccuSeg 占用感知 3D 实例分割
RMP-SNN Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and RMP-SNN 残膜电位神经元，用于实现更深层次的高精度和
SPARE3D A Dataset for SPAtial REasoning on Three-View Line Drawings SPARE3D 用于三视图线图空间推理的数据集
DualSDF Semantic Shape Manipulation Using a Two-Level Representation 使用两级表示的 DualSDF 语义形状操作
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training 通过预训练学习视觉和语言导航的通用代理
ILFO Adversarial Attack on Adaptive Neural Networks ILFO 对自适应神经网络的对抗性攻击
Space-Time-Aware Multi-Resolution Video Enhancement 时空感知多分辨率视频增强
The Knowledge Within Methods for Data-Free Model Compression 无数据模型压缩方法中的知识
Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated 用于未注释癌症亚型分类的多尺度域对抗多实例 CNN
Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction 利用光度一致性随着时间的推移进行稀疏监督的手对象重建
MPM Joint Representation of Motion and Position Map for Cell 细胞运动和位置图的 MPM 联合表示
Nonparametric Object and Parts Modeling With Lie Group Dynamics 使用李群动力学的非参数对象和零件建模
Defending and Harnessing the Bit-Flip Based Adversarial Weight Attack 防御和利用基于位翻转的对抗性权重攻击
Epipolar Transformers 对极变压器
Incremental Learning in Online Scenario 在线场景中的增量学习
Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration 深度卷积神经网络加速的学习过滤器修剪标准
MiLeNAS Efficient Neural Architecture Search via Mixed-Level Reformulation 通过混合级重构的 MiLeNAS 高效神经架构搜索
Momentum Contrast for Unsupervised Visual Representation Learning 无监督视觉表示学习的动量对比
PVN3D A Deep Point-Wise 3D Keypoints Voting Network for 6DoF PVN3D 用于 6DoF 的深度 Point-Wise 3D 关键点投票网络
Structure Aware Single-Stage 3D Object Detection From Point Cloud 基于点云的结构感知单阶段 3D 对象检测
A Lighting-Invariant Point Processor for Shading 用于着色的光照不变点处理器
Leveraging 2D Data to Learn Textured 3D Mesh Generation 利用 2D 数据学习带纹理的 3D 网格生成
Learning a Neural 3D Texture Space From 2D Exemplars 从 2D 样本中学习神经 3D 纹理空间
A Multi-Hypothesis Approach to Color Constancy 颜色恒定性的多假设方法
Learning to Autofocus 学习自动对焦
PointGMM A Neural GMM Network for Point Clouds PointGMM 用于点云的神经 GMM 网络
Exploit Clues From Views Self-Supervised and Regularized Learning for Multiview 利用视图中的线索进行多视图的自我监督和正则化学习
EPOS Estimating 6D Pose of Objects With Symmetries EPOS 估计具有对称性的物体的 6D 位姿
Augment Your Batch Improving Generalization Through Instance Repetition 通过实例重复增强您的批次提高泛化能力
Distilling Image Dehazing With Heterogeneous Task Imitation 使用异构任务模仿蒸馏图像去雾
Learning to Detect Important People in Unlabelled Images for Semi-Supervised 学习在半监督的未标记图像中检测重要人物
Composed Query Image Retrieval Using Locally Bounded Features 使用局部有界特征的组合查询图像检索
Inter-Region Affinity Distillation for Road Marking Segmentation 用于道路标记分割的区域间亲和蒸馏
Learning to Structure an Image With Few Colors 学习用少量颜色构建图像
Real-Time Panoptic Segmentation From Dense Detections 密集检测的实时全景分割
RevealNet Seeing Behind Objects in RGB-D Scans RevealNet 在 RGB-D 扫描中看到物体背后
Strip Pooling Rethinking Spatial Pooling for Scene Parsing Strip Pooling 重新思考用于场景解析的空间池化
ViBE Dressing for Diverse Body Shapes 适合不同体型的 ViBE 敷料
Generalized ODIN Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data 广义 ODIN 检测分布外图像而不从分布外数据中学习
Bi-Directional Relationship Inferring Network for Referring Image Segmentation 用于参考图像分割的双向关系推断网络
Collaborative Motion Prediction via Neural Motion Message Passing 通过神经运动消息传递的协同运动预测
Creating Something From Nothing Unsupervised Knowledge Distillation for Cross-Modal Hashing 从无到有的无监督知识蒸馏用于跨模态散列
DSNAS Direct Neural Architecture Search Without Parameter Retraining 无参数再训练的 DSNAS 直接神经架构搜索
Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA 用于 TextVQA 的指针增强多模态变换器的迭代答案预测
Learning to Segment the Tail 学习分割尾巴
Progressive Relation Learning for Group Activity Recognition 用于群体活动识别的渐进式关系学习
RandLA-Net Efficient Semantic Segmentation of Large-Scale Point Clouds 大规模点云的 RandLA-Net 高效语义分割
Single-Stage 6D Object Pose Estimation 单阶段 6D 物体姿态估计
Temporally Distributed Networks for Fast Video Semantic Segmentation 用于快速视频语义分割的时间分布式网络
Unsupervised Domain Adaptation With Hierarchical Gradient Synchronization 具有分层梯度同步的无监督域自适应
What You See is What You Get Exploiting Visibility for 所见即所得
Adversarial Texture Optimization From RGB-D Scans 来自 RGB-D 扫描的对抗性纹理优化
An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks 一种用于深度神经网络的内部协变量移位边界算法
An Investigation Into the Stochasticity of Batch Whitening 批量美白随机性调查
ARCH Animatable Reconstruction of Clothed Humans ARCH 穿衣人的动画重建
ClusterVO Clustering Moving Instances and Estimating Visual Odometry for Self ClusterVO 聚类移动实例和估计自身的视觉里程计
Controllable Orthogonalization in Training DNNs 训练 DNN 中的可控正交化
CurricularFace Adaptive Curriculum Learning Loss for Deep Face Recognition 用于深度人脸识别的 CurricularFace 自适应课程学习损失
Deep Semantic Clustering by Partition Confidence Maximisation 分区置信度最大化的深度语义聚类
Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic 使用时间聚合网络和动态的快速视频对象分割
Feature-Metric Registration A Fast Semi-Supervised Approach for Robust Point Cloud 特征度量注册一种快速的半监督鲁棒点云方法
Improving Action Segmentation via Graph-Based Temporal Reasoning 通过基于图的时间推理改进动作分割
Interpretable and Accurate Fine-grained Recognition via Region Grouping 通过区域分组进行可解释且准确的细粒度识别
Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment 学习用于跨 ID 人脸重演的身份不变运动表示
NMS by Representative Region Towards Crowded Pedestrian Detection by Proposal NMS by Representative Region to Crowded Pedestrian Detection by Proposal
OctSqueeze Octree-Structured Entropy Model for LiDAR Compression 用于 LiDAR 压缩的 OctSqueeze 八叉树结构熵模型
PF-Net Point Fractal Network for 3D Point Cloud Completion PF-Net Point Fractal Network for 3D Point Cloud Completion
Probability Weighted Compact Feature for Domain Adaptive Retrieval 域自适应检索的概率加权紧凑特征
PropagationNet Propagate Points to Curve to Learn Structure Information PropagationNet 将点传播到曲线以学习结构信息
Real-World Person Re-Identification via Degradation Invariance Learning 通过退化不变学习重新识别真实世界的人
Referring Image Segmentation via Cross-Modal Progressive Comprehension 通过跨模态渐进理解引用图像分割
SQE a Self Quality Evaluation Metric for Parameters Optimization in SQE 参数优化的自我质量评估指标
The Devil Is in the Details Delving Into Unbiased Data 魔鬼在细节中钻研无偏数据
Universal Physical Camouflage Attacks on Object Detectors 对物体探测器的通用物理伪装攻击
Self-Supervised Monocular Scene Flow Estimation 自监督单目场景流估计
A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning 用于多标签零样本学习的共享多注意框架
Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention 通过基于密集属性的注意力的细粒度广义零样本学习
Interactive Multi-Label CNN Learning With Partial Labels 带有部分标签的交互式多标签 CNN 学习
Learning to Super Resolve Intensity Images From Events 从事件中学习超分辨率强度图像
Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks 具有自校正网络的半监督语义图像分割
Low-Rank Compression of Neural Nets Learning the Rank of Each 学习每个等级的神经网络的低等级压缩
Global Optimality for Point Set Registration Using Semidefinite Programming 使用半定规划的点集配准的全局最优性
Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the 基于多视图图像的弱监督 3D 人体姿态学习
Enhancing Generic Segmentation With Learned Region Representations 使用学习的区域表示增强通用分割
DOA-GAN Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery 用于图像复制移动伪造的 DOA-GAN 双阶注意力生成对抗网络
Video Super-Resolution With Temporal Group Attention 具有时间组注意的视频超分辨率
Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation 基于光学非视线物理的 3D 人体姿态估计
Scene Recomposition by Learning-Based ICP 基于学习的ICP场景重构
Can Deep Learning Recognize Subtle Human Activities 深度学习能否识别微妙的人类活动
ActionBytes Learning From Trimmed Videos to Localize Actions ActionBytes 从修剪过的视频中学习以本地化操作
Self-Supervised Learning of Interpretable Keypoints From Unlabelled Videos 未标记视频中可解释关键点的自监督学习
Attack to Explain Deep Representation 攻击解释深度表示
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain 重新思考领域中长尾视觉识别的类平衡方法
Generalized Product Quantization Network for Semi-Supervised Image Retrieval 用于半监督图像检索的广义乘积量化网络
xMUDA Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation xMUDA 用于 3D 语义分割的跨模态无监督域自适应
Learn2Perturb An End-to-End Feature Perturbation Learning to Improve Adversarial Robustness Learn2Perturb 一种端到端的特征扰动学习来提高对抗性鲁棒性
Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics 引导超越局部像素统计的自我监督特征学习
Sparse Layered Graphs for Multi-Object Segmentation 用于多对象分割的稀疏分层图
Action Genome Actions As Compositions of Spatio-Temporal Scene Graphs 动作基因组动作作为时空场景图的组合
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization 用于细粒度视觉分类的注意力卷积二元神经树
Revisiting Saliency Metrics Farthest-Neighbor Area Under Curve 重新审视曲线下的显着性度量最邻近区域
Single-Side Domain Generalization for Face Anti-Spoofing 人脸反欺骗的单边域泛化
Attention Scaling for Crowd Counting 人群计数的注意力缩放
Coherent Reconstruction of Multiple Humans From a Single Image 从单个图像中对多个人进行相干重建
DeeperForensics-1.0 A Large-Scale Dataset for Real-World Face Forgery Detection DeeperForensics-1.0 用于真实世界人脸伪造检测的大规模数据集
End-to-End 3D Point Cloud Instance Segmentation Without Detection 无需检测的端到端 3D 点云实例分割
Fantastic Answers and Where to Find Them Immersive Question-Directed Visual 奇妙的答案以及在哪里可以找到它们 沉浸式问题导向的视觉
In Defense of Grid Features for Visual Question Answering 捍卫视觉问答的网格特征
Learning Event-Based Motion Deblurring 学习基于事件的运动去模糊
Local Implicit Grid Representations for 3D Scenes 3D 场景的局部隐式网格表示
Multi-Scale Progressive Fusion Network for Single Image Deraining 用于单幅图像去雨的多尺度渐进融合网络
Peek-a-Boo Occlusion Reasoning in Indoor Scenes With Plane Representations 具有平面表示的室内场景中的 Peek-a-Boo 遮挡推理
PointGroup Dual-Set Point Grouping for 3D Instance Segmentation 用于 3D 实例分割的 PointGroup 双设定点分组
PSGAN Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup PSGAN Pose and Expression Robust Spatial-Aware GAN 用于可定制的化妆
SDFDiff Differentiable Rendering of Signed Distance Fields for 3D Shape 3D 形状的带符号距离场的 SDFDiff 可微分渲染
SP-NAS Serial-to-Parallel Backbone Search for Object Detection SP-NAS 用于目标检测的串行到并行骨干搜索
AdaBits Neural Network Quantization With Adaptive Bit-Widths 具有自适应位宽的 AdaBits 神经网络量化
Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction 探索高保真和时间一致性视频预测的时空多频分析
Geometric Structure Based and Regularized Depth Estimation From 360 Indoor 360度室内基于几何结构的正则化深度估计
Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and 基于深度组合几何嵌入的光场空间超分辨率和
Style Normalization and Restitution for Generalizable Person Re-Identification 可泛化人物重新识别的风格规范化和恢复
Cross-Modal Cross-Domain Moment Alignment Network for Person Search 用于人员搜索的跨模式跨域矩对齐网络
Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity 使用自我注意和离散视差的自我监督单目训练深度估计
Select to Better Learn Fast and Accurate Deep Learning Using 选择以更好地学习快速准确的深度学习使用
Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation 用于联合目标检测和视点估计的圆柱卷积网络
MMTM Multimodal Transfer Module for CNN Fusion 用于 CNN 融合的 MMTM 多模态传输模块
Deep Polarization Cues for Transparent Object Segmentation 用于透明对象分割的深度极化线索
Benchmarking the Robustness of Semantic Segmentation Models 对语义分割模型的鲁棒性进行基准测试
Noise Robust Generative Adversarial Networks 噪声鲁棒生成对抗网络
Defending Against Model Stealing Attacks With Adaptive Misinformation 使用自适应错误信息防御模型窃取攻击
MSG-GAN Multi-Scale Gradients for Generative Adversarial Networks 用于生成对抗网络的 MSG-GAN 多尺度梯度
Analyzing and Improving the Image Quality of StyleGAN StyleGAN 图像质量分析与改进
Deblurring Using Analysis-Synthesis Networks Pair 使用分析-合成网络对去模糊
On Translation Invariance in CNNs Convolutional Layers Can Exploit Absolute 关于 CNN 中的平移不变性卷积层可以利用 Absolute
Multiple Anchor Learning for Visual Object Detection 视觉对象检测的多锚学习
RGBD-Dog Predicting Canine Pose from RGBD Sensors RGBD-Dog 从 RGBD 传感器预测犬类姿势
RankMI A Mutual Information Maximizing Ranking Loss RankMI A 互信息最大化排名损失
Generalized Zero-Shot Learning via Over-Complete Distribution 通过过完全分布的广义零样本学习
AnimalWeb A Large-Scale Hierarchical Dataset of Annotated Animal Faces AnimalWeb 带注释动物面孔的大规模分层数据集
Hyperbolic Image Embeddings 双曲线图像嵌入
ActiveMoCap Optimized Viewpoint Selection for Active Human Motion Capture 主动人体运动捕捉的 ActiveMoCap 优化视点选择
A Programmatic and Semantic Approach to Explaining and Debugging Neural 一种解释和调试神经网络的程序化和语义化方法
Advisable Learning for Self-Driving Vehicles by Internalizing Observation-to-Action Rules 通过内化观察到行动的规则为自动驾驶汽车提供可取的学习
GroupFace Learning Latent Groups and Constructing Group-Based Representations for Face GroupFace 学习潜在组和构建基于组的人脸表示
Hypergraph Attention Networks for Multimodal Learning 用于多模态学习的超图注意网络
Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation 语义分割领域适应的学习纹理不变表示
Learning to Simulate Dynamic Environments With GameGAN 学习使用 GameGAN 模拟动态环境
M2m Imbalanced Classification via Major-to-Minor Translation 通过从大到小翻译的 M2m 不平衡分类
Modality Shifting Attention Network for Multi-Modal Video Question Answering 用于多模态视频问答的模态转移注意力网络
Modeling Biological Immunity to Adversarial Examples 对对抗样本的生物免疫建模
Proxy Anchor Loss for Deep Metric Learning 深度度量学习的代理锚损失
Regularization on Spatio-Temporally Smoothed Feature for Action Recognition 动作识别时空平滑特征的正则化
Single Image Reflection Removal With Physically-Based Training Images 使用基于物理的训练图像去除单图像反射
Spatially Attentive Output Layer for Image Classification 用于图像分类的空间注意输出层
Transfer Learning From Synthetic to Real-Noise Denoising With Adaptive Instance 使用自适应实例将学习从合成迁移到真实噪声去噪
Video Panoptic Segmentation 视频全景分割4700，全景分割10000
PointRend Image Segmentation As Rendering PointRend 图像分割作为渲染
CONSAC Robust Multi-Model Fitting by Conditional Sample Consensus 基于条件样本一致性的 CONSAC 稳健多模型拟合
Belief Propagation Reloaded Learning BP-Layers for Labeling Problems Belief Propagation Reloaded Learning BP-Layers for Labeling Problems
Embedding Expansion Augmentation in Embedding Space for Deep Metric Learning 在深度度量学习的嵌入空间中嵌入扩展增强
Total Deep Variation for Linear Inverse Problems 线性逆问题的总深度变差
VIBE Video Inference for Human Body Pose and Shape Estimation 用于人体姿势和形状估计的 VIBE 视频推理
Universal Litmus Patterns Revealing Backdoor Attacks in CNNs 揭示 CNN 中后门攻击的通用试金石模式
PhysGAN Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving PhysGAN 为自动驾驶生成物理世界弹性对抗示例
Compositional Convolutional Neural Networks A Deep Architecture With Innate Robustness 组合卷积神经网络具有内在鲁棒性的深层架构
Factorized Higher-Order CNNs With an Application to Spatio-Temporal Emotion Estimation 用于时空情绪估计的分解高阶 CNN
DeepFaceFlow In-the-Wild Dense 3D Facial Motion Estimation DeepFaceFlow In-the-Wild 密集 3D 面部运动估计
Learning Interactions and Relationships Between Movie Characters 学习电影角色之间的互动和关系
Instance Segmentation of Biological Images Using Harmonic Embeddings 使用谐波嵌入的生物图像实例分割
Articulation-Aware Canonical Surface Mapping 关节感知规范曲面映射
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild 弱监督网格卷积手部重建
LUVLi Face Alignment Estimating Landmarks Location Uncertainty and Visibility Likelihood LUVLi 人脸对齐估计地标位置不确定性和可见性可能性
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image 基于部分引导新图像的自我监督 3D 人体姿态估计
Towards Inheritable Models for Open-Set Domain Adaptation 面向开放集域适应的可继承模型
Universal Source-Free Domain Adaptation 通用无源域适配
Normal Assisted Stereo Depth Estimation 正常辅助立体深度估计
Structured Compression by Weight Encryption for Unstructured Pruning and Quantization 用于非结构化剪枝和量化的权重加密结构化压缩
Blur Aware Calibration of Multi-Focus Plenoptic Camera 多焦点全光相机的模糊感知校准
Prior Guided GAN Based Semantic Inpainting 先前引导的基于 GAN 的语义修复
MAST A Memory-Augmented Self-Supervised Tracker MAST 一种记忆增强的自我监督跟踪器
MSeg A Composite Dataset for Multi-Domain Semantic Segmentation MSeg 用于多域语义分割的复合数据集
SaccadeNet A Fast and Accurate Object Detector SaccadeNet 一种快速准确的目标检测器
SampleNet Differentiable Point Cloud Sampling SampleNet 可微分点云采样
Which Is Plagiarism Fashion Image Retrieval Based on Regional Representation 基于区域表征的抄袭时尚图像检索是什么
AvatarMe Realistically Renderable 3D Facial Reconstruction In-the-Wild AvatarMe 真实可渲染的 3D 面部重建在野外
Learning Instance Occlusion for Panoptic Segmentation 全景分割的学习实例遮挡
A Graduated Filter Method for Large Scale Robust Estimation 一种用于大规模鲁棒估计的分级滤波方法
Deep Homography Estimation for Dynamic Scenes 动态场景的深度单应性估计
Going Deeper With Lean Point Networks 使用精益点网络更深入
Guen Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video PredictionGuen 将物理动力学从未知因素中解脱出来，用于无监督视频预测
Hierarchical Conditional Relation Networks for Video Question Answering 用于视频问答的分层条件关系网络
AdaCoF Adaptive Collaboration of Flows for Video Frame Interpolation 视频帧插值流的 AdaCoF 自适应协作
Adversarial Vertex Mixup Toward Better Adversarially Robust Generalization 对抗性顶点混合以实现更好的对抗性鲁棒泛化
CenterMask Real-Time Anchor-Free Instance Segmentation CenterMask 实时无锚实例分割
Continual Learning With Extended Kronecker-Factored Approximate Curvature 扩展克罗内克因子近似曲率的持续学习
Large Scale Video Representation Learning via Relational Graph Clustering 基于关系图聚类的大规模视频表示学习
Learning Augmentation Network via Influence Functions 通过影响函数学习增强网络
MaskGAN Towards Diverse and Interactive Facial Image Manipulation MaskGAN 迈向多样化和交互式面部图像处理
NeuralScale Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks NeuralScale 用于资源受限的深度神经网络的神经元的有效缩放
Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic 使用增强自我参考和密集语义的基于参考的草图图像着色
Structure Boundary Preserving Segmentation for Medical Image With Ambiguous Boundary 具有模糊边界的医学图像的结构保边界分割
TextureFusion High-Quality Texture Acquisition for Real-Time RGB-D Scanning TextureFusion 用于实时 RGB-D 扫描的高质量纹理采集
Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction 用于高保真 3D 人脸重建的不确定性感知网格解码器
Warping Residual Based Image Stitching for Large Parallax 基于翘曲残差的大视差图像拼接
Polarized Reflection Removal With Perfect Alignment in the Wild 在野外完美对齐的偏振反射去除
SegGCN Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel 使用模糊球核的 SegGCN 高效 3D 点云分割
Deep Iterative Surface Normal Estimation 深度迭代表面法线估计
Adaptive Interaction Modeling via Graph Operations Search 通过图操作搜索进行自适应交互建模
Advancing High Fidelity Identity Swapping for Forgery Detection 推进用于伪造检测的高保真身份交换
Adversarial Feature Hallucination Networks for Few-Shot Learning 用于小样本学习的对抗性特征幻觉网络
All in One Bad Weather Removal Using Architectural Search 使用建筑搜索一站式消除恶劣天气
Anisotropic Convolutional Networks for 3D Semantic Scene Completion 用于 3D 语义场景完成的各向异性卷积网络
Approximating shapes in images with low-complexity polygons 具有低复杂度多边形的图像中的近似形状
AutoTrack Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal AutoTrack 面向具有自动时空功能的无人机的高性能视觉跟踪
BachGAN High-Resolution Image Synthesis From Salient Object Layout 显着对象布局的 BachGAN 高分辨率图像合成
Background Data Resampling for Outlier-Aware Classification 异常值感知分类的背景数据重采样
Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation 使用知识蒸馏的分块监督神经架构搜索
Boosting Few-Shot Learning With Adaptive Margin Loss 通过自适应边际损失促进 Few-Shot 学习
Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training 具有进化训练的级联深度单目 3D 人体姿势估计
Category-Level Articulated Object Pose Estimation 类别级关节物体姿态估计
Celeb-DF A Large-Scale Challenging Dataset for DeepFake Forensics Celeb-DF 用于 DeepFake 取证的大规模具有挑战性的数据集
Composing Good Shots by Exploiting Mutual Relations 利用相互关系构筑好镜头
Context-Aware Group Captioning via Self-Attention and Contrastive Features 通过自我注意和对比特征的上下文感知组字幕
Correspondence Networks With Adaptive Neighbourhood Consensus 具有自适应邻域共识的通信网络
Cross-Domain Document Object Detection Benchmark Suite and Method 跨域文档对象检测基准套件和方法
Deep Fair Clustering for Visual Learning 视觉学习的深度公平聚类
Deep Grouping Model for Unified Perceptual Parsing 统一感知解析的深度分组模型
Deformation-Aware Unpaired Image Translation for Pose Estimation on Laboratory Animals 用于实验动物姿态估计的变形感知非配对图像翻译
Density-Aware Graph for Deep Semi-Supervised Visual Recognition 深度半监督视觉识别的密度感知图
Detailed 2D-3D Joint Representation for Human-Object Interaction 用于人-物交互的详细 2D-3D 联合表示
Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives 实现一致优化目标的动态分层模拟
Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human 用于基于人体的 3D 骨架的动态多尺度图神经网络
End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds 3D 点云的端到端学习本地多视图描述符
Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial 使用多示例图像和自适应空间增强盲人脸恢复
Enhanced Transport Distance for Unsupervised Domain Adaptation 无监督域适应的增强传输距离
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder 通过特征金字塔解码器增强内在对抗鲁棒性
Face X-Ray for More General Face Forgery Detection 面部 X 射线用于更一般的面部伪造检测
FALCON A Fourier Transform Based Approach for Fast and Secure FALCON 一种基于傅里叶变换的快速安全方法
Few Sample Knowledge Distillation for Efficient Network Compression 用于高效网络压缩的少量样本知识蒸馏
FSS-1000 A 1000-Class Dataset for Few-Shot Segmentation FSS-1000 用于少镜头分割的 1000 类数据集
Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and 通过半监督分离表示学习识别和识别步态
GAN Compression Efficient Architectures for Interactive Conditional GANs 用于交互式条件 GAN 的 GAN 压缩高效架构
GP-NAS Gaussian Process Based Neural Architecture Search 基于 GP-NAS 高斯过程的神经架构搜索
Group Sparsity The Hinge Between Filter Pruning and Decomposition for 组稀疏性过滤器修剪和分解之间的铰链
Hierarchical Scene Coordinate Classification and Regression for Visual Localization 视觉定位的分层场景坐标分类和回归
Improving Confidence Estimates for Unfamiliar Examples 提高不熟悉示例的置信度估计
Improving One-Shot NAS by Suppressing the Posterior Fading 通过抑制后衰落改进 One-Shot NAS
Inverse Rendering for Complex Indoor Scenes Shape Spatially-Varying Lighting and 复杂室内场景的逆向渲染塑造了空间变化的照明和
Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking 立体 3D 对象跟踪的联合时空优化
Learning Dynamic Routing for Semantic Segmentation 学习语义分割的动态路由
Learning Formation of Physically-Based Face Attributes 基于物理的人脸属性的学习形成
Learning From Noisy Anchors for One-Stage Object Detection 从噪声锚中学习单阶段目标检测
Learning to Learn Cropping Models for Different Aspect Ratio Requirements 学习学习不同长宽比要求的裁剪模型
Learning to Optimize Non-Rigid Tracking 学习优化非刚性跟踪
ManiGAN Text-Guided Image Manipulation ManiGAN 文本引导的图像处理
MixNMatch Multifactor Disentanglement and Encoding for Conditional Image Generation 用于条件图像生成的 MixNMatch 多因素解缠结和编码
Model Adaptation Unsupervised Domain Adaptation Without Source Data 无源数据的模型自适应无监督域自适应
NETNet Neighbor Erasing and Transferring Network for Better Single Shot NETNet 邻居擦除和传输网络以获得更好的单次拍摄
Neural Architecture Search for Lightweight Non-Local Networks 轻量级非本地网络的神经架构搜索
Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group 用平衡组克服分类器不平衡的长尾目标检测
PaStaNet Toward Human Activity Knowledge Engine PaStaNet 迈向人类活动知识引擎
Perspective Plane Program Induction From a Single Image 单幅图像的透视平面程序归纳
PointAugment An Auto-Augmentation Framework for Point Cloud Classification PointAugment 用于点云分类的自动增强框架
Projection Probability-Driven Black-Box Attack 投影概率驱动的黑盒攻击
QEBA Query-Efficient Boundary-Based Blackbox Attack QEBA 查询高效的基于边界的黑盒攻击
Recurrent Feature Reasoning for Image Inpainting 图像修复的循环特征推理
Robust 3D Self-Portraits in Seconds 在几秒钟内完成强大的 3D 自画像
Screencast Tutorial Video Understanding 截屏教程视频理解
Self-Learning With Rectification Strategy for Human Parsing 人类解析的自学习与纠正策略
Self-Supervised Deep Visual Odometry With Online Adaptation 具有在线自适应的自我监督深度视觉里程计
Set-Constrained Viterbi for Set-Supervised Action Segmentation 用于集监督动作分割的集约束维特比
SGAS Sequential Greedy Architecture Search SGAS 顺序贪心架构搜索
Shape correspondence using anisotropic Chebyshev spectral CNNs 使用各向异性切比雪夫谱 CNN 的形状对应
Single Image Reflection Removal Through Cascaded Refinement 通过级联细化去除单幅图像反射
SmallBigNet Integrating Core and Contextual Views for Video Classification SmallBigNet 集成核心视图和上下文视图以进行视频分类
Spatial Pyramid Based Graph Reasoning for Semantic Segmentation 基于空间金字塔的语义分割图推理
Symmetry and Group in Attribute-Object Compositions 属性-对象组合中的对称性和组
TEA Temporal Excitation and Aggregation for Action Recognition 用于动作识别的 TEA 时间激发和聚合
Through the Looking Glass Neural 3D Reconstruction of Transparent Shapes 通过窥镜对透明形状进行神经 3D 重建
Towards Transferable Targeted Attack 迈向可转移的有针对性的攻击
Training a Steerable CNN for Guidewire Detection 训练用于导丝检测的可控 CNN
Transferring Cross-Domain Knowledge for Video Sign Language Recognition 迁移视频手语识别的跨域知识
Unifying Training and Inference for Panoptic Segmentation 统一全景分割的训练和推理
Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation 具身导航的可迁移元技能的无监督强化学习
Visual-Semantic Matching by Exploring High-Order Attention and Distraction 通过探索高阶注意力和分心进行视觉语义匹配
Wavelet Integrated CNNs for Noise-Robust Image Classification 用于抗噪图像分类的小波集成 CNN
PnPNet End-to-End Perception and Prediction With Tracking in the Loop 具有循环跟踪的 PnPNet 端到端感知和预测
PolyTransform Deep Polygon Transformer for Instance Segmentation 用于实例分割的 PolyTransform Deep Polygon Transformer
The Garden of Forking Paths Towards Multi-Future Trajectory Prediction 多未来轨迹预测的分岔路花园
A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression Comprehension 一种用于参考表达理解的实时跨模态相关滤波方法
Iteratively-Refined Interactive 3D Medical Image Segmentation With Multi-Agent Reinforcement Learning 具有多智能体强化学习的迭代改进交互式 3D 医学图像分割
PPDM Parallel Point Detection and Matching for Real-Time Human-Object Interaction 用于实时人-物交互的 PPDM 并行点检测和匹配
Towards Unsupervised Learning of Generative Models for 3D Controllable Image 面向 3D 可控图像的生成模型的无监督学习
A Spatial RNN Codec for End-to-End Image Compression 用于端到端图像压缩的空间 RNN 编解码器
BEDSR-Net A Deep Shadow Removal Network From a Single Document BEDSR-Net 来自单个文档的深度阴影去除网络
Convolution in the Cloud Learning Deformable Kernels in 3D Graph 云中的卷积学习 3D 图中的可变形内核
Fashion Outfit Complementary Item Retrieval 时尚服装配套物品检索
FPConv Learning Local Flattening for Point Convolution FPConv 学习点卷积的局部展平
GPS-Net Graph Property Sensing Network for Scene Graph Generation GPS-Net Graph Property Sensing Network for Scene Graph 生成
Graph-Guided Architecture Search for Real-Time Semantic Segmentation 用于实时语义分割的图形引导架构搜索
HRank Filter Pruning Using High-Rank Feature Map 使用高等级特征图的 HRank 过滤器修剪
Interactive Image Segmentation With First Click Attention 具有首次点击注意的交互式图像分割
M-LVC Multiple Frames Prediction for Learned Video Compression 用于学习视频压缩的 M-LVC 多帧预测
Progressive Mirror Detection 渐进镜检测
Regularizing Neural Networks via Minimizing Hyperspherical Energy 通过最小化超球面能量来正则化神经网络
Shoestring Graph-Based Semi-Supervised Classification With Severely Limited Labeled Data 带有严格有限标记数据的基于小串图的半监督分类
Sketch-BERT Learning Sketch Bidirectional Encoder Representation From Transformers by Self-Supervised Sketch-BERT 通过自我监督从 Transformers 中学习 Sketch 双向编码器表示
Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph 使用图形从野外图像中实现高保真 3D 人脸重建
Unsupervised Person Re-Identification via Softened Similarity Learning 通过软化相似性学习进行无监督人员重新识别
Video Instance Segmentation Tracking With a Modified VAE Architecture 使用修改后的 VAE 架构的视频实例分割跟踪
Visual Chirality 视觉手性
Few-Shot Pill Recognition 少量药丸识别
SCATTER Selective Context Attentional Scene Text Recognizer SCATTER 选择性上下文注意力场景文本识别器
3D Part Guided Image Editing for Fine-Grained Object Understanding 用于细粒度对象理解的 3D 零件引导图像编辑
A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-View Stereo Reconstruction 一种用于大规模多视图立体重建的新型循环编解码器结构
ABCNet Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network 使用自适应贝塞尔曲线网络的 ABCNet 实时场景文本定位
ARShadowGAN Shadow Generative Adversarial Network for Augmented Reality in Single ARSShadowGAN 阴影生成对抗网络，用于单人增强现实
Attention Mechanism Exploits Temporal Contexts Real-Time 3D Human Pose Reconstruction 注意力机制利用时间上下文实时 3D 人体姿势重建
Beyond Short-Term Snippet Video Relation Detection With Spatio-Temporal Global Context 超越时空全局上下文的短期片段视频关系检测
BFBox Searching Face-Appropriate Backbone and Feature Pyramid Network for Face BFBox Searching Face-Apropriate Backbone and Feature Pyramid Network for Face
Boosting Semantic Human Matting With Coarse Annotations 使用粗略注释提升语义人类消光
CARP Compression Through Adaptive Recursive Partitioning for Multi-Dimensional Images 通过自适应递归分区对多维图像进行 CARP 压缩
CRNet Cross-Reference Networks for Few-Shot Segmentation 用于 Few-Shot 分割的 CRNet 交叉参考网络
Cross-View Correspondence Reasoning Based on Bipartite Graph Convolutional Network for 基于二分图卷积网络的跨视图对应推理
Decoupled Representation Learning for Skeleton-Based Gesture Recognition 基于骨架的手势识别的解耦表示学习
Deep Representation Learning on Long-Tailed Data A Learnable Embedding Augmentation 长尾数据的深度表示学习一种可学习的嵌入增强
Deep Shutter Unrolling Network 深度快门展开网络
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition 为基于骨架的动作识别解开和统一图卷积
DIST Rendering Deep Implicit Signed Distance Function With Differentiable Sphere DIST 渲染具有可微球面的深度隐式有符号距离函数
Diverse Image Generation via Self-Conditioned GANs 通过自调节 GAN 生成多样化的图像
Extremely Dense Point Correspondences Using a Learned Feature Descriptor 使用学习到的特征描述符的极其密集的点对应
Few-Shot Open-Set Recognition Using Meta-Learning 使用元学习的 Few-Shot Open-Set 识别
Flow2Stereo Effective Self-Supervised Learning of Optical Flow and Stereo Matching Flow2Stereo 有效的光流自监督学习和立体匹配
Global Texture Enhancement for Fake Face Detection in the Wild 野外假人脸检测的全局纹理增强
Globally Optimal Contrast Maximisation for Event-Based Motion Estimation 基于事件的运动估计的全局最优对比度最大化
Graph Structured Network for Image-Text Matching 用于图文匹配的图结构网络
HAMBox Delving Into Mining High-Quality Anchors on Face Detection HAMBox 深入挖掘人脸检测的高质量锚点
How Does Noise Help Robustness Explanation and Exploration under the 噪声如何帮助鲁棒性解释与探索
Hyperbolic Visual Embedding Learning for Zero-Shot Recognition 用于零样本识别的双曲线视觉嵌入学习
Improving Convolutional Networks With Self-Calibrated Convolutions 使用自校准卷积改进卷积网络
Joint Demosaicing and Denoising With Self Guidance 联合去马赛克和自我指导去噪
KeyPose Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects 透明对象的 KeyPose 多视图 3D 标记和关键点估计
Learning by Analogy Reliable Supervision From Transformations for Unsupervised Optical 从无监督光学转换中类比学习可靠监督
Learning Selective Self-Mutual Attention for RGB-D Saliency Detection 学习用于 RGB-D 显着性检测的选择性自相互注意
Learning to See Through Obstructions 学会看穿障碍物
MemNAS Memory-Efficient Neural Architecture Search With Grow-Trim Learning 使用 Grow-Trim 学习的 MemNAS 内存高效神经架构搜索
Mnemonics Training Multi-Class Incremental Learning Without Forgetting 助记符训练多班增量学习不忘
Neural Contours Learning to Draw Lines From 3D Shapes 神经轮廓学习从 3D 形状中画线
Open Compound Domain Adaptation 开放复合域适配
Recognizing Objects From Any View With Object and Viewer-Centered Representations 使用对象和以查看者为中心的表示从任何视图中识别对象
Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning 为半监督生成学习规范 CGAN 的判别能力
Residual Feature Aggregation Network for Image Super-Resolution 用于图像超分辨率的残差特征聚合网络
Rethinking Computer-Aided Tuberculosis Diagnosis 重新思考计算机辅助结核病诊断
Search to Distill Pearls Are Everywhere but Not the Eyes 寻找蒸馏珍珠无处不在，但不是眼睛
Semantic Correspondence as an Optimal Transport Problem 作为最优传输问题的语义对应
Severity-Aware Semantic Segmentation With Reinforced Wasserstein Training 使用强化 Wasserstein 训练的严重性感知语义分割
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline 通过学习反转相机管道进行单图像 HDR 重建
StereoGAN Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain StereoGAN 通过域的联合优化弥合合成到真实的域差距
Towards Visually Explaining Variational Autoencoders 走向视觉解释变分自编码器
Understanding Road Layout From Videos as a Whole 从视频整体理解道路布局？
Unity Style Transfer for Person Re-Identification 用于人员重新识别的 Unity 风格迁移
Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation 通过全景域自适应在显微镜图像中进行无监督实例分割
Unsupervised Learning for Intrinsic Image Decomposition From a Single Image 从单幅图像进行内在图像分解的无监督学习
Violin A Large-Scale Dataset for Video-and-Language Inference Violin 用于视频和语言推理的大规模数据集？
Visually Imbalanced Stereo Matching 视觉不平衡的立体匹配
When2com Multi-Agent Perception via Communication Graph Grouping 通过通信图分组的When2com 多代理感知
Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions 在半监督学习中生成准确的伪标签并避免过度自信的预测
Searching for Actions on the Hyperbole 搜索夸张的动作
UnrealText Synthesizing Realistic Scene Text Images From the Unreal World UnrealText 合成来自虚幻世界的真实场景文本图像
12-in-1 Multi-Task Vision and Language Representation Learning 12 合 1 多任务视觉和语言表征学习
Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer 具有共享特定特征转移的跨模态人员重新识别
Enhancing Cross-Task Black-Box Transferability of Adversarial Examples With Dispersion Reduction 通过分散减少增强对抗性示例的跨任务黑盒可迁移性
From Depth What Can You See Depth Completion via Auxiliary 从深度你能看到什么深度通过辅助完成
Geometry-Aware Satellite-to-Ground Image Synthesis for Urban Areas 城市地区的几何感知卫星对地图像合成
Learning Video Object Segmentation From Unlabeled Videos 从未标记的视频中学习视频对象分割
MUXConv Information Multiplexing in Convolutional Neural Networks 卷积神经网络中的 MUXConv 信息复用
Predicting Cognitive Declines Using Longitudinally Enriched Representations for Imaging Biomarkers 使用纵向丰富的成像生物标志物表示预测认知衰退
RetinaTrack Online Single Stage Joint Detection and Tracking RetinaTrack 在线单阶段联合检测与跟踪
Stochastic Classifiers for Unsupervised Domain Adaptation 无监督域适应的随机分类器
D3S - A Discriminative Single Shot Segmentation Tracker D3S - 判别性单镜头分割跟踪器
ASLFeat Learning Local Features of Accurate Shape and Localization ASLFeat 学习准确形状和定位的局部特征
Attention-Aware Multi-View Stereo 注意力感知多视图立体
Distortion Agnostic Deep Watermarking 失真不可知的深度水印
End-to-End Optimization of Scene Layout 场景布局端到端优化
Learn to Augment Joint Data Augmentation and Network Optimization for 学习增强联合数据增强和网络优化
Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation 用于联合参考表达理解和分割的多任务协作网络
Neural Network Pruning With Residual-Connections and Limited-Data 带有残差连接和有限数据的神经网络修剪
Wavelet Synthesis Net for Disparity Estimation to Synthesize DSLR Calibre 用于视差估计的小波合成网合成 DSLR 口径
Where What Whether Multi-Modal Learning Meets Pedestrian Detection 多模态学习在哪里遇到行人检测
Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation Transfer 基于域不变交互关系迁移的跨域语义分割
Learning to Segment 3D Point Clouds in 2D Image Space 学习在 2D 图像空间中分割 3D 点云
Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and 深度面部超分辨率与注意力恢复和迭代协作
Learning to Dress 3D People in Generative Clothing 学习为 3D 人物穿上生成式服装
Structure-Preserving Super Resolution With Gradient Guidance 梯度引导的结构保持超分辨率
Unpaired Image Super-Resolution Using Pseudo-Supervision 使用伪监督的未配对图像超分辨率
Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation 使用几何关系从 OCT 图像中分割病理性视网膜区域
Boundary-Aware 3D Building Reconstruction From a Single Overhead Image 从单个俯视图重建边界感知 3D 建筑
Erasing Integrated Learning A Simple Yet Effective Approach for Weakly Erasing Integrated Learning 一种简单而有效的方法
Multimodal Future Localization and Emergence Prediction for Objects in Egocentric 以自我为中心的对象的多模态未来定位和出现预测
SOS Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image 用于快速免疫荧光全玻片图像的 SOS 选择性物镜开关
HandVoxNet Deep Voxel-Based Network for 3D Hand Shape and Pose HandVoxNet 基于深度体素的 3D 手形和姿势网络
Sideways Depth-Parallel Training of Video Models 视频模型的横向深度并行训练
TITAN Future Forecast Using Action Priors 使用行动先验的 TITAN 未来预测
LiDARsim Realistic LiDAR Simulation by Leveraging the Real World LiDARsim 利用现实世界进行逼真的 LiDAR 模拟
MANTRA Memory Augmented Networks for Multiple Trajectory Prediction 用于多轨迹预测的 MANTRA 记忆增强网络
Graph Embedded Pose Clustering for Anomaly Detection 用于异常检测的图形嵌入式姿态聚类
Towards Learning Structure via Consensus for Face Segmentation and Parsing 通过人脸分割和解析的共识走向学习结构
Something-Else Compositional Action Recognition With Spatial-Temporal Interaction Networks 时空交互网络的其他组合动作识别
Minimal Solvers for 3D Scan Alignment With Pairs of Intersecting 具有交叉对的 3D 扫描对齐的最小求解器
Augmenting Colonoscopy Using Extended and Directional CycleGAN for Lossy Image Translation使用扩展和定向 CycleGAN 对有损图像进行增强结肠镜检查
CIAGAN Conditional Identity Anonymization Generative Adversarial Networks CIAGAN 条件身份匿名生成对抗网络
Focus on Defocus Bridging the Synthetic to Real Domain Gap 专注于弥合合成与真实领域差距的散焦
Visual-Textual Capsule Routing for Text-Based Video Segmentation 用于基于文本的视频分割的视觉-文本胶囊路由
Dont Hit Me Glass Detection in Real-World Scenes 不要打我现实世界场景中的玻璃检测
Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining 具有跨尺度非局部注意和详尽自样本挖掘的图像超分辨率
Learning to Have an Ear for Face Super-Resolution 学会倾听面部超分辨率
Controllable Person Image Synthesis With Attribute-Decomposed GAN 具有属性分解GAN的可控人图像合成
ADINet Attribute Driven Incremental Network for Retinal Image Classification 用于视网膜图像分类的 ADINet 属性驱动增量网络
Filter Grafting for Deep Neural Networks 深度神经网络的过滤器嫁接
Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification 用于车辆重新识别的基于解析的视图感知嵌入网络
PULSE Self-Supervised Photo Upsampling via Latent Space Exploration of Generative 通过生成的潜在空间探索的 PULSE 自监督照片上采样
Learning Better Lossless Compression Using Lossy Compression 使用有损压缩学习更好的无损压缩
Can We Learn Heuristics for Graphical Model Inference Using Reinforcement 我们可以使用强化学习启发式图形模型推理吗
Deep Optics for Single-Shot High-Dynamic-Range Imaging 单次高动态范围成像的深度光学
Single-Shot Monocular RGB-D Imaging Using Uneven Double Refraction 使用不均匀双折射的单次单目 RGB-D 成像
Hierarchical Graph Attention Network for Visual Relationship Detection 用于视觉关系检测的分层图注意网络
SSRNet Scalable 3D Surface Reconstruction Network SSRNet 可扩展 3D 表面重建网络
Memory Aggregation Networks for Efficient Interactive Video Object Segmentation 用于高效交互式视频对象分割的内存聚合网络
End-to-End Learning of Visual Representations From Uncurated Instructional Videos 从未经策划的教学视频中端到端学习视觉表示
An Efficient PointLSTM for Point Clouds Based Gesture Recognition 一种基于点云的手势识别的高效 PointLSTM
Domain-Aware Visual Bias Eliminating for Generalized Zero-Shot Learning 用于广义零样本学习的域感知视觉偏差消除
VOLDOR Visual Odometry From Log-Logistic Dense Optical Flow Residuals 来自对数逻辑密集光流残差的 VOLDOR 视觉里程计
Learning Weighted Submanifolds With Variational Autoencoders and Riemannian Variational Autoencoders 使用变分自编码器和黎曼变分自编码器学习加权子流形
Learning to Transfer Texture From Clothing Images to 3D Humans 学习将纹理从服装图像转移到 3D 人体
Self-Supervised Learning of Pretext-Invariant Representations 借口不变表示的自监督学习
Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation 用于 3D 人体姿态估计的多视图一致半监督学习
Learning Visual Motion Segmentation Using Event Surfaces 使用事件表面学习视觉运动分割
EmotiCon Context-Aware Multimodal Emotion Recognition Using Freges Principle 使用弗雷格斯原理的 EmotiCon 上下文感知多模态情感识别
HyperSTAR Task-Aware Hyperparameters for Deep Networks 用于深度网络的 HyperSTAR 任务感知超参数
Just Go With the Flow Self-Supervised Scene Flow Estimation 随大流自监督场景流估计
StructEdit Learning Structural Shape Variations StructEdit 学习结构形状变化
Social-STGCNN A Social Spatio-Temporal Graph Convolutional Neural Network for Human Social-STGCNN 人类社会时空图卷积神经网络
Moving in the Right Direction A Regularization for Deep Metric 朝着正确的方向前进 深度度量的正则化
Towards Verifying Robustness of Neural Networks Against A Family of 朝着验证神经网络对一个家族的鲁棒性
Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networks 卷积神经网络的快速对称微分图像配准
DeepLPF Deep Local Parametric Filters for Image Enhancement 用于图像增强的 DeepLPF 深度局部参数滤波器
Noisier2Noise Learning to Denoise From Unpaired Noisy Data Noisier2Noise 学习从未配对的噪声数据中去噪
Hardware-in-the-Loop End-to-End Optimization of Camera Image Processing Pipelines 相机图像处理管道的硬件在环端到端优化
Learning From Synthetic Animals 向合成动物学习
Local-Global Video-Text Interactions for Temporal Grounding 用于时间接地的本地-全局视频-文本交互
Multi-Modal Domain Adaptation for Fine-Grained Action Recognition 用于细粒度动作识别的多模态域自适应
Dataless Model Selection With the Deep Frame Potential 具有深度框架潜力的无数据模型选择
Self-Supervised Viewpoint Learning From Image Collections 从图像集合中学习自我监督的观点
Ego-Topo Environment Affordances From Egocentric Video 以自我为中心的视频中的自我拓扑环境可供性
Speech2Action Cross-Modal Supervision for Action Recognition Speech2Action 动作识别的跨模态监督
DOPS Learning to Detect 3D Objects and Predict Their 3D DOPS 学习检测 3D 对象并预测其 3D
Deep Learning for Handling Kernelmodel Uncertainty in Image Deconvolution 用于处理图像反卷积中核模型不确定性的深度学习
Variational-EM-Based Deep Learning for Noise-Blind Image Deblurring 用于噪声盲图像去模糊的基于变分 EM 的深度学习
A Self-supervised Approach for Adversarial Robustness 对抗性鲁棒性的自我监督方法
From Image Collections to Point Clouds With Self-Supervised Shape and 从图像集合到具有自我监督形状的点云和
Learning Physics-Guided Face Relighting Under Directional Light 在定向光下学习物理引导的面部重新照明
Image Based Virtual Try-On Network From Unpaired Data 来自未配对数据的基于图像的虚拟试穿网络
How Useful Is Self-Supervised Pretraining for Visual Tasks 视觉任务的自我监督预训练有多大用处
Adaptive Hierarchical Down-Sampling for Point Cloud Classification 点云分类的自适应分层下采样
You2Me Inferring Body Pose in Egocentric Video via First and You2Me 在以自我为中心的视频中通过 First 和
Total3DUnderstanding Joint Layout Object Pose and Mesh Reconstruction for Indoor Total3DUnderstanding Joint Layout Object Pose and Mesh Reconstruction for Indoor
Differentiable Volumetric Rendering Learning Implicit 3D Representations Without 3D Supervision 可微分体积渲染学习隐式 3D 表示，无需 3D 监督
Softmax Splatting for Video Frame Interpolation 用于视频帧插值的 Softmax Splatting
Breaking the Cycle - Colleagues Are All You Need 打破循环——你只需要同事
HCNAF Hyper-Conditioned Neural Autoregressive Flow and its Application for Probabilistic HCNAF 超条件神经自回归流及其在概率学中的应用
Learning Situational Driving 学习情景驾驶
Intuitive Interactive Beard and Hair Synthesis With Generative Models 使用生成模型的直观交互式胡须和头发合成
TetraTSDF 3D Human Reconstruction From a Single Image With a TetraTSDF 3D 人体重建从单个图像与
A Unified Optimization Framework for Low-Rank Inducing Penalties 低秩诱导惩罚的统一优化框架
Bundle Adjustment on a Graph Processor 图处理器上的捆绑调整
Local Context Normalization Revisiting Local Normalization 局部上下文规范化重新审视局部规范化
Semi-Supervised Semantic Segmentation With Cross-Consistency Training 具有交叉一致性训练的半监督语义分割
Efficient Neural Vision Systems Based on Convolutional Image Acquisition 基于卷积图像采集的高效神经视觉系统
3DRegNet A Deep Neural Network for 3D Point Registration 3DRegNet 用于 3D 点配准的深度神经网络
Faster Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric 通过自我监督的深度不对称更快地重建碎文本文档
Looking at the Right Stuff - Guided Semantic-Gaze for Autonomous 寻找正确的东西——自主的引导语义注视
On the Regularization Properties of Structured Dropout 结构化Dropout的正则化性质
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior 使用时间清晰度先验的级联深度视频去模糊
Dynamic Refinement Network for Oriented and Densely Packed Object Detection 用于定向和密集对象检测的动态细化网络
Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation 探索类别不可知的集群以适应开放集域
Single Image Optical Flow Estimation With an Event Camera 使用事件相机进行单图像光流估计
Spatio-Temporal Graph for Video Captioning With Knowledge Distillation 知识蒸馏视频字幕的时空图
Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision 通过自我监督进行语义分割的无监督域内自适应
X-Linear Attention Networks for Image Captioning 用于图像描述的 X 线性注意网络
BidNet Binocular Image Dehazing Without Explicit Disparity Estimation 没有显式视差估计的 BidNet 双目图像去雾
Multi-Scale Interactive Network for Salient Object Detection 用于显着目标检测的多尺度交互网络
Self-Trained Deep Ordinal Regression for End-to-End Video Anomaly Detection 用于端到端视频异常检测的自训练深度序数回归
Solving Mixed-Modal Jigsaw Puzzle for Fine-Grained Sketch-Based Image Retrieval 解决基于细粒度草图的图像检索的混合模态拼图
TubeTK Adopting Tubes to Track Multi-Object in a One-Step Training TubeTK 在一步训练中采用 Tubes 跟踪多对象
Local Non-Rigid Structure-From-Motion From Diffeomorphic Mappings 来自微分映射的局部非刚性结构运动
LatentFusion End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose LatentFusion端到端可微重构和渲染看不见的物体姿势
Learning Memory-Guided Normality for Anomaly Detection 学习用于异常检测的记忆引导正态性
Seeing the World in a Bag of Chips 一袋薯片看世界
Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a 学习 3D 对象的无监督分层部分分解
Heterogeneous Knowledge Distillation Using Information Flow Modeling 使用信息流建模的异构知识蒸馏
TailorNet Predicting Clothing in 3D as a Function of Human TailorNet 预测 3D 服装作为人类的功能
An End-to-End Edge Aggregation Network for Moving Object Segmentation 用于移动对象分割的端到端边缘聚合网络
Seeing without Looking Contextual Rescoring of Object Detections for AP 视而不见的 AP 对象检测的上下文重新评分
3D-ZeF A 3D Zebrafish Tracking Benchmark Dataset 3D-ZeF 3D 斑马鱼跟踪基准数据集
Deep Snake for Real-Time Instance Segmentation 用于实时实例分割的 Deep Snake
IDA-3D Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous IDA-3D Instance-Depth-Aware 3D Object Detection from Stereo Vision for Autonomous
Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels 来自不平衡多标签的大规模目标检测
SAINT Spatially Aware Interpolation NeTwork for Medical Slice Synthesis 用于医学切片合成的 SAINT 空间感知插值网络
Generative-Discriminative Feature Representations for Open-Set Recognition 用于开放集识别的生成判别特征表示
Incremental Few-Shot Object Detection 增量少镜头目标检测
Binarizing MobileNet via Evolution-Based Searching 通过基于进化的搜索对 MobileNet 进行二值化
CoverNet Multimodal Behavior Prediction Using Trajectory Sets 使用轨迹集的 CoverNet 多模式行为预测
Learning to Evaluate Perception Models Using Planner-Centric Metrics 学习使用以计划者为中心的指标评估感知模型
A2dele Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient 用于高效 RGB-D 显着性的 A2dele 自适应和细心深度蒸馏器
Adversarial Latent Autoencoders 对抗性潜在自动编码器
Evolving Losses for Unsupervised Video Representation Learning 无监督视频表示学习的演化损失
SharinGAN Combining Synthetic and Real Data for Unsupervised Geometry Estimation SharinGAN 结合合成数据和真实数据进行无监督几何估计
On the Uncertainty of Self-Supervised Monocular Depth Estimation 关于自监督单目深度估计的不确定性
Uncertainty Based Camera Model Selection 基于不确定性的相机模型选择
Learning Multi-Object Tracking and Segmentation From Automatic Annotations 从自动注释中学习多对象跟踪和分割
Embodied Language Grounding With 3D Visual Feature Representations 具有 3D 视觉特征表示的具身语言基础
Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis 学习个人说话风格以实现准确的唇语合成
Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous 探索基于视觉的城市自治政策学习中的数据聚合
C-Flow Conditional Generative Flow Models for Images and 3D Point 图像和 3D 点的 C-Flow 条件生成流模型
Imitative Non-Autoregressive Modeling for Trajectory Forecasting and Imputation 用于轨迹预测和插补的模拟非自回归建模
ImVoteNet Boosting 3D Object Detection in Point Clouds With Image ImVoteNet 用图像增强点云中的 3D 对象检测
P2B Point-to-Box Network for 3D Object Tracking in Point Clouds 用于点云中 3D 对象跟踪的 P2B 点对盒网络
REVERIE Remote Embodied Visual Referring Expression in Real Indoor Environments REVERIE 真实室内环境中的远程体现视觉参考表达
Two Causal Principles for Improving Visual Dialog 改善视觉对话的两个因果原则
DR Loss Improving Object Detection by Distributional Ranking DR Loss 通过分布排序改进目标检测
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection 用于基于图像的 3D 对象检测的端到端伪激光雷达
Hierarchically Robust Representation Learning 分层鲁棒表示学习
Attention-Guided Hierarchical Structure Aggregation for Image Matting 用于图像抠图的注意力引导层次结构聚合
Learning to Learn Single Domain Generalization 学习学习单域泛化
SEED Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition 用于场景文本识别的 SEED 语义增强型编码器-解码器框架
Forward and Backward Information Retention for Accurate Binary Neural Networks 精确二元神经网络的前向和后向信息保留
Offset Bin Classification Network for Accurate Object Detection 用于精确目标检测的偏移箱分类网络
Adaptive Loss-Aware Quantization for Multi-Bit Networks 多比特网络的自适应损失感知量化
Self2Self With Dropout Learning Self-Supervised Denoising From Single Image Self2Self with Dropout Learning 自监督单幅图像去噪
Designing Network Design Spaces 设计网络设计空间
GeoDA A Geometric Framework for Black-Box Adversarial Attacks GeoDA 用于黑盒对抗攻击的几何框架
Robust Design of Deep Neural Networks Against Adversarial Attacks Based 基于对抗性攻击的深度神经网络鲁棒设计
iTAML An Incremental Task-Agnostic Meta-learning Approach iTAML 一种与任务无关的增量元学习方法
TBT Targeted Neural Network Attack With Bit Trojan 使用 Bit Trojan 的 TBT 目标神经网络攻击
Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation 在单目深度估计中预测清晰准确的遮挡边界
DLWL Improving Detection for Lowshot Classes With Weakly Labelled Data DLWL 改进对带有弱标记数据的 Lowshot 类的检测
Whats Hidden in a Randomly Weighted Neural Network 随机加权神经网络中隐藏的内容
Straight to the Point Fast-Forwarding Videos via Reinforcement Learning Using 通过强化学习直接快速转发视频
A Local-to-Global Approach to Multi-Modal Movie Scene Segmentation 一种局部到全局的多模态电影场景分割方法
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point 3D点无监督表示学习的全局-局部双向推理
RL-CycleGAN Reinforcement Learning Aware Simulation-to-Real RL-CycleGAN Reinforcement Learning Aware Simulation-to-Real
Learning to Measure the Static Friction Coefficient in Cloth Contact 学习测量布接触中的静摩擦系数
There and Back Again Revisiting Backpropagation Saliency Methods 一次又一次地重新审视反向传播显着性方法
Neural Voxel Renderer Learning an Accurate and Controllable Rendering Tool Neural Voxel Renderer 学习准确可控的渲染工具
Lightweight Multi-View 3D Pose Estimation Through Camera-Disentangled Representation 通过相机解耦表示进行轻量级多视图 3D 姿势估计
Deep Image Spatial Transformation for Person Image Generation 用于人物图像生成的深度图像空间变换
Instance-Aware Context-Focused and Memory-Efficient Weakly Supervised Object Detection Instance-Aware Context-Focused 和 Memory-Efficient 弱监督目标检测
Neural Blind Deconvolution Using Deep Priors 使用深度先验的神经盲反卷积
Sketchformer Transformer-Based Representation for Sketched Structure 草图结构的基于 Sketchformer 变压器的表示
McFlow Monte Carlo Flow Models for Data Imputation 用于数据插补的 McFlow Monte Carlo 流模型
Learning Fast and Robust Target Models for Video Object Segmentation 学习用于视频对象分割的快速且稳健的目标模型
Predicting Semantic Map Representations From Images Using Pyramid Occupancy Networks 使用金字塔占用网络从图像中预测语义地图表示
Optimizing Rank-Based Metrics With Blackbox Differentiation 使用黑盒微分优化基于等级的指标
Joint Graph-Based Depth Refinement and Normal Estimation 基于联合图的深度细化和正态估计
PADS Policy-Adapted Sampling for Visual Similarity Learning 用于视觉相似性学习的 PADS 策略自适应采样
STEFANN Scene Text Editor Using Font Adaptive Neural Network 使用字体自适应神经网络的 STEFANN 场景文本编辑器
Sub-Frame Appearance and 6D Pose Estimation of Fast Moving Objects 快速移动物体的子帧外观和 6D 位姿估计
Cloth in the Wind A Case Study of Physical Measurement 风中的布 物理测量的案例研究
FroDO From Detections to 3D Objects FroDO 从检测到 3D 对象
Video Object Grounding Using Semantic Roles in Language Description 在语言描述中使用语义角色的视频对象接地
PIFuHD Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization 用于高分辨率 3D 人体数字化的 PIFuHD 多级像素对齐隐式函数
Active 3D Motion Visualization Based on Spatiotemporal Light-Ray Integration 基于时空光线集成的主动3D运动可视化
Learning a Dynamic Map of Visual Appearance 学习视觉外观的动态地图
Show Edit and Tell A Framework for Editing Image Captions Show Edit and Tell 用于编辑图像标题的框架
Transferring Dense Pose to Proximal Animal Classes 将密集姿势转移到近端动物类
Separating Particulate Matter From a Single Microscopic Image 从单个显微图像中分离颗粒物
Warp to the Future Joint Forecasting of Features and Feature Warp to the Future 联合预测特征和特征
Can Facial Pose and Expression Be Separated With Weak Perspective 弱视能把人脸姿势和表情分开吗
Discovering Synchronized Subsets of Sequences A Large Scale Solution 发现序列的同步子集 大规模解决方案
SuperGlue Learning Feature Matching With Graph Neural Networks SuperGlue 学习特征匹配与图神经网络
Seeing Around Street Corners Non-Line-of-Sight Detection and Tracking In-the-Wild Using 环顾街角：使用多普勒雷达进行野外非视距检测和跟踪
On Joint Estimation of Pose Geometry and svBRDF From a 关于姿态几何和 svBRDF 的联合估计
A U-Net Based Discriminator for Generative Adversarial Networks 一种基于 U-Net 的生成对抗网络鉴别器
Why Having 10000 Parameters in Your Camera Model Is Better 为什么在你的相机模型中有 10000 个参数会更好
DualConvMesh-Net Joint Geodesic and Euclidean Convolutions on 3D Meshes 3D 网格上的 DualConvMesh-Net 联合测地线和欧几里得卷积
Learning Nanoscale Motion Patterns of Vesicles in Living Cells 学习活细胞中囊泡的纳米级运动模式
SQuINTing at VQA Models Introspecting VQA Models With Sub-Questions SQuINTing at VQA Models Introspecting VQA Models with Sub-Questions
Background Matting The World Is Your Green Screen 背景消光 世界是你的绿屏
End-to-End Camera Calibration for Broadcast Videos 广播视频的端到端摄像机校准
ColorFool Semantic Adversarial Colorization ColorFool 语义对抗着色
Understanding Human Hands in Contact at Internet Scale 了解互联网规模的人手接触
Domain Adaptation for Image Dehazing 图像去雾的域自适应
FineGym A Hierarchical Video Dataset for Fine-Grained Action Understanding FineGym 用于细粒度动作理解的分层视频数据集
Intra- and Inter-Action Understanding via Temporal Action Parsing 通过时间动作解析进行动作内和动作间理解
PFRL Pose-Free Reinforcement Learning for 6D Pose Estimation PFRL Pose-Free Reinforcement Learning for 6D Pose Estimation
Auto-Encoding Twin-Bottleneck Hashing 自动编码双瓶颈哈希
Blurry Video Frame Interpolation 模糊视频帧插值
Interpreting the Latent Space of GANs for Semantic Face Editing 解释 GAN 的潜在空间以进行语义人脸编辑
Noise-Aware Fully Webly Supervised Object Detection 噪声感知的全网络监督目标检测
Towards Backward-Compatible Representation Learning 迈向向后兼容的表示学习
Fast Texture Synthesis via Pseudo Optimizer 通过伪优化器进行快速纹理合成
Learning Fused Pixel and Feature-Based View Reconstructions for Light Fields 学习融合像素和基于特征的光场视图重建
Point-GNN Graph Neural Network for 3D Object Detection in a 用于 3D 对象检测的点 GNN 图神经网络
Polishing Decision-Based Adversarial Noise With a Customized Sampling 使用自定义采样对基于决策的对抗性噪声进行抛光
PV-RCNN Point-Voxel Feature Set Abstraction for 3D Object Detection 用于 3D 对象检测的 PV-RCNN 点体素特征集抽象
SpSequenceNet Semantic Segmentation Network on 4D Point Clouds 4D 点云上的 SpSequenceNet 语义分割网络
Towards Universal Representation Learning for Deep Face Recognition 面向深度人脸识别的通用表示学习
Unsupervised Deep Shape Descriptor With Point Distribution Learning 具有点分布学习的无监督深度形状描述符
Weakly-Supervised Action Localization by Generative Attention Modeling 通过生成注意建模进行弱监督动作定位
Where Am I Looking At Joint Location and Orientation Estimation 我在哪里查看联合位置和方向估计
3D Photography Using Context-Aware Layered Depth Inpainting 使用上下文感知分层深度修复的 3D 摄影
Robust Reference-Based Super-Resolution With Similarity-Aware Deformable Convolution 具有相似性感知可变形卷积的强大的基于参考的超分辨率
Semantic Pyramid for Image Generation 图像生成的语义金字塔
ALFRED A Benchmark for Interpreting Grounded Instructions for Everyday Tasks ALFRED 解释日常任务接地指令的基准
ViewAL Active Learning With Viewpoint Entropy for Semantic Segmentation ViewAL Active Learning with Viewpoint Entropy for Semantic Segmentation
Visual Grounding in Video for Unsupervised Word Translation 无监督词翻译的视频视觉基础
Adaptive Subspaces for Few-Shot Learning 少样本学习的自适应子空间
Barycenters of Natural Images Constrained Wasserstein Barycenters for Image 自然图像的重心约束了图像的 Wasserstein 重心
Dont Judge an Object by Its Context Learning to Overcome 不要通过上下文来判断一个对象学习克服
Filter Response Normalization Layer Eliminating Batch Dependence in the Training 过滤响应归一化层消除训练中的批次依赖性
Inferring Attention Shift Ranks of Objects for Image Saliency 为图像显着性推断对象的注意力转移等级
Deep Parametric Shape Predictions Using Distance Fields 使用距离场的深度参数形状预测
A Morphable Face Albedo Model 可变形面反照率模型
15 Keypoints Is All You Need 您只需要 15 个关键点
F-BRS Rethinking Backpropagating Refinement for Interactive Segmentation F-BRS 重新思考交互式分割的反向传播细化
Meta-Transfer Learning for Zero-Shot Super-Resolution 零样本超分辨率的元迁移学习
Efficient Derivative Computation for Cumulative B-Splines on Lie Groups 李群上累积 B 样条的高效导数计算
Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution 基于通道注意的深度图超分辨率迭代残差学习
DEPARA Deep Attribution Graph for Deep Knowledge Transferability 用于深度知识可迁移性的 DEPARA 深度归因图
HybridPose 6D Object Pose Estimation Under Hybrid Representations HybridPose 混合表示下的 6D 对象姿态估计
Revisiting the Sibling Head in Object Detector 重访对象检测器中的兄弟头
DeFeat-Net General Monocular Depth via Simultaneous Unsupervised Representation Learning 通过同时无监督表示学习的 DeFeat-Net 通用单目深度
Same Features Different Day Weakly Supervised Feature Learning for Seasonal 相同的特征不同的日子弱监督特征学习季节性
Lighthouse Predicting Lighting Volumes for Spatially-Coherent Illumination Lighthouse 预测空间相干照明的照明体积
GrappaNet Combining Parallel Imaging With Deep Learning for Multi-Coil MRI GrappaNet 将并行成像与深度学习相结合用于多线圈 MRI
Noise Modeling Synthesis and Classification for Generic Object Anti-Spoofing 通用对象反欺骗的噪声建模合成和分类
Where Does It End - Reasoning About Hidden Surfaces by 它在哪里结束 - 关于隐藏表面的推理
Blindly Assess Image Quality in the Wild Guided by a 在野外盲目评估图像质量
Instance-Aware Image Colorization 实例感知图像着色
PREDICT CLUSTER Unsupervised Skeleton Based Action Recognition PREDICT CLUSTER 无监督基于骨架的动作识别
Gate-Shift Networks for Video Action Recognition 用于视频动作识别的 Gate-Shift 网络
Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring 用于自适应运动去模糊的空间注意力补丁分层网络
ACNe Attentive Context Normalization for Robust Permutation-Equivariant Learning 用于鲁棒置换-等变学习的 ACNe 注意力上下文归一化
Circle Loss A Unified Perspective of Pair Similarity Optimization Circle Loss 对相似度优化的统一视角
Conditional Gaussian Distribution Learning for Open Set Recognition 开放集识别的条件高斯分布学习
Disp R-CNN Stereo 3D Object Detection via Shape Prior Guided Disp R-CNN Stereo 3D Object Detection via Shape Prior Guided
Fast Template Matching and Update for Video Object Tracking and 视频对象跟踪的快速模板匹配和更新
Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging 学习用于单次高动态范围成像的 Rank-1 衍射光学
Reciprocal Learning Networks for Human Trajectory Prediction 用于人类轨迹预测的互惠学习网络
Recursive Social Behavior Graph for Trajectory Prediction 用于轨迹预测的递归社会行为图
Scalability in Perception for Autonomous Driving Waymo Open Dataset 自动驾驶 Waymo 开放数据集的感知可扩展性
Multi-Path Learning for Object Pose Estimation Across Domains 跨域对象姿态估计的多路径学习
Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer 用于任意图像风格迁移的两阶段对等正则化特征重组
EfficientDet Scalable and Efficient Object Detection EfficientDet 可扩展且高效的目标检测
Equalization Loss for Long-Tailed Object Recognition 长尾目标识别的均衡损失
Self-Supervised Human Depth Estimation From Monocular Videos 单目视频的自我监督人体深度估计
VecRoad Point-Based Iterative Graph Exploration for Road Graphs Extraction 用于道路图提取的 VecRoad 基于点的迭代图探索
Polarized Non-Line-of-Sight Imaging 偏振非视距成像
StegaStamp Invisible Hyperlinks in Physical Photographs StegaStamp 物理照片中的隐形超链接
A Semi-Supervised Assessor of Neural Architectures 神经架构的半监督评估者
Deep Implicit Volume Compression 深度隐式体积压缩
Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided 用于语义引导的局部类特定和全局图像级生成对抗网络
LSM Learning Subspace Minimization for Low-Level Vision 低级视觉的 LSM 学习子空间最小化
Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition 重新审视用于细粒度 Few-Shot 识别的姿势归一化
Unbiased Scene Graph Generation From Biased Training 从有偏训练中生成无偏场景图
Uncertainty-Aware Score Distribution Learning for Action Quality Assessment 用于行动质量评估的不确定性感知分数分布学习
Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering 通过结构正则化深度聚类的无监督域适应
Computing Valid P-Values for Image Segmentation by Selective Inference 通过选择性推理计算图像分割的有效 P 值
Alleviation of Gradient Exploding in GANs Fake Can Be Real GANs 中梯度爆炸的缓解可能是真实的
Few-Shot Class-Incremental Learning Few-Shot Class-增量学习
FastDVDnet Towards Real-Time Deep Video Denoising Without Flow Estimation FastDVDnet 实现无流量估计的实时深度视频去噪
SER-FIQ Unsupervised Estimation of Face Image Quality Based on Stochastic 基于随机的SER-FIQ无监督人脸图像质量估计
StyleRig Rigging StyleGAN for 3D Control Over Portrait Images StyleRig Rigging StyleGAN 用于人像图像的 3D 控制
Dynamic Fluid Surface Reconstruction Using Deep Neural Network 使用深度神经网络的动态流体表面重建
TDAN Temporally-Deformable Alignment Network for Video Super-Resolution 用于视频超分辨率的 TDAN 时间可变形对齐网络
End-to-End Model-Free Reinforcement Learning for Urban Driving Using Implicit Affordances 使用隐式供能的城市驾驶端到端无模型强化学习
Distilled Semantics for Comprehensive Scene Understanding from Videos 从视频中全面理解场景的蒸馏语义
Transform and Tell Entity-Aware News Image Captioning 转换并告诉实体感知新闻图像字幕
GLU-Net Global-Local Universal Network for Dense Flow and Correspondences GLU-Net Global-Local Universal Network for Dense Flow and Correspondences
Self-Supervised Learning of Video-Induced Visual Invariances 视频诱导视觉不变性的自监督学习
STAViS Spatio-Temporal AudioVisual Saliency Network STAViS时空视听显着网络
Learning From Web Data With Self-Organizing Memory Module 使用自组织内存模块从 Web 数据中学习
Physically Realizable Adversarial Examples for LiDAR Object Detection 用于 LiDAR 目标检测的物理可实现对抗示例
Single-View View Synthesis With Multiplane Images 具有多平面图像的单视图视图合成
VSGNet Spatial Attention Network for Detecting Human Object Interactions Using 用于检测人类对象交互的 VSGNet 空间注意网络
Learning When and Where to Zoom With Deep Reinforcement Learning 通过深度强化学习学习何时何地进行缩放
UNAS Differentiable Architecture Search Meets Reinforcement Learning UNAS 可微架构搜索遇到强化学习
Butterfly Transform An Efficient FFT Based Neural Architecture Design 蝴蝶变换一种高效的基于 FFT 的神经架构设计
Mixture Dense Regression for Object Detection and Human Pose Estimation 用于目标检测和人体姿态估计的混合密集回归
VQA With No Questions-Answers Training VQA 无问题解答培训
ProAlignNet Unsupervised Learning for Progressively Aligning Noisy Contours ProAlignNet 无监督学习，用于逐步对齐噪声轮廓
Toward a Universal Model for Shape From Texture 面向纹理形状的通用模型
Dynamic Convolutions Exploiting Spatial Sparsity for Faster Inference 利用空间稀疏性进行更快推理的动态卷积
Siam R-CNN Visual Tracking by Re-Detection 重新检测的 Siam R-CNN 视觉跟踪
PointPainting Sequential Fusion for 3D Object Detection 用于 3D 对象检测的 PointPainting 顺序融合
NestedVAE Isolating Common Factors via Weak Supervision NestedVAE 通过弱监督隔离公因子
MoreFusion Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion MoreFusion Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion
Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions 从 3D 室内重建中学习 3D 语义场景图
Bringing Old Photos Back to Life 让旧照片重获新生
FBNetV2 Differentiable Neural Architecture Search for Spatial and Channel Dimensions FBNetV2 可微分神经架构搜索空间和通道维度
On Vocabulary Reliance in Scene Text Recognition 论场景文本识别中的词汇依赖
Reflection Scene Separation From a Single Image 从单个图像中分离反射场景
Super-BPD Super Boundary-to-Pixel Direction for Fast Image Segmentation 用于快速图像分割的 Super-BPD 超边界到像素方向
3DV 3D Dynamic Voxel for Action Recognition in Depth Video 用于深度视频中动作识别的 3DV 3D 动态体素
A Model-Driven Deep Neural Network for Single Image Rain Removal 用于单幅图像去雨的模型驱动深度神经网络
Active Vision for Early Recognition of Human Actions 早期识别人类行为的主动视觉
Affinity Graph Supervision for Visual Recognition 视觉识别的亲和图监督
APQ Joint Search for Network Architecture Pruning and Quantization Policy APQ 联合搜索网络架构剪枝和量化策略
Attentive Normalization for Conditional Image Generation 用于条件图像生成的注意归一化
BiDet An Efficient Binarized Object Detector BiDet 一种高效的二值化对象检测器
BiFuse Monocular 360 Depth Estimation via Bi-Projection Fusion 通过双投影融合的 BiFuse 单目 360 深度估计
Cascaded Refinement Network for Point Cloud Completion 点云补全的级联细化网络
CenterMask Single Shot Instance Segmentation With Point Representation 具有点表示的 CenterMask 单镜头实例分割
CNN-Generated Images Are Surprisingly Easy to Spot… for Now CNN 生成的图像非常容易发现……目前
Collaborative Distillation for Ultra-Resolution Universal Style Transfer 超分辨率通用风格转移的协同蒸馏
Combining Detection and Tracking for Human Pose Estimation in Videos 结合检测和跟踪在视频中进行人体姿态估计
ContourNet Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text ContourNet 向准确的任意形状场景文本迈进了一步
Cross-Batch Memory for Embedding Learning 用于嵌入学习的跨批次记忆
Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning 基于多域解耦表示学习的跨域人脸表示攻击检测
Cross-Modal Pattern-Propagation for RGB-T Tracking 用于 RGB-T 跟踪的跨模态模式传播
Deep Degradation Prior for Low-Quality Image Classification 低质量图像分类的深度退化先验
Deep Distance Transform for Tubular Structure Segmentation in CT Scans CT 扫描中管状结构分割的远距离变换
Deep Generative Model for Robust Imbalance Classification 鲁棒不平衡分类的深度生成模型
Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing 用于人脸反欺骗的深度空间梯度和时间深度学习
DeepFLASH An Efficient Network for Learning-Based Medical Image Registration DeepFLASH 一种高效的基于学习的医学图像配准网络
Differential Treatment for Stuff and Things A Simple Unsupervised Domain 事物的差异化处理一个简单的无监督域
Discovering Human Interactions With Novel Objects via Zero-Shot Learning 通过零样本学习发现人类与新物体的交互
Diversified Arbitrary Style Transfer via Deep Feature Perturbation 通过深度特征扰动实现多样化任意风格迁移
DNU Deep Non-Local Unrolling for Computational Spectral Imaging 用于计算光谱成像的 DNU 深度非局部展开
Dual Super-Resolution Learning for Semantic Segmentation 用于语义分割的双超分辨率学习
Dynamic Face Video Segmentation via Reinforcement Learning 通过强化学习进行动态人脸视频分割
ECA-Net Efficient Channel Attention for Deep Convolutional Neural Networks 深度卷积神经网络的 ECA-Net 高效通道注意力
EventSR From Asynchronous Events to Image Reconstruction Restoration and Super-Resolution EventSR 从异步事件到图像重建恢复和超分辨率
Few-Shot Learning of Part-Specific Probability Space for 3D Shape Segmentation 用于 3D 形状分割的零件特定概率空间的 Few-Shot 学习
FM2u-Net Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification FM2u-Net Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification
FocalMix Semi-Supervised Learning for 3D Medical Image Detection 用于 3D 医学图像检测的 FocalMix 半监督学习
G3AN Disentangling Appearance and Motion for Video Generation 用于视频生成的 G3AN 解开外观和运动
Hierarchical Human Parsing With Typed Part-Relation Reasoning 具有类型化部分关系推理的分层人类解析
Hierarchical Pyramid Diverse Attention Networks for Face Recognition 用于人脸识别的分层金字塔多样化注意网络
High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks 高频分量有助于解释卷积神经网络的泛化
High-Order Information Matters Learning Relation and Topology for Occluded Person 高阶信息对遮挡人的学习关系和拓扑很重要
Instance Credibility Inference for Few-Shot Learning 少样本学习的实例可信度推断
Instance Shadow Detection 实例阴影检测
Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution 高分辨率的强度图像和神经形态事件的联合过滤
Learning a Reinforced Agent for Flexible Exposure Bracketing Selection 学习用于灵活曝光包围选择的增强代理
Learning Combinatorial Solver for Graph Matching 用于图匹配的学习组合求解器
Learning Human-Object Interaction Detection Using Interaction Points 使用交互点学习人与对象交互检测
Learning to Cartoonize Using White-Box Cartoon Representations 学习使用白盒卡通表示进行卡通化
Lightweight Photometric Stereo for Facial Details Recovery 用于面部细节恢复的轻量级光度立体
LT-Net Label Transfer by Learning Reversible Voxel-Wise Correspondence for One-Shot LT-Net Label Transfer by Learning Reversible Voxel-Wise Correspondence for One-Shot
Mesh-Guided Multi-View Stereo With Pyramid Architecture 具有金字塔架构的网格引导多视图立体
MineGAN Effective Knowledge Transfer From GANs to Target Domains With MineGAN 从 GAN 到目标域的有效知识转移
Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning 使用偏度感知强化学习减轻人脸识别中的偏差
NAS-FCOS Fast Neural Architecture Search for Object Detection 用于对象检测的 NAS-FCOS 快速神经架构搜索
Neural Networks Are More Productive Teachers Than Human Raters Active 神经网络是比人类评分者更有效率的教师
Neural Pose Transfer by Spatially Adaptive Instance Normalization 通过空间自适应实例归一化的神经姿态转移
On the General Value of Evidence and Bilingual Scene-Text Visual Question Answering论证据的普遍价值与双语景文视觉
Orthogonal Convolutional Neural Networks 正交卷积神经网络
PANDA A Gigapixel-Level Human-Centric Video Dataset PANDA 千兆像素级以人为中心的视频数据集
Pixel Consensus Voting for Panoptic Segmentation 全景分割的像素共识投票
Probabilistic Video Prediction From Noisy Data With a Posterior Confidence 具有后验置信度的噪声数据的概率视频预测
Progressive Adversarial Networks for Fine-Grained Domain Adaptation 用于细粒度域适应的渐进对抗网络
Robust Object Detection Under Occlusion With Context-Aware CompositionalNets 使用上下文感知组合网络在遮挡下进行鲁棒目标检测
Scale-Equalizing Pyramid Convolution for Object Detection 用于目标检测的尺度均衡金字塔卷积
SCOUT Self-Aware Discriminant Counterfactual Explanations SCOUT 自我意识判别反事实解释
SDC-Depth Semantic Divide-and-Conquer Network for Monocular Depth Estimation 用于单目深度估计的 SDC 深度语义分治网络
Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation 弱监督语义分割的自监督等变注意机制
Semi-Supervised Learning for Few-Shot Image-to-Image Translation 少镜头图像到图像转换的半监督学习
Sequential 3D Human Pose and Shape Estimation From Point Clouds 点云的连续 3D 人体姿势和形状估计
Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person 跨域人员的平滑对抗域攻击和 P 内存重新整合
Suppressing Uncertainties for Large-Scale Facial Expression Recognition 抑制大规模面部表情识别的不确定性
TCTS A Task-Consistent Two-Stage Framework for Person Search TCTS 用于人员搜索的任务一致的两阶段框架
Towards Fairness in Visual Recognition Effective Strategies for Bias Mitigation 朝着视觉识别的公平性迈进 减轻偏见的有效策略
Tracking by Instance Detection A Meta-Learning Approach 通过实例检测进行跟踪一种元学习方法
Train in Germany Test in the USA Making 3D Object 德国火车在美国测试制作 3D 物体
Training Noise-Robust Deep Neural Networks via Meta-Learning 通过元学习训练抗噪深度神经网络
Transferable Controllable and Inconspicuous Adversarial Attacks on Person Re-identification With 可转移可控且不显眼的对人重新识别的对抗性攻击
Transformation GAN for Unsupervised Image Synthesis and Representation Learning 用于无监督图像合成和表示学习的转换 GAN
Unsupervised Person Re-Identification via Multi-Label Classification 通过多标签分类的无监督人员重新识别
Video Modeling With Correlation Networks 使用相关网络进行视频建模
Visual Commonsense R-CNN 视觉常识 R-CNN
VPLNet Deep Single View Normal Estimation With Vanishing Points and 具有消失点的 VPLNet 深度单视图正态估计和
Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented 面向高斯混合模型的弱监督细粒度图像分类
What Deep CNNs Benefit From Global Covariance Pooling An Optimization 深度 CNN 从全局协方差池化优化中受益什么
What Makes Training Multi-Modal Classification Networks Hard 是什么让训练多模态分类网络变得困难
Zero-Assignment Constraint for Graph Matching With Outliers 图匹配异常值的零分配约束
Probabilistic Pixel-Adaptive Refinement Networks 概率像素自适应细化网络
Mapillary Street-Level Sequences A Dataset for Lifelong Place Recognition 用于终身地点识别的 Mapillary 街道级序列数据集
Footprints and Free Space From a Single Color Image 单色图像的足迹和可用空间
RoutedFusion Learning Real-Time Depth Map Fusion RoutedFusion 学习实时深度图融合
A Physics-Based Noise Formation Model for Extreme Low-Light Raw Denoising 一种基于物理的极低光原始去噪噪声形成模型
Combating Noisy Labels by Agreement A Joint Training Method with 通过协议来对抗嘈杂的标签
Label Decoupling Framework for Salient Object Detection 显着目标检测的标签解耦框架
Learning Visual Emotion Representations From Web Data 从 Web 数据中学习视觉情感表示
Multi-Modality Cross Attention Network for Image and Sentence Matching 用于图像和句子匹配的多模态交叉注意网络
Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on 用于弱监督 3D 语义分割的多路径区域挖掘
Universal Weighting Metric Learning for Cross-Modal Matching 用于跨模式匹配的通用加权度量学习
View-GCN View-Based Graph Convolutional Network for 3D Shape Analysis 用于 3D 形状分析的 View-GCN 基于视图的图卷积网络
Correspondence-Free Material Reconstruction using Sparse Surface Constraints 使用稀疏表面约束的无对应材料重建
Point Cloud Completion by Skip-Attention Network With Hierarchical Folding 通过具有层次折叠的 Skip-Attention 网络完成点云
GNN3DMOT Graph Neural Network for 3D Multi-Object Tracking With 2D-3D 用于 2D-3D 的 3D 多对象跟踪的 GNN3DMOT 图神经网络
MISC Multi-Condition Injection and Spatially-Adaptive Compositing for Conditional Person Image 条件人图像的 MISC 多条件注入和空间自适应合成
Relative Interior Rule in Block-Coordinate Descent 块坐标下降中的相对内部规则
Google Landmarks Dataset v2 - A Large-Scale Benchmark for Instance-Level Google Landmarks Dataset v2 - 实例级的大规模基准
SynSin End-to-End View Synthesis From a Single Image 来自单个图像的 SynSin 端到端视图合成
On the Distribution of Minima in Intrinsic-Metric Rotation Averaging 内在度量旋转平均中的极小值分布
Dynamic Traffic Modeling From Overhead Imagery 来自头顶图像的动态交通建模
A Multigrid Method for Efficiently Training Video Models 一种高效训练视频模型的多重网格方法
Bidirectional Graph Reasoning Network for Panoptic Segmentation 用于全景分割的双向图推理网络
Boosting the Transferability of Adversarial Samples via Attention 通过注意力提高对抗样本的可转移性
Cascade EF-GAN Progressive Facial Expression Editing With Local Focuses 具有局部焦点的 Cascade EF-GAN 渐进式面部表情编辑
Exploring Bottom-Up and Top-Down Cues With Attentive Learning for Webly 通过 Webly 的专注学习探索自下而上和自上而下的线索
Future Video Synthesis With Object Motion Prediction 具有对象运动预测的未来视频合成
MEBOW Monocular Estimation of Body Orientation in the Wild 野外体向MEBOW单目估计
MotionNet Joint Perception and Motion Prediction for Autonomous Driving Based 基于 MotionNet 的自动驾驶联合感知和运动预测
Multi-View Neural Human Rendering 多视图神经人体渲染
PhraseCut Language-Based Image Segmentation in the Wild 野外基于 PhraseCut 语言的图像分割
PQ-NET A Generative Part Seq2Seq Network for 3D Shapes PQ-NET 用于 3D 形状的生成部件 Seq2Seq 网络
Rethinking Classification and Localization for Object Detection 重新思考目标检测的分类和定位
Robustness Guarantees for Deep Neural Networks on Videos 视频上深度神经网络的鲁棒性保证
Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition 用于高效低位人脸识别的旋转一致边距损失
Self-Supervised Domain-Aware Generative Network for Generalized Zero-Shot Learning 用于广义零样本学习的自监督领域感知生成网络
Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians 重度遮挡行人的时域增强检测
Towards Global Explanations of Convolutional Neural Networks With Concept Attribution 对具有概念属性的卷积神经网络的全局解释
Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images 来自图像的可能对称可变形 3D 对象的无监督学习
Basis Prediction Networks for Effective Burst Denoising With Large Kernels 大核有效突发去噪的基预测网络
Generating and Exploiting Probabilistic Monocular Depth Estimates 生成和利用概率单目深度估计
Structure Preserving Generative Cross-Domain Learning 结构保持生成式跨域学习
Structure-Guided Ranking Loss for Single Image Depth Prediction 单幅图像深度预测的结构引导排序损失
Efficient and Robust Shape Correspondence via Sparsity-Enforced Quadratic Assignment 通过稀疏强制二次分配实现高效且稳健的形状对应
SAPIEN A SimulAted Part-Based Interactive ENvironment SAPIEN 模拟的基于零件的交互式环境
Zooming Slow-Mo Fast and Accurate One-Stage Space-Time Video Super-Resolution 缩放慢动作快速准确的一级时空视频超分辨率
Evade Deep Image Retrieval by Stashing Private Images in the 通过隐藏私有图像来规避深度图像检索
Multi-Domain Learning for Accurate and Few-Shot Color Constancy 用于准确和少镜头颜色稳定性的多域学习
One Mans Trash Is Another Mans Treasure Resisting Adversarial Examples 一个男人的垃圾是另一个男人的宝藏，抵抗对抗性的例子
Adversarial Examples Improve Image Recognition 对抗样本改善图像识别
MetaFuse A Pre-trained Fusion Model for Human Pose Estimation MetaFuse 用于人体姿势估计的预训练融合模型
MLCVNet Multi-Level Context VoteNet for 3D Object Detection MLCVNet 用于 3D 对象检测的多级上下文 VoteNet
Partial Weight Adaptation for Robust DNN Inference 稳健 DNN 推理的部分权重自适应
PolarMask Single Shot Instance Segmentation With Polar Representation 极地表示的 PolarMask 单次实例分割
Self-Training With Noisy Student Improves ImageNet Classification 使用嘈杂的学生进行自我训练改进了 ImageNet 分类
Inducing Hierarchical Compositional Model by Sparsifying Generator Network 通过稀疏生成器网络引入层次组合模型
Fine-Grained Image-to-Image Transformation Towards Visual Recognition 面向视觉识别的细粒度图像到图像转换
TA-Student VQA Multi-Agents Training by Self-Questioning TA-Student VQA 多智能体自问训练
Variational Context-Deformable ConvNets for Indoor Scene Parsing 用于室内场景解析的变分上下文可变形卷积网络
AANet Adaptive Aggregation Network for Efficient Stereo Matching 用于高效立体匹配的 AANet 自适应聚合网络
Attribution in Scale and Space 比例和空间归因
Cross-Domain Detection via Graph-Induced Prototype Alignment 通过图形诱导的原型对齐进行跨域检测
Deep 3D Portrait From a Single Image 来自单个图像的深度 3D 肖像
Deep Kinematics Analysis for Monocular 3D Human Pose Estimation 单目 3D 人体姿态估计的深度运动学分析
Discriminative Multi-Modality Speech Recognition 判别式多模态语音识别
End-to-End Illuminant Estimation Based on Deep Metric Learning 基于深度度量学习的端到端光源估计
EventCap Monocular 3D Capture of High-Speed Human Motions Using an EventCap 使用单目 3D 捕捉高速人体运动
Explainable Object-Induced Action Decision for Autonomous Vehicles 自动驾驶汽车的可解释对象诱导行动决策
Exploring Categorical Regularization for Domain Adaptive Object Detection 探索域自适应对象检测的分类正则化
Fast MSER 快速 MSER
GHUM GHUML Generative 3D Human Shape and Articulated Pose GHUM GHUML 生成 3D 人体形状和关节姿势
Grid-GCN for Fast and Scalable Point Cloud Learning Grid-GCN 用于快速和可扩展的点云学习
G-TAD Sub-Graph Localization for Temporal Action Detection 用于时间动作检测的 G-TAD 子图定位
How to Train Your Deep Multi-Object Tracker 如何训练您的深度多目标跟踪器
Learning in the Frequency Domain 频域学习
Learning to Restore Low-Light Images via Decomposition-and-Enhancement 学习通过分解和增强恢复低光图像
MARMVS Matching Ambiguity Reduced Multiple View Stereo for Efficient Large MARMVS 匹配模糊度减少了多视角立体，以实现高效大
On the Acceleration of Deep Learning Model Parallelism With Staleness 论深度学习模型并行与陈旧的加速
Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation 无监督域自适应的可靠加权最优传输
Stylization-Based Architecture for Fast Deep Exemplar Colorization 用于快速深度示例着色的基于风格化的架构
Unified Dynamic Convolutional Network for Super-Resolution With Variational Degradations 具有变分退化的超分辨率统一动态卷积网络
Weakly Supervised Semantic Point Cloud Segmentation Towards 10x Fewer Labels 弱监督语义点云分割，标签数量减少 10 倍
What Machines See Is Not What They Get Fooling Scene 机器看到的不是他们得到的愚弄场景
Holistically-Attracted Wireframe Parsing 整体吸引的线框解析
Learning Multi-View Camera Relocalization With Graph Neural Networks 使用图神经网络学习多视图相机重定位
Assessing Eye Aesthetics for Automatic Multi-Reference Eye In-Painting 评估自动多参考眼睛修复的眼睛美学
ClusterFit Improving Generalization of Visual Representations ClusterFit 改进视觉表示的泛化
Cooling-Shrinking Attack Blinding the Tracker With Imperceptible Noises 冷却收缩攻击以难以察觉的噪音使跟踪器失明
Disparity-Aware Domain Adaptation in Stereo Image Restoration 立体图像恢复中的视差感知域自适应
Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification 学习用于基于视频的人员重新识别的多粒度超图
Neural Data Server A Large-Scale Search Engine for Transfer Learning 神经数据服务器 用于迁移学习的大规模搜索引擎
Optical Flow in Dense Foggy Scenes Using Semi-Supervised Learning 使用半监督学习的浓雾场景中的光流
PointASNL Robust Point Clouds Processing Using Nonlocal Neural Networks With PointASNL 使用非局部神经网络的鲁棒点云处理
3DSSD Point-Based 3D Single Stage Object Detector 3DSSD 基于点的 3D 单级物体检测器
Automatic Neural Network Compression by Sparsity-Quantization Joint Learning A Constrained 稀疏量化联合学习的自动神经网络压缩
CARS Continuous Evolution for Efficient Neural Architecture Search 用于高效神经架构搜索的 CARS 持续进化
Cost Volume Pyramid Based Depth Inference for Multi-View Stereo 基于成本体积金字塔的多视图立体深度推断
CPR-GCN Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling 自动解剖标记中的 CPR-GCN 条件部分残差图卷积网络
D3VO Deep Depth Deep Pose and Deep Uncertainty for Monocular D3VO Deep Depth Deep Pose and Deep Uncertainty for Monoocular
Distilling Knowledge From Graph Convolutional Networks 从图卷积网络中提取知识
DPGN Distribution Propagation Graph Network for Few-Shot Learning 用于小样本学习的 DPGN 分布传播图网络
Extreme Relative Pose Network Under Hybrid Representations 混合表示下的极端相对位姿网络
FaceScape A Large-Scale High Quality 3D Face Dataset and Detailed FaceScape 大规模高质量 3D 人脸数据集和详细信息
FDA Fourier Domain Adaptation for Semantic Segmentation 用于语义分割的 FDA 傅里叶域自适应
From Fidelity to Perceptual Quality A Semi-Supervised Approach for Low-Light 从保真度到感知质量低光的半监督方法
Gated Channel Transformation for Visual Recognition 用于视觉识别的门控通道转换
Graph-Structured Referring Expression Reasoning in the Wild 野外图结构的引用表达式推理
Hierarchical Feature Embedding for Attribute Recognition 用于属性识别的分层特征嵌入
In Perfect Shape Certifiably Optimal 3D Shape Reconstruction From 2D 完美的形状 可证明的最佳 3D 形状从 2D 重建
IntrA 3D Intracranial Aneurysm Dataset for Deep Learning 用于深度学习的 Intra 3D 颅内动脉瘤数据集
Learning for Video Compression With Hierarchical Quality and Recurrent Enhancement 学习具有分层质量和循环增强的视频压缩
Learning Texture Transformer Network for Image Super-Resolution 学习用于图像超分辨率的纹理变换器网络
Learning to Cluster Faces via Confidence and Connectivity Estimation 通过置信度和连通性估计学习聚类人脸
Learning to Generate 3D Training Data Through Hybrid Gradient 学习通过混合梯度生成 3D 训练数据
Learning to Manipulate Individual Objects in an Image 学习操纵图像中的单个对象
Learning Unseen Concepts via Hierarchical Decomposition and Composition 通过分层分解和组合学习看不见的概念
One-Shot Domain Adaptation for Face Generation 人脸生成的 One-Shot 域自适应
PFCNN Convolutional Neural Networks on 3D Surfaces Using Parallel Frames 使用并行帧的 3D 表面上的 PFCNN 卷积神经网络
Phase Consistent Ecological Domain Adaptation 相位一致的生态域适应
Predicting Goal-Directed Human Attention Using Inverse Reinforcement Learning 使用逆强化学习预测目标导向的人类注意力
Resolution Adaptive Networks for Efficient Inference 用于高效推理的分辨率自适应网络
Reverse Perspective Network for Perspective-Aware Object Counting 用于透视感知对象计数的反向透视网络
ROAM Recurrently Optimizing Tracking Model ROAM 循环优化跟踪模型
Rotation Equivariant Graph Convolutional Network for Spherical Image Classification 用于球面图像分类的旋转等变图卷积网络
Self-Learning Video Rain Streak Removal When Cyclic Consistency Meets Temporal 当循环一致性遇到时间时，自学视频雨条纹去除
Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification 用于基于视频的人员重新识别的时空图卷积网络
Superpixel Segmentation With Fully Convolutional Networks 全卷积网络的超像素分割
SurfelGAN Synthesizing Realistic Sensor Data for Autonomous Driving SurfelGAN 为自动驾驶合成逼真的传感器数据
SwapText Image Based Texts Transfer in Scenes SwapText 基于图像的文本在场景中传输
Telling Left From Right Learning Spatial Correspondence of Sight and 分辨左右学习视觉的空间对应和
Temporal Pyramid Network for Action Recognition 用于动作识别的时间金字塔网络
Towards Photo-Realistic Virtual Try-On by Adaptively Generating-Preserving Image Content 通过自适应生成保留图像内容实现逼真的虚拟试穿
TransMoMo Invariance-Driven Unsupervised Video Motion Retargeting TransMoMo 不变性驱动的无监督视频运动重定向
Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion 通过光扩展将光流升级为 3D 场景流
WaveletStereo Learning Wavelet Coefficients of Disparity Map in Stereo Matching 立体匹配中视差图的小波立体学习小波系数
BlendedMVS A Large-Scale Dataset for Generalized Multi-View Stereo Networks BlendedMVS 用于广义多视图立体网络的大规模数据集
Front2Back Single View 3D Shape Reconstruction via Front to Back Front2Back 单视图 3D 形状重建通过从前到后
Quasi-Newton Solver for Robust Non-Rigid Registration 用于稳健非刚性配准的准牛顿求解器
Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning 自监督时空表示学习的视频播放速率感知
Syn2Real Transfer Learning for Image Deraining Using Gaussian Processes 使用高斯过程进行图像去雨的 Syn2Real 迁移学习
Orderless Recurrent Models for Multi-Label Classification 多标签分类的无序循环模型
Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN 通过 Group-Stack Dual-GAN 实现无数据知识融合
Distilling Cross-Task Knowledge via Relationship Matching 通过关系匹配提取跨任务知识
Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions 使用 Set-to-Set 函数嵌入自适应的 Few-Shot 学习
HVNet Hybrid Voxel Network for LiDAR Based 3D Object Detection 用于基于 LiDAR 的 3D 对象检测的 HVNet 混合体素网络
Light-weight Calibrator A Separable Component for Unsupervised Domain Adaptation 用于无监督域自适应的轻量级校准器
Probabilistic Structural Latent Representation for Unsupervised Embedding 无监督嵌入的概率结构潜在表示
RPM-Net Robust Point Matching Using Learned Features 使用学习特征的 RPM-Net 鲁棒点匹配
Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting 用于超高分辨率图像修复的上下文残差聚合
Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping 通过非对称循环映射生成不成对的肖像画
Neural Cages for Detail-Preserving 3D Deformations 用于保留细节的 3D 变形的神经笼
A Unified Object Motion and Affinity Model for Online Multi-Object 在线多对象的统一对象运动和亲和模型
Accurate Estimation of Body Height From a Single Depth Image 从单一深度图像准确估计身体高度
Dreaming to Distill Data-Free Knowledge Transfer via DeepInversion 梦想通过 DeepInversion 提取无数据知识转移
LiDAR-Based Online 3D Video Object Detection With Graph-Based Message Passing 基于 LiDAR 的在线 3D 视频对象检测和基于图形的消息传递
From Patches to Pictures PaQ-2-PiQ Mapping the Perceptual Space of 从补丁到图片 PaQ-2-PiQ 映射感知空间
GIFnets Differentiable GIF Encoding Framework GIFnets 可区分的 GIF 编码框架
Rethinking Data Augmentation for Image Super-resolution A Comprehensive Analysis and 重新思考图像超分辨率的数据增强综合分析和
GAMIN Generative Adversarial Multiple Imputation Network for Highly Missing Data 用于高度缺失数据的 GAMIN 生成对抗多重插补网络
Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths 具有全局相干深度的动态场景的新颖视图合成
GreedyNAS Towards Fast One-Shot NAS With Greedy Supernet GreedyNAS 通过贪婪超网实现快速一次性 NAS
KeypointNet A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human KeypointNet 一个由大量人类聚合而成的大规模 3D 关键点数据集
L2-GCN Layer-Wise and Learned Efficient Training of Graph Convolutional Networks 图卷积网络的 L2-GCN 分层和学习高效训练
Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform 使用定向光锥变换的非视线表面重建
OrigamiNet Weakly-Supervised Segmentation-Free One-Step Full Page Text Recognition by learning OrigamiNet Weakly-Supervised Segmentation-Free One Step Full Page Text Recognition by learning
BDD100K A Diverse Driving Dataset for Heterogeneous Multitask Learning BDD100K 用于异构多任务学习的多样化驱动数据集
C2FNAS Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation 用于 3D 医学图像分割的 C2FNAS 粗到细神经架构搜索
COCAS A Large-Scale Clothes Changing Person Dataset for Re-Identification COCAS 用于重新识别的大规模换衣人员数据集
Context Prior for Scene Segmentation 场景分割的上下文先验
Deformable Siamese Attention Networks for Visual Object Tracking 用于视觉对象跟踪的可变形连体注意网络
Determinant Regularization for Gradient-Efficient Graph Matching 梯度高效图匹配的行列式正则化
Episode-Based Prototype Generating Network for Zero-Shot Learning 零样本学习的基于情节的原型生成网络
Fast-MVSNet Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement Fast-MVSNet Sparse-to-Dense Multi-View Stereo with Learned Propagation and Gauss-Newton Refinement
FOAL Fast Online Adaptive Learning for Cardiac Motion Estimation FOAL 用于心脏运动估计的快速在线自适应学习
HUMBI A Large Multiview Dataset of Human Body Expressions HUMBI 人体表情的大型多视图数据集
Learning Video Stabilization Using Optical Flow 使用光流学习视频稳定
Searching Central Difference Convolutional Networks for Face Anti-Spoofing 搜索中心差分卷积网络进行人脸反欺骗
Semantic Drift Compensation for Class-Incremental Learning 类增量学习的语义漂移补偿
Towards Accurate Scene Text Recognition With Semantic Reasoning Networks 利用语义推理网络实现准确的场景文本识别
TransMatch A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning TransMatch 一种用于半监督 Few-Shot 学习的迁移学习方案
Unsupervised Representation Learning for Gaze Estimation 用于注视估计的无监督表示学习
Weakly Supervised Discriminative Feature Learning With State Information for Person 基于个人状态信息的弱监督判别特征学习
Central Similarity Quantization for Efficient Image and Video Retrieval 用于高效图像和视频检索的中心相似性量化
Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With 使用空间变体反卷积网络的高效动态场景去模糊
Ensemble Generative Cleaning With Feedback Loops for Defending Adversarial Attacks 用于防御对抗性攻击的带有反馈循环的集成生成清洗
Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging 用于大规模快照压缩成像的即插即用算法
Revisiting Knowledge Distillation via Label Smoothing Regularization 通过标签平滑正则化重新审视知识蒸馏
Supervised Raw Video Denoising With a Benchmark Dataset on Dynamic 基于动态基准数据集的监督原始视频去噪
Regularizing Class-Wise Predictions via Self-Knowledge Distillation 通过自知识蒸馏对分类预测进行正则化
Old Is Gold Redefining the Adversarially Learned One-Class Classifier Training 老是黄金重新定义对抗学习的一类分类器训练
Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors 使用 SDF 形状先验的可微分渲染自动标记 3D 对象
CycleISP Real Image Restoration via Improved Data Synthesis CycleISP 通过改进的数据合成进行真实图像恢复
Robust Learning Through Cross-Task Consistency 通过跨任务一致性进行稳健学习
TomoFluid Reconstructing Dynamic Fluid From Sparse View Videos TomoFluid 从稀疏视图视频中重建动态流体
Weakly Supervised Visual Semantic Parsing 弱监督视觉语义分析
3D Human Mesh Regression With Dense Correspondence 具有密集对应的 3D 人体网格回归
Bundle Pooling for Polygonal Architecture Segmentation Problem 用于多边形架构分割问题的捆绑池化
Dense Regression Network for Video Grounding 用于视频接地的密集回归网络
Gum-Net Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Gum-Net 无监督几何匹配用于快速准确的 3D 子图
Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification 用于人员重新识别的具有 Hard-Batch Triplet Loss 的层次聚类
Visual Reaction Learning to Play Catch With Your Drone 视觉反应学习用你的无人机接球
AD-Cluster Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification 用于域自适应人员重新识别的 AD-Cluster 增强判别聚类
Deep Structure-Revealed Network for Texture Recognition 用于纹理识别的深层结构显示网络
Online Deep Clustering for Unsupervised Representation Learning 用于无监督表示学习的在线深度聚类
Self-Supervised Scene De-Occlusion 自监督场景去遮挡
4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple 使用多个实时多人运动捕捉的 4D 关联图
A Transductive Approach for Video Object Segmentation 一种用于视频对象分割的转导方法
Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency 具有注意力图聚类的自适应图卷积网络共显着性
Auxiliary Training Towards Accurate and Robust Models 针对准确和稳健模型的辅助训练
Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive 通过自适应弥合基于锚点和无锚点检测之间的差距
Context Aware Graph Convolution for Skeleton-Based Action Recognition 基于骨架的动作识别的上下文感知图卷积
Context-Aware and Scale-Insensitive Temporal Repetition Counting 上下文感知和尺度不敏感的时间重复计数
Context-Aware Attention Network for Image-Text Retrieval 用于图像文本检索的上下文感知注意网络
Conv-MPN Convolutional Message Passing Neural Network for Structured Outdoor Architecture 用于结构化户外建筑的 Conv-MPN 卷积消息传递神经网络
Copy and Paste GAN Face Hallucination From Shaded Thumbnails 从阴影缩略图中复制和粘贴 GAN 幻脸
Correlating Edge Pose With Parsing 将边缘姿势与解析相关联
Cross-Domain Correspondence Learning for Exemplar-Based Image Translation 基于样本的图像翻译的跨域对应学习
DAVD-Net Deep Audio-Aided Video Decompression of Talking Heads 说话头的 DAVD-Net 深度音频辅助视频解压缩
Deblurring by Realistic Blurring 通过逼真的模糊去模糊
Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection 用于任意形状文本检测的深度关系推理图网络
Deep Unfolding Network for Image Super-Resolution 用于图像超分辨率的深度展开网络
DeepEMD Few-Shot Image Classification With Differentiable Earth Movers Distance and DeepEMD Few-Shot 图像分类与可微的推土机距离和
Depth Sensing Beyond LiDAR Range 超出 LiDAR 范围的深度感应
Distilling Effective Supervision From Severe Label Noise 从严重的标签噪声中提取有效的监督
Distribution-Aware Coordinate Representation for Human Pose Estimation 人体姿态估计的分布感知坐标表示
Dynamic Graph Message Passing Networks 动态图消息传递网络
Exemplar Normalization for Learning Deep Representation 用于学习深度表示的示例归一化
Fixed-Point Back-Propagation Training 定点反向传播训练
FReeNet Multi-Identity Face Reenactment FReeNet 多身份人脸重演
Fusing Wearable IMUs With Multi-View Images for Human Pose Estimation 将可穿戴 IMU 与多视图图像融合以进行人体姿势估计
Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation 用于在线语义 3D 场景分割的融合感知点卷积
Generating 3D People in Scenes Without People 在没有人的场景中生成 3D 人物
Global-Local GCN Large-Scale Label Noise Cleansing for Face Recognition 用于人脸识别的全局-局部 GCN 大规模标签噪声清理
Interactive Object Segmentation With Inside-Outside Guidance 具有内外指导的交互式对象分割
Mask Encoding for Single Shot Instance Segmentation 单次实例分割的掩码编码
Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising 用于图像去噪的内存高效分层神经架构搜索
METAL Minimum Effort Temporal Activity Localization in Untrimmed Videos 未修剪视频中的 METAL 最小努力时间活动定位
Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-Based Person Re-Identification 用于基于视频的人员重新识别的多粒度参考辅助注意力特征聚合
Nested Scale-Editing for Conditional Image Synthesis 用于条件图像合成的嵌套比例编辑
Object Relational Graph With Teacher-Recommended Learning for Video Captioning 具有教师推荐学习的视频字幕对象关系图
Object-Occluded Human Shape and Pose Estimation From a Single Color 基于单一颜色的物体遮挡人体形状和姿势估计
Online Depth Learning Against Forgetting in Monocular Videos 在线深度学习对抗单目视频中的遗忘
Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization 通过多样性最大化克服 One-Shot NAS 中的多模型遗忘
Part-Aware Context Network for Human Parsing 用于人类解析的部分感知上下文网络
PolarNet An Improved Grid Representation for Online LiDAR Point Clouds PolarNet 一种改进的在线 LiDAR 点云网格表示
Putting Visual Object Recognition in Context 将视觉对象识别置于上下文中
Quaternion Product Units for Deep Learning on 3D Rotation Groups 用于 3D 旋转组深度学习的四元数乘积单元
Relation-Aware Global Attention for Person Re-Identification 用于人员重新识别的关系感知全局注意力
Rethinking the Route Towards Weakly Supervised Object Localization 重新思考弱监督对象定位的路径
Select Supplement and Focus for RGB-D Saliency Detection 为 RGB-D 显着性检测选择补充和焦点
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition 语义引导神经网络用于高效的基于骨架的人体动作识别
State-Relabeling Adversarial Active Learning 状态重新标记对抗性主动学习
STINet Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction 用于行人检测和轨迹预测的 STINet 时空交互网络
Texture and Shape Biased Two-Stream Networks for Clothing Classification and 用于服装分类的纹理和形状偏向两流网络
The Secret Revealer Generative Model-Inversion Attacks Against Deep Neural Networks 针对深度神经网络的 Secret Revealer 生成模型反转攻击
Transferring and Regularizing Prediction for Semantic Segmentation 语义分割的转移和正则化预测
UC-Net Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders 通过条件变分自动编码器的 UC-Net 不确定性启发 RGB-D 显着性检测
Understanding Adversarial Examples From the Mutual Influence of Images and 从图像和图像的相互影响中理解对抗性示例
Unsupervised Adaptation Learning for Hyperspectral Imagery Super-Resolution 高光谱图像超分辨率的无监督适应学习
WCP Worst-Case Perturbations for Semi-Supervised Deep Learning 半监督深度学习的 WCP 最坏情况扰动
Weakly-Supervised Salient Object Detection via Scribble Annotations 通过涂鸦注释进行弱监督显着目标检测
Where Does It Exist Spatio-Temporal Video Grounding for Multi-Form Sentences 多形式句子的时空视频接地在哪里
ZSTAD Zero-Shot Temporal Activity Detection ZSTAD 零样本时间活动检测
A Certifiably Globally Optimal Solution to Generalized Essential Matrix Estimation 广义基本矩阵估计的可证明全局最优解
Bayesian Adversarial Human Motion Synthesis 贝叶斯对抗人体运动合成
Clean-Label Backdoor Attacks on Video Recognition Models 对视频识别模型的清洁标签后门攻击
Domain Decluttering Simplifying Images to Mitigate Synthetic-Real Domain Shift and 域去杂波简化图像以减轻合成真实域移位和
Exploring Self-Attention for Image Recognition 探索图像识别的自注意力
Knowledge As Priors Cross-Modal Knowledge Generalization for Datasets Without Superior 知识作为先验数据集的跨模态知识泛化
Learning Deep Network for Detecting 3D Object Keypoints and 6D 用于检测 3D 对象关键点和 6D 的学习深度网络
Maintaining Discrimination and Fairness in Class Incremental Learning 在课堂增量学习中保持歧视和公平
MaskFlownet Asymmetric Feature Matching With Learnable Occlusion Mask MaskFlownet 非对称特征匹配与可学习遮挡掩码
On Isometry Robustness of Deep 3D Point Cloud Models Under 深3D点云模型的等距鲁棒性
Painting Many Pasts Synthesizing Time Lapse Videos of Paintings 绘画许多过去，合成时间流逝的绘画视频
Predicting Lymph Node Metastasis Using Histopathological Images Based on Multiple 使用基于多个的组织病理学图像预测淋巴结转移
RDCFace Radial Distortion Correction for Face Recognition RDCFace 人脸识别径向畸变校正
SESS Self-Ensembling Semi-Supervised 3D Object Detection SESS 自集成半监督 3D 目标检测
Towards Better Generalization Joint Depth-Pose Learning Without PoseNet 在没有 PoseNet 的情况下实现更好的泛化联合深度姿势学习
Towards Large Yet Imperceptible Adversarial Image Perturbations With Perceptual Color 朝向具有感知色彩的大而难以察觉的对抗性图像扰动
UCTGAN Diverse Image Inpainting Based on Unsupervised Cross-Space Translation 基于无监督跨空间翻译的UCTGAN多样化图像修复
Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts 使用迭代金字塔上下文的联合语义分割和边界检测
Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation 通过粗到细特征自适应的跨域目标检测
Deep Metric Learning via Adaptive Learnable Assessment 通过自适应可学习评估进行深度度量学习
Distribution-Induced Bidirectional Generative Adversarial Network for Graph Representation Learning 用于图表示学习的分布诱导双向生成对抗网络
Efficient Adversarial Training With Transferable Adversarial Examples 具有可转移对抗样本的高效对抗训练
Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial 高空间地理空间对象分割的前景感知关系网络
Image Demoireing with Learnable Bandpass Filters 使用可学习的带通滤波器进行图像分解
Learning to Shadow Hand-Drawn Sketches 学习阴影手绘草图
Optical Flow in the Dark 黑暗中的光流
Rethinking Performance Estimation in Neural Architecture Search 重新思考神经架构搜索中的性能估计
Syntax-Aware Action Targeting for Video Captioning 视频字幕的语法感知动作定位
Webly Supervised Knowledge Embedding Model for Visual Reasoning 用于视觉推理的 Webly 监督知识嵌入模型
What Does Plate Glass Reveal About Camera Calibration 平板玻璃对相机校准有何启示
Minimizing Discrete Total Curvature for Image Processing 最小化图像处理的离散总曲率
Regularizing CNN Transfer Learning With Randomised Regression 使用随机回归正则化 CNN 迁移学习
Robust Partial Matching for Person Search in the Wild 野外人员搜索的鲁棒部分匹配
Squeeze-and-Attention Networks for Semantic Segmentation 用于语义分割的 Squeeze-and-Attention 网络
BBN Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual Recognition 用于长尾视觉识别的具有累积学习的 BBN 双边分支网络
Cascaded Human-Object Interaction Recognition 级联人-物交互识别
DaST Data-Free Substitute Training for Adversarial Attacks 对抗性攻击的 DaST 无数据替代训练
Deepstrip High-Resolution Boundary Refinement Deepstrip高分辨率边界细化
DuDoRNet Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction DuDoRNet 学习用于快速 MRI 重建的双域循环网络
EcoNAS Finding Proxies for Economical Neural Architecture Search EcoNAS 为经济的神经架构搜索寻找代理
End-to-End Adversarial-Attention Network for Multi-Modal Clustering 用于多模态聚类的端到端对抗注意网络
Geometry and Learning Co-Supported Normal Estimation for Unstructured Point Cloud 非结构化点云的几何和学习共同支持的正态估计
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection 用于准确和快速显着性检测的交互式双流解码器
Joint 3D Instance Segmentation and Object Detection for Autonomous Driving 用于自动驾驶的联合 3D 实例分割和目标检测
KFNet Learning Temporal Camera Relocalization Using Kalman Filtering 使用卡尔曼滤波的 KFNet 学习时间相机重定位
Learning Oracle Attention for High-Fidelity Face Completion 学习 Oracle Attention 以实现高保真人脸补全
Learning Saliency Propagation for Semi-Supervised Instance Segmentation 半监督实例分割的学习显着性传播
Learning to Select Base Classes for Few-Shot Classification 学习为 Few-Shot 分类选择基类
LG-GAN Label Guided Adversarial Network for Flexible Targeted Attack of 用于灵活有针对性攻击的 LG-GAN 标签引导对抗网络
Look-Into-Object Self-Supervised Structure Modeling for Object Recognition 面向对象识别的对象自监督结构建模
Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data 使用多模态数据的单目实时手形和动作捕捉
More Grounded Image Captioning by Distilling Image-Text Matching Model 通过提取图像文本匹配模型进行更扎实的图像描述
Multi-Mutual Consistency Induced Transfer Subspace Learning for Human Motion Segmentation 用于人体运动分割的多相一致性诱导迁移子空间学习
Online Joint Multi-Metric Adaptation From Frequent Sharing-Subset Mining for Person 个人频繁共享子集挖掘的在线联合多度量适应
Pattern-Structure Diffusion for Multi-Task Learning 多任务学习的模式结构扩散
Rotate-and-Render Unsupervised Photorealistic Face Rotation From Single-View Images 从单视图图像旋转和渲染无监督照片级真实面部旋转
Spatiotemporal Fusion in 3D CNNs A Probabilistic View 3D CNN 中的时空融合概率视图
ActBERT Learning Global-Local Video-Text Representations ActBERT 学习全局-本地视频-文本表示
AdaCoSeg Adaptive Shape Co-Segmentation With Group Consistency Loss 具有组一致性损失的 AdaCoSeg 自适应形状协同分割
CookGAN Causality Based Text-to-Image Synthesis CookGAN 基于因果关系的文本到图像合成
Dont Even Look Once Synthesizing Features for Zero-Shot Detection 甚至不要看一次综合特征以进行零样本检测
Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition 用于长尾视觉识别的区域自注意力膨胀情景记忆
MetaIQA Deep Meta-Learning for No-Reference Image Quality Assessment 用于无参考图像质量评估的 MetaIQA 深度元学习
Private-kNN Practical Differential Privacy for Computer Vision 用于计算机视觉的 Private-kNN 实用差分隐私
ReDAReinforced Differentiable Attribute for 3D Face Reconstruction 用于 3D 人脸重建的 ReDAReinforced 可微属性
Retina-Like Visual Image Reconstruction via Spiking Neural Model 基于脉冲神经模型的类视网膜视觉图像重建
S3VAE Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation S3VAE 用于表示分离和数据生成的自监督顺序 VAE
SEAN Image Synthesis With Semantic Region-Adaptive Normalization 具有语义区域自适应归一化的 SEAN 图像合成
Semantically Multi-Modal Image Synthesis 语义多模态图像合成
The Edge of Depth Explicit Constraints Between Segmentation and Depth 分割和深度之间的深度边界显式约束
Towards Unified INT8 Training for Convolutional Neural Network 迈向卷积神经网络的统一 INT8 训练
Vision-Dialog Navigation by Exploring Cross-Modal Memory 探索跨模态记忆的视觉对话导航
Vision-Language Navigation With Self-Supervised Auxiliary Reasoning Tasks 具有自我监督辅助推理任务的视觉语言导航
Training Quantized Neural Networks With a Full-Precision Auxiliary Module 使用全精度辅助模块训练量化神经网络
Unsupervised Learning From Video With Deep Neural Embeddings 具有深度神经嵌入的视频无监督学习
Cogradient Descent for Bilinear Optimization 双线性优化的协梯度下降
Deep Residual Flow for Out of Distribution Detection 用于不分布检测的深度剩余流
Sequential Motif Profiles and Topological Plots for Offline Signature Verification 用于离线签名验证的序列基序配置文件和拓扑图
Towards Robust Image Classification Using Sequential Attention Models 使用顺序注意模型实现稳健的图像分类
Deep Adversarial Decomposition A Unified Framework for Separating Superimposed Images Deep Adversarial Decomposition 一种用于分离叠加图像的统一框架