目录
CVPR2018所有文章列表（篇幅有限，只放一部分）
| Paper ID | Type | Title |
| 5 | Poster | Single-Shot Refinement Neural Network for Object Detection |
| 7 | Poster | Video Captioning via Hierarchical Reinforcement Learning |
| 12 | Oral | DensePose: Multi-Person Dense Human Pose Estimation In The Wild |
| 12 | Poster | DensePose: Multi-Person Dense Human Pose Estimation In The Wild |
| 19 | Poster | Frustum PointNets for 3D Object Detection from RGB-D Data |
| 21 | Poster | Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge |
| 24 | Poster | Rethinking the Faster R-CNN Architecture for Temporal Action Localization |
| 27 | Spotlight | Shape from Shading through Shape Evolution |
| 27 | Poster | Shape from Shading through Shape Evolution |
| 34 | Poster | A High-Quality Denoising Dataset for Smartphone Cameras |
| 35 | Poster | Improving Color Reproduction Accuracy in the Camera Imaging Pipeline |
| 37 | Spotlight | End-to-End Dense Video Captioning with Masked Transformer |
| 37 | Poster | End-to-End Dense Video Captioning with Masked Transformer |
| 41 | Poster | pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment |
| 47 | Poster | Learning to Segment Every Thing |
| 48 | Poster | Density-aware Single Image De-raining using a Multi-stream Dense Network |
| 49 | Poster | Densely Connected Pyramid Dehazing Network |
| 52 | Poster | Embodied Question Answering |
| 53 | Spotlight | TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays |
| 53 | Poster | TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays |
| 64 | Poster | Towards Open-Set Identity Preserving Face Synthesis |
| 67 | Poster | Baseline Desensitizing In Translation Averaging |
| 68 | Poster | Learning from the Deep: A Revised Underwater Image Formation Model |
| 76 | Oral | Context Encoding for Semantic Segmentation |
| 76 | Poster | Context Encoding for Semantic Segmentation |
| 77 | Poster | Deep Texture Manifold for Ground Terrain Recognition |
| 83 | Poster | DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems |
| 85 | Poster | Sparse, Smart Contours to Represent and Edit Images |
| 92 | Poster | Every Smile is Unique: Landmark-guided Diverse Smile Generation |
| 95 | Poster | Generative Non-Rigid Shape Completion with Graph Convolutional Autoencoders |
| 97 | Poster | Learning a Discriminative Prior for Blind Image Deblurring |
| 100 | Poster | Attentional ShapeContextNet for Point Cloud Recognition |
| 102 | Poster | Learning Superpixels with Segmentation-Aware Affinity Loss |
| 103 | Spotlight | Real-World Repetition Estimation by Div, Grad and Curl |
| 103 | Poster | Real-World Repetition Estimation by Div, Grad and Curl |
| 106 | Poster | Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation |
| 109 | Poster | MegaDepth: Learning Single-View Depth Prediction from Internet Photos |
| 110 | Spotlight | Learning Intrinsic Image Decomposition from Watching the World |
| 110 | Poster | Learning Intrinsic Image Decomposition from Watching the World |
| 112 | Poster | Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering |
| 116 | Poster | Human-centric Indoor Scene Synthesis Using Stochastic Grammar |
| 120 | Poster | Learning by Asking Questions |
| 121 | Poster | Instance Embedding Transfer to Unsupervised Video Object Segmentation |
| 122 | Poster | Detect-and-Track: Efficient Pose Estimation in Videos |
| 124 | Poster | Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval |
| 125 | Poster | Guided Proofreading of Automatic Segmentations for Connectomics |
| 128 | Oral | Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation |
| 128 | Poster | Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation |
| 130 | Poster | Context-aware Synthesis for Video Frame Interpolation |
| 131 | Poster | 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning |
| 135 | Poster | NAG: Network for Adversary Generation |
| 136 | Spotlight | LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation |
| 136 | Poster | LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation |
| 137 | Poster | Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration |
| 142 | Spotlight | Multi-view Harmonized Bilinear Network for 3D Object Recognition |
| 142 | Poster | Multi-view Harmonized Bilinear Network for 3D Object Recognition |
| 144 | Spotlight | Tangent Convolutions for Dense Prediction in 3D |
| 144 | Poster | Tangent Convolutions for Dense Prediction in 3D |
| 145 | Oral | Semi-parametric Image Synthesis |
| 145 | Poster | Semi-parametric Image Synthesis |
| 147 | Poster | Interactive Image Segmentation with Latent Diversity |
| 155 | Spotlight | 3D Hand Pose Estimation: From Current Achievements to Future Goals |
| 155 | Poster | 3D Hand Pose Estimation: From Current Achievements to Future Goals |
| 165 | Poster | W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection |
| 167 | Spotlight | BlockDrop: Dynamic Inference Paths in Residual Networks |
| 167 | Poster | BlockDrop: Dynamic Inference Paths in Residual Networks |
| 168 | Spotlight | MapNet: Geometry-Aware Learning of Maps for Camera Localization |
| 168 | Poster | MapNet: Geometry-Aware Learning of Maps for Camera Localization |
| 170 | Poster | BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning |
| 178 | Poster | Salient Object Detection Driven by Fixation Prediction |
| 179 | Poster | 3D Object Detection with Latent Support Surfaces |
| 181 | Oral | Practical Block-wise Neural Network Architecture Generation |
| 181 | Poster | Practical Block-wise Neural Network Architecture Generation |
| 182 | Poster | Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points |
| 185 | Oral | Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning |
| 185 | Poster | Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning |
| 186 | Poster | Visual Grounding via Accumulated Attention |
| 191 | Poster | Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors |
| 195 | Poster | ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing |
| 200 | Poster | Perturbative Neural Networks: Rethinking Convolution in CNNs |
| 203 | Spotlight | Nonlinear 3D Face Morphable Model |
| 203 | Poster | Nonlinear 3D Face Morphable Model |
| 205 | Spotlight | Neural Baby Talk |
| 205 | Poster | Neural Baby Talk |
| 216 | Poster | Towards Pose Invariant Face Recognition in the Wild |
| 224 | Poster | MoNet: Deep Motion Exploitation for Video Object Segmentation |
| 229 | Poster | Exploring Disentangled Feature Representation Beyond Face Identification |
| 232 | Poster | Towards Effective Low-bitwidth Convolutional Neural Networks |
| 234 | Poster | Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries |
| 237 | Poster | Learning Facial Action Units from Web Images with Scalable Weakly Supervised Clustering |
| 242 | Spotlight | Few-Shot Image Recognition by Predicting Parameters from Activations |
| 242 | Poster | Few-Shot Image Recognition by Predicting Parameters from Activations |
| 246 | Poster | Single-Shot Object Detection with Enriched Semantics |
| 250 | Poster | Unifying Identification and Context Learning for Person Recognition |
| 252 | Poster | Separating Self-Expression and Visual Content in Hashtag Supervision |
| 255 | Poster | Multi-Cue Correlation Filters for Robust Visual Tracking |
| 260 | Poster | Beyond Trade-off: Accelerate FCN-based Face Detection with Higher Accuracy |
| 261 | Poster | On the Robustness of Semantic Segmentation Models to Adversarial Attacks |
| 266 | Oral | PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume |
| 266 | Poster | PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume |
| 270 | Oral | Illuminant Spectra-based Source Separation Using Flash Photography |
| 270 | Poster | Illuminant Spectra-based Source Separation Using Flash Photography |
| 281 | Spotlight | Tracking Multiple Objects Outside the Line of Sight using Speckle Imaging |
| 281 | Poster | Tracking Multiple Objects Outside the Line of Sight using Speckle Imaging |
| 285 | Poster | Improved Human Pose Estimation through Adversarial Data Augmentation |
| 289 | Poster | Generative Adversarial Learning Towards Fast Weakly Supervised Detection |
| 298 | Spotlight | Audio to Body Dynamics |
| 298 | Poster | Audio to Body Dynamics |
| 299 | Poster | The Unreasonable Effectiveness of Deep Features as a Perceptual Metric |
| 303 | Poster | Frame-Recurrent Video Super-Resolution |
| 304 | Poster | Deep Mutual Learning |
| 308 | Poster | Real-world Anomaly Detection in Surveillance Videos |
| 310 | Poster | Soccer on Your Tabletop |
| 312 | Poster | Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification |
| 313 | Poster | HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN |
| 316 | Poster | Excitation Backprop for RNNs |
| 319 | Poster | Dynamic-Structured Semantic Propagation Network |
| 325 | Spotlight | Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation |
| 325 | Poster | Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation |
| 326 | Oral | SPLATNet: Sparse Lattice Networks for Point Cloud Processing |
| 326 | Poster | SPLATNet: Sparse Lattice Networks for Point Cloud Processing |
| 329 | Poster | Video Representation Learning Using Discriminative Pooling |
| 330 | Poster | Attend and Interact: Higher-Order Object Interactions for Video Understanding |
| 342 | Poster | Human Pose Estimation with Parsing Induced Learner |
| 345 | Poster | 4D Human Body Correspondences from Panoramic Depth Maps |
| 346 | Poster | Recognizing Human Actions as Evolution of Pose Estimation Maps |
| 348 | Poster | GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning |
| 350 | Spotlight | Deep Adversarial Metric Learning |
| 350 | Poster | Deep Adversarial Metric Learning |
| 353 | Poster | Revisiting Video Saliency: A Large-scale Benchmark and a New Model |
| 362 | Poster | Graph-Cut RANSAC |
| 363 | Poster | Five-point Fundamental Matrix Estimation for Uncalibrated Cameras |
| 367 | Poster | Hashing as Tie-Aware Learning to Rank |
| 368 | Poster | Optimizing Local Feature Descriptors for Nearest Neighbor Matching |
| 369 | Oral | Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies |
| 369 | Poster | Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies |
| 374 | Spotlight | Consensus Maximization for Semantic Region Correspondences |
| 374 | Poster | Consensus Maximization for Semantic Region Correspondences |
| 380 | Poster | ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing |
| 391 | Poster | Motion-Guided Cascaded Refinement Network for Video Object Segmentation |
| 397 | Poster | Zigzag Learning for Weakly Supervised Object Detection |
| 405 | Spotlight | Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models |
| 405 | Poster | Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models |
| 406 | Spotlight | VITON: An Image-based Virtual Try-on Network |
| 406 | Poster | VITON: An Image-based Virtual Try-on Network |
| 408 | Poster | Cross-Domain Self-supervised Multi-task Feature Learning Using Synthetic Game Imagery |
| 409 | Poster | LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image |
| 418 | Poster | Thoracic Disease Identification and Localization with Limited Supervision |
| 419 | Poster | Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks |
| 420 | Poster | Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation |
| 421 | Poster | Deep End-to-End Time-of-Flight Imaging |
| 423 | Spotlight | Fast and Accurate Online Video Object Segmentation via Tracking Parts |
| 423 | Poster | Fast and Accurate Online Video Object Segmentation via Tracking Parts |
| 425 | Poster | Min-Entropy Latent Model for Weakly Supervised Object Detection |
| 429 | Poster | Future Frame Prediction for Anomaly Detection A New Baseline |
| 430 | Poster | Face Aging with Identity-Preserved Conditional Generative Adversarial Networks |
| 431 | Poster | Learning to Compare: Relation Network for Few-Shot Learning |
| 435 | Oral | Deep Layer Aggregation |
| 435 | Poster | Deep Layer Aggregation |
| 436 | Poster | Style Aggregated Network for Facial Landmark Detection |
| 442 | Spotlight | M3: Multimodal Memory Modelling for Video Captioning |
| 442 | Poster | M3: Multimodal Memory Modelling for Video Captioning |
| 449 | Poster | Classification Driven Dynamic Image Enhancement |
| 456 | Poster | Generative Image Inpainting with Contextual Attention |
| 458 | Spotlight | Iterative Visual Reasoning Beyond Convolutions |
| 458 | Poster | Iterative Visual Reasoning Beyond Convolutions |
| 460 | Poster | Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification |
| 465 | Spotlight | Textbook Question Answering under Teacher Guidance with Memory Networks |
| 465 | Poster | Textbook Question Answering under Teacher Guidance with Memory Networks |
| 468 | Poster | Multi-Level Factorisation Net for Person Re-Identification |
| 471 | Spotlight | Functional Map of the World |
| 471 | Poster | Functional Map of the World |
| 473 | Poster | A Two-Step Disentanglement Method |
| 475 | Poster | Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization |
| 482 | Poster | Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet? |
| 483 | Oral | Left-Right Comparative Recurrent Model for Stereo Matching |
| 483 | Poster | Left-Right Comparative Recurrent Model for Stereo Matching |
| 487 | Oral | Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input |
| 487 | Poster | Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input |
| 488 | Spotlight | Zero-Shot Sketch-Image Hashing |
| 488 | Poster | Zero-Shot Sketch-Image Hashing |
| 490 | Spotlight | Interpretable Convolutional Neural Networks |
| 490 | Poster | Interpretable Convolutional Neural Networks |
| 491 | Poster | Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial Curves |
| 493 | Poster | Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior |
| 494 | Poster | Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB |
| 500 | Spotlight | Generating Synthetic X-ray Images of a Person from the Surface Geometry |
| 500 | Poster | Generating Synthetic X-ray Images of a Person from the Surface Geometry |
| 505 | Poster | Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification |
| 506 | Poster | Unsupervised CCA |
| 510 | Poster | Discovering Point Lights with Intensity Distance Fields |
| 512 | Poster | Universal Denoising Networks : A Novel CNN-based Network Architecture for Image Denoising |
| 517 | Poster | Easy Identification from Better Constraints: Multi-Shot Person Re-Identification from Reference Constraints |
| 533 | Spotlight | Recurrent Pixel Embedding for Instance Grouping |
| 533 | Poster | Recurrent Pixel Embedding for Instance Grouping |
| 534 | Poster | Recurrent Scene Parsing with Perspective Understanding in the Loop |
| 540 | Poster | Learning to Hash by Discrepancy Minimization |
| 542 | Poster | Fast End-to-End Trainable Guided Filter |
| 550 | Poster | Disentangling Structure and Aesthetics for Content-aware Image Completion |
| 552 | Oral | An Analysis of Scale Invariance in Object Detection - SNIP |
| 552 | Poster | An Analysis of Scale Invariance in Object Detection - SNIP |
| 561 | Poster | CSGNet: Neural Shape Parser for Constructive Solid Geometry |
| 565 | Oral | Finding Tiny Faces in the Wild with Generative Adversarial Network |
| 565 | Poster | Finding Tiny Faces in the Wild with Generative Adversarial Network |
| 567 | Spotlight | SSNet: Scale Selection Network for Online 3D Action Prediction |
| 567 | Poster | SSNet: Scale Selection Network for Online 3D Action Prediction |
| 568 | Spotlight | Integrated facial landmark localization and super-resolution of real-world very low resolution faces in arbitrary poses with GANs |
| 568 | Poster | Integrated facial landmark localization and super-resolution of real-world very low resolution faces in arbitrary poses with GANs |
| 569 | Poster | The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation |
| 573 | Poster | In-Place Activated BatchNorm for Memory-Optimized Training of DNNs |
| 574 | Poster | Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks |
| 581 | Spotlight | Deep Cross-media Knowledge Transfer |
| 581 | Poster | Deep Cross-media Knowledge Transfer |
| 588 | Poster | Coupled End-to-end Transfer Learning with Generalized Fisher Information |
| 589 | Poster | Knowledge Aided Consistency for Weakly Supervised Phrase Grounding |
| 593 | Poster | Viewpoint-aware Attentive Multi-view Inference for Vehicle Re-identification |
| 594 | Poster | MatNet: Modular Attention Network for Referring Expression Comprehension |
| 598 | Poster | CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation |
| 601 | Spotlight | NISP: Pruning Networks using Neuron Importance Score Propagation |
| 601 | Poster | NISP: Pruning Networks using Neuron Importance Score Propagation |
| 603 | Poster | Who Let The Dogs Out? Modeling Dog Behavior From Visual Data |
| 609 | Poster | Efficient Video Object Segmentation via Network Modulation |
| 615 | Poster | Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision |
| 618 | Poster | Feedback-prop: Convolutional Neural Network Inference under Partial Evidence |
| 619 | Poster | A Memory Network Approach for Story-based Temporal Summarization of 360?Videos |
| 620 | Poster | Improving Occlusion and Hard Negative Handling for Single-Stage Object Detectors |
| 623 | Poster | UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition |
| 630 | Spotlight | Learning a Toolchain for Image Restoration |
| 630 | Poster | Learning a Toolchain for Image Restoration |
| 631 | Poster | Learning to Act Properly: Predicting and Explaining Affordances from Images |
| 632 | Poster | Learning a Discriminative Feature Network for Semantic Segmentation |
| 633 | Poster | Optimizing Video Object Detection via a Scale-Time Lattice |
| 642 | Poster | ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices |
| 643 | Poster | Cascaded Pyramid Network for Multi-Person Pose Estimation |
| 648 | Poster | Seeing Temporal Modulation of Lights from Standard Cameras |
| 649 | Poster | Point-wise Convolutional Neural Networks |
| 668 | Spotlight | Fine-grained Video Captioning for Sports Narrative |
| 668 | Poster | Fine-grained Video Captioning for Sports Narrative |
| 671 | Poster | Dense 3D Regression for Hand Pose Estimation |
| 672 | Poster | Missing Slice Recovery for Tensors Using a Low-rank Model in Embedded Space |
| 673 | Poster | Learning Convolutional Networks for Content-weighted Image Compression |
| 678 | Poster | Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking |
| 680 | Poster | Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation |
| 683 | Poster | First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations |
| 687 | Spotlight | Hand PointNet: 3D Hand Pose Estimation using Point Sets |
| 687 | Poster | Hand PointNet: 3D Hand Pose Estimation using Point Sets |
| 695 | Poster | Recovering Realistic Texture in Image Super-resolution by Spatial Feature Modulation |
| 700 | Poster | Cube Padding for Weakly-Supervised Saliency Prediction in 360$^{\circ}$ Videos |
| 710 | Poster | A Face to Face Neural Conversation Model |
| 711 | Poster | SurfConv: Bridging 3D and 2D Convolution for RGBD Images |
| 717 | Poster | Dynamic Video Segmentation Network |
| 721 | Poster | Multiple Granularity Group Interaction Prediction |
| 732 | Spotlight | Visual Question Reasoning on General Dependency Tree |
| 732 | Poster | Visual Question Reasoning on General Dependency Tree |
| 733 | Poster | From Lifestyle VLOGs to Everyday Interactions |
| 735 | Poster | COCO-Stuff: Thing and Stuff Classes in Context |
| 736 | Spotlight | GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB |
| 736 | Poster | GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB |
| 739 | Poster | Non-local Neural Networks |
| 740 | Poster | Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs |
| 744 | Oral | Taskonomy: Disentangling Task Transfer Learning |
| 744 | Poster | Taskonomy: Disentangling Task Transfer Learning |
| 747 | Spotlight | Embodied Real-World Active Perception |
| 747 | Poster | Embodied Real-World Active Perception |
| 754 | Spotlight | SfSNet : Learning Shape, Reflectance and Illuminance of Faces `in the wild' |
| 754 | Poster | SfSNet : Learning Shape, Reflectance and Illuminance of Faces `in the wild' |
| 756 | Poster | End-to-end Recovery of Human Shape and Pose |
| 757 | Poster | Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene |
| 759 | Poster | Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction |
| 762 | Poster | A Fast Resection-Intersection Method for the Known Rotation Problem |
| 764 | Poster | Image Generation from Scene Graphs |
| 765 | Spotlight | What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets |
| 765 | Poster | What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets |
| 766 | Poster | PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation |
| 768 | Oral | High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs |
| 768 | Poster | High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs |
| 769 | Poster | Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks |
| 777 | Spotlight | Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference |
| 777 | Poster | Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference |
| 778 | Oral | Finding It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Video" |
| 778 | Poster | Finding It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Video" |
| 779 | Poster | Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatio-temporal Patterns |
| 784 | Poster | Kernelized Subspace Pooling for Deep Local Descriptors |
| 786 | Poster | Video Rain Removal By Multiscale Convolutional Sparse Coding |
| 789 | Poster | Learning from Millions of 3D Scans for Large-scale 3D Face Recognition |
| 792 | Poster | Referring Relationships |
| 794 | Poster | Improving Object Localization with Fitness NMS and Bounded IoU Loss |
| 801 | Spotlight | Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination |
| 801 | Poster | Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination |
| 809 | Spotlight | CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization |
| 809 | Poster | CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization |
| 811 | Spotlight | Visual Question Generation as Dual Task of Visual Question Answering |
| 811 | Poster | Visual Question Generation as Dual Task of Visual Question Answering |
| 812 | Spotlight | Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation |
| 812 | Poster | Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation |
| 816 | Poster | Learning Dual Convolutional Neural Networks for Low-Level Vision |
| 823 | Poster | Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation |
| 836 | Spotlight | MegDet: A Large Mini-Batch Object Detector |
| 836 | Poster | MegDet: A Large Mini-Batch Object Detector |
| 842 | Poster | AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks |
| 844 | Spotlight | TOM-Net: Learning Transparent Object Matting from a Single Image |
| 844 | Poster | TOM-Net: Learning Transparent Object Matting from a Single Image |
| 847 | Poster | End-to-End Deep Kronecker-Product Matching for Person Re-identification |
| 849 | Poster | Semantic Visual Localization |
| 851 | Poster | Joint Cuts and Matching of Partitions in One Graph |
| 853 | Spotlight | Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions |
| 853 | Poster | Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions |
| 862 | Poster | Crowd Counting via Adversarial Cross-Scale Consistency Pursuit |
| 874 | Poster | Deep Group-shuffling Random Walk for Person Re-identification |
| 878 | Spotlight | Learning to Detect Features in Texture Images |
| 878 | Poster | Learning to Detect Features in Texture Images |
| 888 | Poster | Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification |
| 890 | Poster | CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles |
| 892 | Poster | Context-aware Deep Feature Compression for High-speed Visual Tracking |
| 894 | Poster | Deep Material-aware Cross-spectral Stereo Matching |
| 899 | Poster | Deep Extreme Cut: From Extreme Points to Object Segmentation |
| 906 | Spotlight | Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images |
| 906 | Poster | Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images |
| 908 | Poster | Harmonious Attention Network for Person Re-Identication |
| 909 | Spotlight | Unsupervised Deep Generative Adversarial Hashing Network |
| 909 | Poster | Unsupervised Deep Generative Adversarial Hashing Network |
| 910 | Poster | Pseudo-Mask Augmented Object Detection |
| 914 | Spotlight | LSTM stack-based Neural Multi-sequence Alignment TeCHnique (NeuMATCH) |
| 914 | Poster | LSTM stack-based Neural Multi-sequence Alignment TeCHnique (NeuMATCH) |
| 927 | Poster | Adversarial Complementary Learning for Weakly Supervised Object Localization |
| 932 | Oral | Unsupervised Discovery of Object Landmarks as Structural Representations |
| 932 | Poster | Unsupervised Discovery of Object Landmarks as Structural Representations |
| 936 | Poster | DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map |
| 944 | Poster | Monocular Relative Depth Perception with Web Stereo Data Supervision |
| 948 | Poster | Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification |
| 952 | Poster | Objects as context for detecting their semantic parts |
| 954 | Poster | Camera Style Adaptation for Person Re-identification |
| 961 | Poster | Conditional Generative Adversarial Network for Structured Domain Adaptation |
| 962 | Poster | Rotation-sensitive Regression for Oriented Scene Text Detection |
| 963 | Poster | Residual Parameter Transfer for Deep Domain Adaptation |
| 967 | Spotlight | SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation |
| 967 | Poster | SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation |
| 974 | Spotlight | Weakly Supervised Instance Segmentation using Class Peak Response |
| 974 | Poster | Weakly Supervised Instance Segmentation using Class Peak Response |
| 978 | Poster | Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network |
| 984 | Oral | Rotation Averaging and Strong Duality |
| 984 | Poster | Rotation Averaging and Strong Duality |
| 985 | Poster | PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning |
| 999 | Oral | Im2Flow: Motion Hallucination from Static Images for Action Recognition |
| 999 | Poster | Im2Flow: Motion Hallucination from Static Images for Action Recognition |
| 1001 | Poster | Feature Quantization for Defending Against Distortion of Images |
| 1016 | Poster | End-to-end weakly-supervised semantic alignment |
| 1018 | Spotlight | PointGrid: A Deep Network for 3D Shape Understanding |
| 1018 | Poster | PointGrid: A Deep Network for 3D Shape Understanding |
| 1019 | Poster | Imagine it for me: Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts |
| 1020 | Poster | A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds |
| 1022 | Poster | A Benchmark for Articulated Human Pose Estimation and Tracking |
| 1024 | Poster | Boosting Self-Supervised Learning via Knowledge Transfer |
| 1025 | Spotlight | PPFNet: Global Context Aware Local Features for Robust 3D Point Matching |
| 1025 | Poster | PPFNet: Global Context Aware Local Features for Robust 3D Point Matching |
| 1027 | Spotlight | Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments |
| 1027 | Poster | Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments |
| 1029 | Spotlight | Fast Video Object Segmentation by Reference-Guided Mask Propagation |
| 1029 | Poster | Fast Video Object Segmentation by Reference-Guided Mask Propagation |
| 1035 | Poster | Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes |
| 1036 | Poster | Video Person Re-identification with Competitive Snippet-similarity Aggregation and Co-attentive Snippet Embedding |
| 1037 | Poster | One-shot Action Localization by Sequence Matching Network |
| 1052 | Poster | Efficient Subpixel Refinement with Symbolic Linear Predictors |
| 1056 | Poster | Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning |
| 1057 | Oral | Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification |
| 1057 | Poster | Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification |
| 1058 | Poster | Single Image Reflection Separation with Perceptual Losses |
| 1063 | Spotlight | AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions |
| 1063 | Poster | AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions |
| 1067 | Poster | Recognize Actions by Disentangling Components of Dynamics |
| 1078 | Poster | Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains |
| 1082 | Poster | Attention-aware Compositional Network for Person Re-Identification |
| 1083 | Poster | HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification |
| 1085 | Poster | Mask-guided Contrastive Attention Model for Person Re-Identification |
| 1097 | Spotlight | Pose-Guided Photorealistic Face Rotation |
| 1097 | Poster | Pose-Guided Photorealistic Face Rotation |
| 1099 | Spotlight | Automatic 3D Indoor Scene Modeling from Single Panorama |
| 1099 | Poster | Automatic 3D Indoor Scene Modeling from Single Panorama |
| 1101 | Spotlight | SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-rigid Motion |
| 1101 | Poster | SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-rigid Motion |
| 1103 | Poster | A Biresolution Spectral framework for Product Quantization |
| 1109 | Poster | Dynamic Zoom-in Network for Fast Object Detection in Large Images |
| 1110 | Poster | On the Importance of Label Quality for Semantic Segmentation |
| 1113 | Poster | EPINET: A Fully-Convolutional Neural Network for Light Field Depth Estimation by Using Epipolar Geometry |
| 1114 | Poster | A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking |
| 1118 | Poster | Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos |
| 1124 | Poster | Scalable and Effective Deep CCA via Soft Decorrelation |
| 1126 | Poster | High-order tensor regularization with application to attribute ranking |
| 1128 | Oral | 3D-RCNN: Instance-level 3D Scene Understanding via Render-and-Compare |
| 1128 | Poster | 3D-RCNN: Instance-level 3D Scene Understanding via Render-and-Compare |
| 1129 | Spotlight | FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds |
| 1129 | Poster | FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds |
| 1133 | Poster | Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network |
| 1134 | Poster | Decorrelated Batch Normalization |
| 1139 | Spotlight | Unsupervised Textual Grounding: Linking Words to Image Concepts |
| 1139 | Poster | Unsupervised Textual Grounding: Linking Words to Image Concepts |
| 1156 | Poster | Scale-recurrent Network for Deep Image Deblurring |
| 1162 | Poster | Low-Shot Recognition with Imprinted Weights |
| 1163 | Oral | Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering |
| 1163 | Poster | Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering |
| 1164 | Poster | Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation |
| 1170 | Poster | Facelet-Bank for Fast Portrait Manipulation |
| 1172 | Poster | Duplex Generative Adversarial Network for Unsupervised Domain Adaptation |
| 1173 | Poster | Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation |
| 1177 | Poster | Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks |
| 1178 | Poster | Structure Preserving Video Prediction |
| 1182 | Poster | Tagging Like Humans: Diverse and Distinct Image Annotation |
| 1185 | Poster | Learning to Sketch with Shortcut Cycle Consistency |
| 1186 | Poster | GroupCap: Group-based Image Captioning with Structured Relevance and Diversity Constraints |
| 1193 | Spotlight | Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks |
| 1193 | Poster | Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks |
| 1194 | Poster | Hyperparameter Optimization for Tracking with Continuous Deep Q-Learning |
| 1202 | Spotlight | Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective |
| 1202 | Poster | Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective |
| 1203 | Spotlight | NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning |
| 1203 | Poster | NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning |
| 1209 | Spotlight | Detecting and Recognizing Human-Object Interactions |
| 1209 | Poster | Detecting and Recognizing Human-Object Interactions |
| 1213 | Poster | Augmenting Crowd-Sourced 3D Reconstructions using Semantic Detections |
| 1219 | Poster | Visual Relationship Learning with a Factorization-based Prior |
| 1224 | Poster | Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation |
| 1226 | Poster | Flow Guided Recurrent Neural Encoder for Video Salient Object Detection |
| 1230 | Poster | Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment |
| 1235 | Poster | Progressive Attention Guided Recurrent Network for Salient Object Detection |
| 1240 | Spotlight | Answer with Grounding Snippets: Focal Visual-Text Attention for Visual Question Answering |
| 1240 | Poster | Answer with Grounding Snippets: Focal Visual-Text Attention for Visual Question Answering |
| 1244 | Poster | Unsupervised Learning of Depth and Egomotion from Monocular Video Using 3D Geometric Constraints |
| 1247 | Poster | Repulsion Loss: Detecting Pedestrians in a Crowd |
| 1248 | Poster | PU-Net: Point Cloud Upsampling Network |
| 1249 | Spotlight | Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF |
| 1249 | Poster | Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF |
| 1251 | Poster | PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection |
| 1252 | Poster | Gated Fusion Network for Single Image Dehazing |
| 1255 | Spotlight | Interleaved Structured Sparse Convolutional Neural Networks |
| 1255 | Poster | Interleaved Structured Sparse Convolutional Neural Networks |
| 1258 | Poster | Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks |
| 1264 | Poster | End-to-end Flow Correlation Tracking with Spatial-temporal Attention |
| 1271 | Poster | Left/Right Asymmetric Layer Skippable Networks |
| 1276 | Oral | Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation |
| 1276 | Poster | Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation |
| 1280 | Spotlight | VITAL: VIsual Tracking via Adversarial Learning |
| 1280 | Poster | VITAL: VIsual Tracking via Adversarial Learning |
| 1282 | Poster | RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints |
| 1284 | Spotlight | Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints |
| 1284 | Poster | Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints |
| 1287 | Oral | Squeeze-and-Excitation Networks |
| 1287 | Poster | Squeeze-and-Excitation Networks |
| 1288 | Poster | Edit Probability for Scene Text Recognition |
| 1289 | Spotlight | Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning |
| 1289 | Poster | Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning |
| 1290 | Poster | Exploit the Unknown Gradually:~ One-Shot Video-Based Person Re-Identification by Stepwise Learning |
| 1294 | Poster | Learning to Localize Sound Source in Visual Scenes |
| 1296 | Poster | Dynamic Few-Shot Visual Learning without Forgetting |
| 1303 | Poster | Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features |
| 1304 | Poster | SINT++: Robust Visual Tracking via Adversarial Hard Positive Generation |
| 1308 | Poster | Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer |
| 1315 | Poster | Fast and Accurate Single Image Super-Resolution via Information Distillation Network |
CVPR2018百度云链接
考虑到有所有论文下载需求，于是本文将CVPR2018都下载了
所有论文百度云链接
链接：https://pan.baidu.com/s/1gt6ghy_C_QIOb1crqnog0A
提取码：关注【计算机视觉联盟】回复: CVPR2018