Last updated: 2021/01/25
- 2019/07/26 * - 更新28篇IIAI录用论文
- 2019/07/28 * - 更新11篇旷视ICCV2019
- 2019/08/28 * - 更新31篇Oral
- 2019/08/29 * - 增加116篇ICCV2019文章
- 2019/08/29 * - 增加35篇包含开源代码的ICCV2019
- 2019/09/12 * - ICCV 1998-2017最佳论文
- 2019/10/26 * - ICCV 所有论文百度云链接更新
- ICCV简介
- ICCV录用编号
- 起源人工智能研究院28篇
- 旷视11篇
- 2019ICCVOral31篇
- 增加116篇ICCV2019文章
- 增加35篇包含开源代码的ICCV2019
- ICCV1998-2017最佳论文
ICCV 的全称是 IEEE International Conference on Computer Vision，即国际计算机视觉大会，由IEEE主办，与计算机视觉模式识别会议（CVPR）和欧洲计算机视觉会议（ECCV）并称计算机视觉方向的三大顶级会议，被澳大利亚ICT学术会议排名和中国计算机学会等机构评为最高级别学术会议，在业内具有极高的评价。 不同于在美国每年召开一次的CVPR和只在欧洲召开的ECCV，ICCV在世界范围内每两年召开一次。ICCV论文录用率非常低，是三大会议中公认级别最高的 。上一届提交的论文中，其中621篇被接收，录用比例达 28.9%；其中 poster、spotlight、oral 的比例分别为 24.61%、2.61% 以及 2.09%。
今年有一名大会主席是来自香港中文大学的信息工程系系主任汤晓鸥，他同时还是中国科学院深圳先进技术研究院的副院长兼商汤科技创始人。其他三名大会主席则分别是首尔大学的 Kyoung Mu Lee 教授、伊利诺伊大学厄巴纳-香槟分校的 David Forsyth 教授以及苏黎世联邦理工学院的 Marc Pollefeys 教授。
本届大会最终的递交补充材料的截止日期为 3 月 29 日。大会召开时间为2019年10月27日至11月2日，举行地点是韩国首尔的 COEX 会议中心。
刚刚，计算机视觉三大顶会之一ICCV2019终于公布了它的最终论文接收结果，一共有1077篇论文被接收，接收率为25.02%
24 17 25 30 31 33 37 41 45 49 59 60 69 84 91 93 102 105 110 126 141 153 157 159 171 175 176 178 184 187 213 226 229 238 242 245 247 251 258 281 285 294 302 320 330 350 351 354 356 361 367 375 376 380 382 383 385 397 405 406 407 409 421 426 428 445 446 450 456 464 466 479 490 491 496 502 504 507 508 520 531 539 568 579 582 585 596 609 620 622 630 634 636 668 669 673 678 680 691 701 706 711 715 719 720 722 727 732 733 735 737 742 751 754 756 759 767 768 770 774 778 782 791 797 800 806 809 811 813 818 827 832 836 838 839 845 855 862 868 876 877 879 888 890 892 899 900 902 904 905 909 912 917 920 921 940 943 959 964 965 976 981 989 1001 1005 1006 1011 1017 1020 1023 1031 1032 1039 1040 1042 1045 1046 1057 1062 1067 1077 1083 1092 1093 1096 1097 1098 1104 1105 1111 1112 1113 1119 1135 1139 1142 1148 1160 1163 1165 1166 1168 1174 1180 1182 1197 1200 1205 1206 1211 1215 1223 1233 1245 1249 1252 1272 1277 1285 1288 1291 1323 1330 1334 1335 1342 1343 1356 1370 1378 1381 1384 1390 1394 1395 1403 1404 1406 1411 1412 1417 1422 1426 1428 1434 1439 1442 1452 1455 1457 1463 1477 1479 1485 1488 1501 1517 1527 1535 1538 1542 1550 1551 1552 1562 1565 1570 1574 1581 1583 1585 1586 1590 1592 1596 1597 1616 1621 1624 1630 1638 1639 1642 1643 1647 1648 1650 1652 1656 1657 1667 1672 1675 1681 1693 1700 1705 1706 1714 1743 1746 1768 1772 1773 1774 1779 1785 1788 1805 1811 1819 1820 1823 1826 1827 1829 1844 1850 1854 1855 1859 1860 1861 1863 1865 1866 1870 1874 1879 1881 1882 1911 1917 1919 1924 1926 1933 1942 1943 1959 1960 1963 1967 1970 1971 1972 1982 1983 1984 1990 2005 2010 2012 2017 2024 2029 2032 2037 2040 2043 2055 2065 2070 2077 2097 2101 2115 2126 2127 2132 2134 2140 2148 2149 2155 2157 2160 2163 2169 2177 2179 2205 2206 2209 2214 2223 2230 2235 2240 2245 2246 2247 2248 2259 2266 2267 2272 2275 2277 2282 2284 2286 2288 2289 2290 2291 2303 2304 2312 2322 2323 2336 2337 2338 2339 2344 2353 2355 2359 2385 2390 2391 2392 2397 2402 2406 2413 2419 2420 2421 2436 2437 2441 2448 2450 2454 2458 2470 2473 2478 2481 2490 2495 2498 2501 2511 2517 2521 2525 2531 2545 2547 2548 2551 2553 2555 2556 2557 2561 2563 2564 2571 2578 2580 2595 2601 2603 2607 2608 2609 2610 2613 2615 2619 2622 2633 2634 2637 2638 2642 2660 2661 2679 2683 2684 2690 2717 2725 2732 2739 2740 2768 2790 2792 2795 2796 2798 2799 2814 2820 2830 2833 2836 2838 2840 2842 2850 2855 2857 2862 2865 2872 2886 2899 2908 2912 2919 2927 2928 2939 2944 2957 2958 2962 2963 2964 2968 2979 2980 3001 3016 3034 3035 3036 3051 3058 3059 3060 3068 3072 3080 3095 3102 3104 3107 3110 3114 3116 3120 3123 3127 3128 3133 3136 3137 3139 3140 3141 3145 3151 3154 3164 3166 3172 3180 3185 3193 3197 3198 3203 3215 3220 3222 3233 3239 3242 3243 3246 3260 3272 3273 3280 3281 3286 3290 3293 3300 3315 3321 3326 3327 3339 3345 3346 3352 3359 3361 3372 3375 3378 3379 3380 3382 3391 3394 3398 3402 3403 3410 3419 3430 3435 3436 3438 3439 3443 3458 3462 3463 3464 3468 3476 3489 3492 3494 3496 3502 3505 3508 3510 3514 3518 3521 3523 3540 3544 3547 3548 3552 3554 3555 3556 3559 3571 3572 3589 3592 3593 3596 3609 3611 3618 3620 3622 3627 3632 3636 3638 3646 3652 3655 3658 3662 3665 3667 3670 3674 3676 3682 3693 3695 3700 3717 3718 3723 3729 3734 3735 3739 3740 3743 3749 3750 3758 3761 3762 3767 3768 3772 3786 3787 3788 3795 3807 3808 3813 3818 3821 3824 3832 3834 3838 3857 3860 3867 3869 3879 3882 3897 3919 3921 3923 3926 3932 3933 3937 3941 3942 3949 3964 3971 3987 3988 3992 3998 4006 4007 4009 4019 4021 4022 4024 4032 4033 4034 4042 4047 4057 4067 4075 4079 4085 4088 4090 4092 4093 4094 4097 4102 4105 4112 4113 4118 4121 4122 4124 4125 4130 4144 4151 4154 4159 4162 4164 4167 4168 4171 4176 4192 4194 4199 4211 4212 4217 4237 4245 4246 4248 4249 4253 4267 4275 4285 4289 4293 4305 4309 4311 4330 4341 4342 4343 4346 4365 4366 4367 4370 4374 4406 4410 4414 4428 4430 4434 4446 4449 4453 4481 4485 4500 4506 4509 4526 4530 4533 4534 4541 4549 4560 4562 4563 4576 4585 4599 4600 4602 4614 4618 4634 4647 4649 4660 4666 4672 4690 4697 4701 4702 4712 4721 4737 4757 4765 4766 4768 4785 4787 4794 4798 4811 4825 4835 4846 4848 4851 4856 4861 4865 4870 4874 4881 4890 4901 4903 4910 4925 4928 4943 4946 4971 4996 5005 5008 5011 5016 5018 5023 5029 5051 5052 5053 5062 5073 5088 5099 5103 5105 5112 5114 5116 5127 5128 5129 5131 5135 5136 5148 5158 5161 5162 5164 5171 5172 5174 5180 5183 5184 5195 5196 5201 5215 5223 5235 5264 5269 5274 5280 5290 5292 5296 5301 5302 5314 5321 5323 5338 5344 5348 5370 5378 5384 5393 5412 5413 5417 5423 5437 5444 5454 5455 5457 5465 5519 5532 5540 5548 5576 5582 5594 5601 5626 5649 5651 5657 5662 5672 5683 5684 5696 5698 5700 5704 5705 5725 5728 5742 5752 5797 5801 5810 5819 5823 5827 5844 5845 5853 5863 5869 5880 5892 5903 5925 5927 5935 5948 5950 5952 5957 5961 5968 6009 6021 6026 6034 6035 6036 6072 6083 6105 6132 6174 6175 6178 6191 6204 6209 6215 6221 6232 6250 6258 6267 6284 6287 6289 6294 6296 6302 6328 6329 6352 6367 6372 6379 6385 6398 6400 6403 6404 6405 6410 6414 6423 6428 6430 6433 6467 6471 6480 6483 6496 6506 6512 6519 6521 6529 6532 6534 6554 6563 6568 6578 6579 6597 6602 6608 6622 6625 6640 6668 6691 6696 6700 6740 6744 6752 6780 6783 6829 6886 6887 6929 6944 6968 6978 6981
IIAI主页：www.inceptioniai.org/
-
Unsupervised Video Object Segmentation via Attentive Graph Neural Networks
-
DUAL-GLOWs: Conditional Flow-Based Generative Models for Inter-Modality Transfer in Brain Imaging
-
Unsupervised Graph Association for Person Re-identification
-
Relational Attention Network for Crowd Counting
-
Attentional Neural Fields for Crowd Counting
-
Learning Compositional Neural Information Fusion for Human Parsing
-
RANet: Ranking Attention Network for Fast Video Object Segmentation
-
Learning to Mask Visible Regions for Occluded Pedestrian Detection
-
Boosted Feature Guided Refinement Network for Single-Shot Detection
-
Deep Contextual Attention for Human-Object Interaction Detection
-
Learning the Model Update for Siamese Trackers
-
3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
-
Learning Rich Features at High-Speed for Single-Shot Object Detection
-
Transductive learning for zero-shot object detection
-
Ground-to-aerial Image Geo-localization with a Hard Exemplar Reweighting Triplet Loss
-
Towards Bridging Semantic Gap to Improve Semantic Segmentation
-
Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks
-
Motion Deblurring via Human-Aware Attention Network
-
Gaussian Affinity for Max-margin Class Imbalanced Learning
-
A Deep Step Pattern Representation for Multimodal Retinal Image Registration
-
SegEQA: Video Segmentation based Visual Attention for Embodied Question Answering
-
Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering
-
Scoot: A Perceptual Metric for Facial Sketches
-
EGNet: Edge Guidance Network for Salient Object Detection
-
PointAE: Point Auto-encoder for 3D Statistical Shape and Texture Modelling
-
Understanding Human Gaze Communication by Spatio-temporal Graph Reasoning
-
Optimizing the F-measure for Threshold-free Salient Object Detection
-
SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion
1、Objects365: A Large-scale, High-quality Dataset for Object Detection
2、ThunderNet: Towards Real-time Generic Object Detection
3、Efficient and Accurate Arbitrary-Shaped Text Detection with PixelAggregation Network
4、Semi-supervised Skin Detection by Network with Mutual Guidance
5、Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
6、Disentangled Image Matting
7、Re-ID Driven Localization Refinement for Person Search
8、Vehicle Re-identification with Viewpoint-aware Metric Learning
9、MetaPruning: Meta Learning for Automatic Neural Network ChannelPruning
10、Symmetry-constrained Rectification Network for Scene Text Recognition
11、Learning to Paint with Model-based Deep Reinforcement Learning
- Interpolated Convolutional Networks for 3D Point Cloud Understanding
- Memory-Based Neighbourhood Embedding for Visual Recognition
- Learning Trajectory Dependencies for Human Motion Prediction
- Domain Adaptation for Structured Output via Discriminative Patch Representations
- Deep Non-Rigid Structure from Motion
- Scalable Place Recognition Under Appearance Change for Autonomous Driving
- Restoration of Non-rigidly Distorted Underwater Images using a Combination of Compressive Sensing and Local Polynomial Image Representations
- Consensus Maximization Tree Search Revisited
- Weakly Supervised Energy-Based Learning for Action Segmentation
- Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
- Controllable Artistic Text Style Transfer via Shape-Matching GAN
- Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition
- Expectation-Maximization Attention Networks for Semantic Segmentation
- VideoBERT: A Joint Model for Video and Language Representation Learning
- CARAFE: Content-Aware ReAssembly of FEatures
- Habitat: A Platform for Embodied AI Research
- Equivariant Multi-View Networks
- PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows
- Learnable Triangulation of Human Pose
- Learning Implicit Generative Models by Matching Perceptual Features
- COCO-GAN: Generation by Parts via Conditional Coordinating
- SlowFast Networks for Video Recognition
- Exploring Randomly Wired Neural Networks for Image Recognition
- Can GCNs Go as Deep as CNNs?
- Deep SR-ITM: Joint Learning of Super-resolution and Inverse Tone-Mapping for 4K UHD HDR Applications
- Meta-Sim Learning to Generate Synthetic Datasets
- Deep HoughVoting for 3D Object Detection in Point Clouds
- Variational Adversarial Active Learning
- Towards Unconstrained End-to-End Text Spotting
- Non-local Recurrent Neural Memory for Supervised Sequence Modeling
- Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels
- Similarity-Preserving Knowledge Distillation
- GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
- Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction
- Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers
- nocaps: novel object captioning at scale
- ThunderNet: Towards Real-time Generic Object Detection
- Scene GraphPrediction with Limited Labels
- Ego-Pose Estimation and Forecasting as Real-Time PD Control
- The Trajectron: Probabilistic Multi-Agent Trajectory Modeling withDynamic Spatiotemporal Graphs
- End-to-End Learning of Representations for Asynchronous Event-BasedData
- Efficient Learning on Point Clouds with Basis Point Sets
- Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
- Single-Stage Multi-Person Pose Machines
- Towards Unsupervised Image Captioning with Shared Multimodal Embeddings
- advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns
- Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images
- Relation Distillation Networks for Video Object Detection
- Object-Driven Multi-Layer Scene Decomposition From a Single Image
- Embarrassingly Simple Binary Representation Learning
- Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images
- Learning the Model Update for Siamese Trackers
- Distilling Knowledge From a Deep Pose Regressor Network
- Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
- ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
- Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation
- View N-gram Network for 3D Object Retrieval
- Semi-supervised Skin Detection by Network with Mutual Guidance
- Deep Self-Learning From Noisy Labels
- Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking
- Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning
- Expert Sample Consensus Applied to Camera Re-Localization
- SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition
- GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
- Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction
- Orientation-aware Semantic Segmentation on Icosahedron Spheres
- EMPNet: Neural Localisation and Mapping using Embedded Memory Points
- SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
- On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
- Goal-Driven Sequential Data Abstraction
- Recursive Cascaded Networks for Unsupervised Medical Image Registration
- Learn to Scale: Generating Multipolar Normalized Density Map for Crowd Counting
- HoloGAN: Unsupervised learning of 3D representations from natural images
- MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
- FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image
- Face De-occlusion using 3D Morphable Model and Generative Adversarialhttp://image.inha.ac.kr/paper/ICCV2019_Xaiowei.pdf
- Deep Meta Learning for Real-Time Target-Aware Visual Tracking
- Switchable Whitening for Deep Representation Learning
- Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
- Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction
- Task2Vec: Task Embedding for Meta-Learning
- ACE: Adapting to Changing Environments for Semantic Segmentation
- Few-shot Object Detection via Feature Reweighting
- Disentangling Propagation and Generation for Video Prediction
- An Empirical Study of Spatial Attention Mechanisms in Deep Networks
- Fashion++: Minimal Edits for Outfit Improvement
- Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment
- Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded
- SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation
- EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Association
- Texture Fields: Learning Texture Representations in Function Space
- AMASS: Archive of Motion Capture as Surface Shapes
- End-to-end Learning for Graph Decomposition
- Towards Multi-pose Guided Virtual Try-on Network
- Learning to Reconstruct 3D Manhattan Wireframes from a Single Image
- Coherent Semantic Attention for Image Inpainting
- LayoutVAE: Stochastic Scene Layout Generation from a Label Set
- Co-Evolutionary Compression for Unpaired Image Translation
- Enhancing Adversarial Example Transferability with an Intermediate Level Attack
- Simultaneous multi-view instance detection with learned geometric soft-constraints
- Gated2Depth: Real-time Dense Lidar from Gated Images
- Moment Matching for Multi-Source Domain Adaptation
- Learning Compositional Representations for Few-Shot Recognition
- Digging Into Self-Supervised Monocular Depth Estimation
- Deep Interpretable Non-Rigid Structure from Motion
- PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings
- Lifelong GAN: Continual Learning for Conditional Image Generation
- Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
- Towards Adversarially Robust Object Detection
- 6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
- Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction
- DAFL: Data-Free Learning of Student Networks
- Multi-adversarial Faster-RCNN for Unrestricted Object Detection
- Boosting Few-Shot Visual Learning with Self-Supervision
- A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers
- Embodied Visual Recognition
- Rethinking ImageNet Pre-training
- TensorMask: A Foundation for Dense Object Segmentation
- 3D Point Cloud Learning for Large-scale Environment Analysis and Place Recognition
- Selectivity or Invariance: Boundary-aware Salient Object Detection
- Creativity Inspired Zero-Shot Learning
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
- Correlation Congruence for Knowledge Distillation
- VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
- Episodic Training for Domain Generalization
- GarNet: A Two-stream Network for Fast and Accurate 3D Cloth Draping
- Semi-supervised Domain Adaptation via Minimax Entropy
- xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera
- Canonical Surface Mapping via Geometric Cycle Consistency
- Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
- U4D: Unsupervised 4D Dynamic Scene Understanding
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation
- SPGNet: Semantic Prediction Guidance for Scene Parsing
- Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
- DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense
- Closed-Form Optimal Two-View Triangulation Based on Angular Errors
- Learning Combinatorial Embedding Networks for Deep Graph Matching
- A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
- Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement
- Symmetry-constrained Rectification Network for Scene Text Recognition
- STM: SpatioTemporal and Motion Encoding for Action Recognition
- Explicit Shape Encoding for Real-Time Instance Segmentation
- Few-Shot Learning with Global Class Representations
- Symmetric Cross Entropy for Robust Learning with Noisy Labels
- Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation
- DADA: Depth-Aware Domain Adaptation in Semantic Segmentation
- Bidirectional One-Shot Unsupervised Domain Mapping
- Joint Monocular 3D Detection and Tracking
- MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation
- Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data
- Towards High-Resolution Salient Object Detection
- Confidence Regularized Self-Training
- Optimizing the F-measure for Threshold-free Salient Object Detectionhttp://data.kaizhao.net/publications/iccv2019fmeasure.pdf
- Perspective-Guided Convolution Networks for Crowd Counting
- End-to-End Wireframe Parsing
- Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
- From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer
https://github. com/xhp-hust-2018-2011/S-DCNet
- Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN
- What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention
- CompenNet++: End-to-end Full Projector Compensation
- Pose-aware Dynamic Attention for Human Object Interaction Detection
- Temporally-Aggregating Spatial Encoder-Decoder for Video Saliency Detection
- PU-GAN: a Point Cloud Upsampling Adversarial Network
- A Closed-form Solution to Universal Style Transfer
- Video Face Clustering with Unknown Number of Clusters
- TSM: Temporal Shift Module for Efficient Video Understanding
- Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
- 3D-RelNet: Joint Object and Relational Network for 3D Prediction
- Few-shot Unsupervised Image-to-Image Translation
- Metric Learning with HORDE: High-Order Regularizer for Deep Embeddings
- Model Vulnerability to Distributional Shifts over Image Transformation Sets
- Language-Conditioned Graph Networks for Relational Reasoning
- Domain Intersection and Domain Difference
- Probabilistic Face Embeddings
- Counting with Focus for Free
- CCNet: Criss-Cross Attention for Semantic Segmentation
- ABD-Net: Attentive but Diverse Person Re-Identification
- AutoGAN: Neural Architecture Search for Generative Adversarial Networks
- SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation with Semi-supervised Learning
- Tex2Shape: Detailed Full Human Body Geometry from a Single Image
- FCOS: Fully Convolutional One-Stage Object Detectio
Piotr Dollar, Facebook AI Research
Ross Girshick, Facebook AI Research
Antonio Criminisi, Microsoft Research
Samuel Rota Bulò, Microsoft Research
Yejin Choi, Stony Brook University
Alexander Berg, University of North Carolina at Chapel Hill
Tamara Berg, University of North Carolina at Chapel Hill
Kristen Grauman, University of Texas at Austin2009Discriminative models for multi-class object layoutChaitanya Desai, University of California Irvine; et al.
Charless Fowlkes, University of California Irvine
Elizabeth Bullitt, University of North Carolina at Chapel Hill
Sarang Joshi, University of Utah
Didier Henrion, LAAS-CNRS2003Detecting Pedestrians using Patterns of Motion and AppearancePaul Viola, Microsoft Research; et al.
Daniel Snow, Mitsubishi Electric Research Laboratories
Alan L. Yuille, University of California Los Angeles
Song-Chun Zhu, University of California Los Angeles
Andrew Zisserman, University of Oxford
Jana Kosecka, University of California Berkeley
Shankar Sastry, University of California Berkeley
Steven Seitz, Carnegie Mellon University1998Self-Calibration and Metric Reconstruction in spite of Varying and Unknown Internal Camera Paramet...Marc Pollefeys, Katholieke Universiteit Leuven; et al.
Luc Van Gool, Katholieke Universiteit Leuven
Andrew Zisserman, University of Oxford
| 2017 | Mask R-CNN | Kaiming He, Facebook AI Research; et al. |
| 2015 | Deep Neural Decision Forests | Peter Kontschieder, Microsoft Research; et al. |
| 2013 | From Large Scale Image Categorization to Entry-Level Categories | Vicente Ordonez, University of North Carolina at Chapel Hill; et al. |
| 2011 | Relative Attributes | Devi Parikh, Toyota Technological Institute at Chicago |
| Kristen Grauman, University of Texas at Austin | ||
| 2009 | Discriminative models for multi-class object layout | Chaitanya Desai, University of California Irvine; et al. |
| 2007 | Population Shape Regression From Random Design Data | Bradley Davis, University of North Carolina at Chapel Hill; et al. |
| 2005 | Globally Optimal Estimates for Geometric Reconstruction Problems | Fredrik Kahl, Lund University |
| 2003 | Detecting Pedestrians using Patterns of Motion and Appearance | Paul Viola, Microsoft Research; et al. |
| Image Parsing: Unifying Segmentation, Detection and Recognition | Zhuowen Tu, University of California Los Angeles; et al. | |
| Image-based Rendering using Image-based Priors | Andrew Fitzgibbon, University of Oxford; et al. | |
| 2001 | Probabilistic Tracking with Exemplars in a Metric Space | Kentaro Toyama & Andrew Blake, Microsoft Research |
| The Space of All Stereo Images | Steven Seitz, University of Washington | |
| 1999 | Euclidean Reconstruction and Reprojection up to Subgroups | Yi Ma, University of California Berkeley; et al. |
| A Theory of Shape by Space Carving | Kiriakos Kutulakos, University of Rochester | |
| Steven Seitz, Carnegie Mellon University | ||
| 1998 | Self-Calibration and Metric Reconstruction in spite of Varying and Unknown Internal Camera Paramet... | Marc Pollefeys, Katholieke Universiteit Leuven; et al. |
| The Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences | Phil Torr, Microsoft Research; et al. |