IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017. IEEE Computer Society 2017, ISBN 978-1-5386-1032-9

Oral Session 1

1. Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence. 1-10
2. Robust Pseudo Random Fields for Light-Field Stereo Matching. 11-19
3. A Lightweight Approach for On-the-Fly Reflectance Estimation. 20-28
4. Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus. 29-38
5. Practical Projective Structure from Motion (P2SfM). 39-47

Spotlight Session 1

1. Anticipating Daily Intention Using On-wrist Motion Triggered Sensing. 48-56
2. Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction from a Single Image. 57-65
3. End-to-End Learning of Geometry and Context for Deep Stereo Regression. 66-75
4. Using Sparse Elimination for Solving Minimal Problems in Computer Vision. 76-84
5. High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference. 85-93
6. Temporal Tessellation: A Unified Approach for Video Analysis. 94-104
7. Learning Policies for Adaptive Tracking with Deep Feature Cascades. 105-114
8. Temporal Shape Super-Resolution by Intra-frame Motion Encoding Using High-fps Structured Light. 115-123

Poster 1

1. Real-Time Monocular Pose Estimation of 3D Objects Using Temporally Consistent Local Color Histograms. 124-132
2. CAD Priors for Accurate and Flexible Instance Reconstruction. 133-142
3. Colored Point Cloud Registration Revisited. 143-152
4. Learning Compact Geometric Features. 153-161
5. Joint Layout Estimation and Global Multi-view Registration for Indoor Reconstruction. 162-171
6. A Geometric Framework for Statistical Analysis of Trajectories with Distinct Temporal Spans. 172-181
7. An Optimal Transportation Based Univariate Neuroimaging Index. 182-191
8. S^3FD: Single Shot Scale-Invariant Face Detector. 192-201
9. Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection. 202-211
10. Learning Uncertain Convolutional Features for Accurate Saliency Detection. 212-221
11. Zero-Order Reverse Filtering. 222-230
12. Learning Blind Motion Deblurring. 231-240
13. Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising. 241-250
14. Learning to Super-Resolve Blurry Face and Text Images. 251-260
15. Video Frame Interpolation via Adaptive Separable Convolution. 261-270
16. Deep Occlusion Reasoning for Multi-camera Multi-target Detection. 271-279
17. Encouraging LSTMs to Anticipate Actions Very Early. 280-289
18. PathTrack: Fast Trajectory Annotation with Path Supervision. 290-299
19. Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies. 300-311
20. MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation. 312-321
21. Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning. 322-331
22. Non-convex Rank/Sparsity Regularization and Local Minima. 332-340
23. A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework. 341-349
24. HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis. 350-359
25. No Fuss Distance Metric Learning Using Proxies. 360-368
26. Benchmarking and Error Diagnosis in Multi-instance Pose Estimation. 369-378
27. Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification. 379-387
28. Fashion Forward: Forecasting Visual Style in Fashion. 388-397
29. Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach. 398-407
30. Flow-Guided Feature Aggregation for Video Object Detection. 408-417
31. Reasoning About Fine-Grained Attribute Phrases Using Reference Games. 418-427
32. DeNet: Scalable Real-Time Object Detection with Directed Sparse Sampling. 428-436
33. MIHash: Online Hashing with Mutual Information. 437-445
34. SafetyNet: Detecting and Rejecting Adversarial Examples Robustly. 446-454
35. Recurrent Models for Situation Recognition. 455-463
36. Multi-label Image Recognition by Recurrently Discovering Attentional Regions. 464-472
37. Deep Determinantal Point Process for Large-Scale Multi-label Classification. 473-482
38. Visual Semantic Planning Using Deep Successor Representations. 483-492
39. Neural Person Search Machines. 493-501
40. DualNet: Learn Complementary Features for Image Recognition. 502-510
41. Higher-Order Integration of Hierarchical Convolutional Activations for Fine-Grained Visual Categorization. 511-520
42. Show, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner. 521-530
43. Attribute Recognition by Joint Recurrent Learning of Context and Correlation. 531-540
44. VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization. 541-549
45. Increasing CNN Robustness to Occlusions by Reducing Filter Support. 550-561
46. Exploiting Multi-grain Ranking Constraints for Precisely Searching Visually-similar Vehicles. 562-570
47. Recurrent Scale Approximation for Object Detection in CNN. 571-579
48. Embedding 3D Geometric Features for Rigid Object Part Segmentation. 580-588
49. Towards Context-Aware Interaction Recognition for Visual Relationship Detection. 589-598
50. When Unsupervised Domain Adaptation Meets Tensor Representations. 599-608
51. Look, Listen and Learn. 609-617
52. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. 618-626
53. Image-Based Localization Using LSTMs for Structured Feature Correlation. 627-637
54. Personalized Image Aesthetics. 638-647
55. Predicting Deeper into the Future of Semantic Segmentation. 648-657
56. Coordinating Filters for Faster Deep Neural Networks. 658-666
57. Unsupervised Representation Learning by Sorting Sequences. 667-676
58. A Read-Write Memory Network for Movie Story Understanding. 677-685
59. SegFlow: Joint Learning for Video Object Segmentation and Optical Flow. 686-695
60. Unsupervised Action Discovery and Localization in Videos. 696-705
61. Dense-Captioning Events in Videos. 706-715
62. Learning Long-Term Dependencies for Action Recognition with a Biologically-Inspired Deep Network. 716-725
63. Compressive Quantization for Fast Object Instance Search in Videos. 726-735
64. Complex Event Detection by Identifying Reliable Shots from Untrimmed Videos. 736-744
65. Deep Direct Regression for Multi-oriented Scene Text Detection. 745-753

Oral Session 2

1. Open Set Domain Adaptation. 754-763
2. Deformable Convolutional Networks. 764-773
3. Ensemble Diffusion for Retrieval. 774-783
4. FoveaNet: Perspective-Aware Urban Scene Parsing. 784-792
5. Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild. 793-803

Spotlight Session 2

1. Learning to Reason: End-to-End Module Networks for Visual Question Answering. 804-813
2. Hard-Aware Deeply Cascaded Embedding. 814-823
3. Query-Guided Regression Network with Context Policy for Phrase Grounding. 824-832
4. SuBiC: A Supervised, Structured Binary Code for Image Search. 833-842
5. Revisiting Unreasonable Effectiveness of Data in Deep Learning Era. 843-852
6. A Generative Model of People in Clothing. 853-862
7. Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models. 863-872
8. Improved Image Captioning via Policy Gradient optimization of SPIDEr. 873-881

Poster Session 2

1. Rolling Shutter Correction in Manhattan World. 882-890
2. Local-to-Global Point Cloud Registration Using a Dictionary of Viewpoint Descriptors. 891-899
3. 3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks. 900-909
4. BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera. 910-919
5. Quasiconvex Plane Sweep for Triangulation with Outliers. 920-928
6. "Maximizing Rigidity" Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views.929-937
7. Surface Registration via Foliation. 938-947
8. Rolling-Shutter-Aware Differential SfM and Image Rectification. 948-956
9. Corner-Based Geometric Calibration of Multi-focus Plenoptic Cameras. 957-965
10. Focal Track: Depth and Accommodation with Oscillating Lens Deformation. 966-974
11. Reconfiguring the Imaging Pipeline for Computer Vision. 975-984
12. Catadioptric HyperSpectral Light Field Imaging. 985-993
13. Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification. 994-1002
14. Real Time Eye Gaze Tracking with 3D Deformable Eye-Face Model. 1003-1011
15. Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks. 1012-1020
16. How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230, 000 3D Facial Landmarks). 1021-1030
17. Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression. 1031-1039
18. RankIQA: Learning from Rankings for No-Reference Image Quality Assessment. 1040-1049
19. Look, Perceive and Segment: Finding the Salient Objects in Images via Two-stream Fixation-Semantic CNNs. 1050-1058
20. Delving into Salient Object Subitizing and Detection. 1059-1067
21. Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation. 1068-1076
22. Learning Discriminative Data Fitting Functions for Blind Image Deblurring. 1077-1085
23. Video Deblurring via Semantic Segmentation and Pixel-Wise Non-linear Kernel. 1086-1094
24. On-demand Learning for Deep Image Restoration. 1095-1104
25. Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising. 1105-1113
26. Coherent Online Video Style Transfer. 1114-1123
27. SHaPE: A Novel Graph Theoretic Algorithm for Making Consensus-Based Decisions in Person Re-identification Systems. 1124-1133
28. Need for Speed: A Benchmark for Higher Frame Rate Object Tracking. 1134-1143
29. Learning Background-Aware Correlation Filters for Visual Tracking. 1144-1152
30. Robust Object Tracking Based on Temporal and Spatial Deep Networks. 1153-1162
31. Real-Time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor. 1163-1172
32. Predicting Human Activities Using Stochastic Grammar. 1173-1181
33. ProbFlow: Joint Optical Flow and Uncertainty Estimation. 1182-1191
34. Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems. 1192-1200
35. DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding. 1201-1210
36. BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography. 1211-1220
37. Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation. 1221-1230
38. An Empirical Study of Language CNN for Image Captioning. 1231-1240
39. Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning. 1241-1250
40. Areas of Attention for Image Captioning. 1251-1259
41. Generative Modeling of Audible Shapes for Object Perception. 1260-1269
42. Scene Graph Generation from Objects, Phrases and Region Captions. 1270-1279
43. Recurrent Multimodal Interaction for Referring Image Segmentation. 1280-1289
44. Learning Feature Pyramids for Human Pose Estimation. 1290-1299
45. Structured Attentions for Visual Question Answering. 1300-1309
46. Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection. 1310-1319
47. Cascaded Feature Network for Semantic Segmentation of RGB-D Images. 1320-1328
48. Encoder Based Lifelong Learning. 1329-1337
49. Transitive Invariance for Self-Supervised Visual Representation Learning. 1338-1347
50. Weakly Supervised Learning of Deep Metrics for Stereo Reconstruction. 1348-1357
51. Fine-Grained Recognition in the Wild: A Multi-task Domain Adaptation Approach. 1358-1367
52. SORT: Second-Order Response Transform for Visual Recognition. 1368-1377
53. Adversarial Examples for Semantic Segmentation and Object Detection. 1378-1387
54. Genetic CNN. 1388-1397
55. Channel Pruning for Accelerating Very Deep Neural Networks. 1398-1406
56. Infinite Latent Feature Selection: A Probabilistic Latent Graph-Based Ranking Approach. 1407-1415
57. Video Fill In the Blank Using LR/RL LSTMs with Spatial-Temporal Attentions. 1416-1425
58. Primary Video Object Segmentation via Complementary CNNs and Neighborhood Reversible Flow. 1426-1434
59. Attentive Semantic Video Generation Using Captions. 1435-1443
60. Following Gaze in Video. 1444-1452
61. Adaptive RNN Tree for Large-Scale Human Action Recognition. 1453-1461
62. Spatio-Temporal Person Retrieval via Natural Language Queries. 1462-1471
63. Automatic Spatially-Aware Fashion Concept Discovery. 1472-1480
64. ChromaTag: A Colored Marker and Fast Detection Algorithm. 1481-1490
65. Adversarial Image Perturbation for Privacy Protection A Game Theory Perspective. 1491-1500
66. WeText: Scene Text Detection under Weak Supervision. 1501-1509

Vision for X Oral Session 3

1. Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization. 1510-1519
2. Photographic Image Synthesis with Cascaded Refinement Networks. 1520-1529
3. SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again. 1530-1538
4. Unsupervised Creation of Parameterized Avatars. 1539-1547
5. Learning for Active 3D Mapping. 1548-1556

Poster Session 3

1. Toward Perceptually-Consistent Stereo: A Scanline Study. 1557-1565
2. Surface Normals in the Wild. 1566-1575
3. Unsupervised Learning of Stereo Matching. 1576-1584
4. Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation. 1585-1594
5. Learned Multi-patch Similarity. 1595-1603
6. Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation. 1604-1613
7. Unsupervised Adaptation for Deep Stereo. 1614-1622
8. Composite Focus Measure for High Quality Depth Maps. 1623-1631
9. Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition. 1632-1641
10. Recurrent 3D-2D Dual Learning for Large-Pose Facial Landmark Detection. 1642-1651
11. Anchored Regression Networks Applied to Age Estimation and Super Resolution. 1652-1661
12. Infant Footprint Recognition. 1662-1669
13. Self-Paced Kernel Estimation for Robust Blind Image Deblurring. 1670-1679
14. Super-Trajectory for Video Segmentation. 1680-1688
15. Be Your Own Prada: Fashion Synthesis with Structural Coherence. 1689-1697
16. Wavelet-SRNet: A Wavelet-Based CNN for Multi-scale Face Super Resolution. 1698-1706
17. Learning Gaze Transitions from Depth to Improve Video Saliency Estimation. 1707-1716
18. Joint Convolutional Analysis and Synthesis Sparse Representation for Single Image Layer Separation. 1717-1725
19. Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network. 1726-1734
20. Transformed Low-Rank Model for Line Pattern Noise Removal. 1735-1743
21. Weakly Supervised Manifold Learning for Dense Semantic Object Correspondence. 1744-1752
22. PanNet: A Deep Network Architecture for Pan-Sharpening. 1753-1761
23. Dual Motion GAN for Future-Flow Embedded Video Prediction. 1762-1770
24. Online Robust Image Alignment via Subspace Learning from Gradient Orientations. 1771-1780
25. Learning Dynamic Siamese Network for Visual Object Tracking. 1781-1789
26. High Order Tensor Formulation for Convolutional Sparse Coding. 1790-1798
27. Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems. 1799-1808
28. ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond. 1809-1818
29. Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection. 1819-1828
30. VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation.1829-1838
31. Multi-modal Factorized Bilinear Pooling with Co-attention Learning for Visual Question Answering. 1839-1848
32. SCNet: Learning Semantic Correspondence. 1849-1858
33. Soft Proposal Networks for Weakly Supervised Object Localization. 1859-1868
34. Class Rectification Hard Mining for Imbalanced Deep Learning. 1869-1878
35. Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs. 1879-1888
36. See the Glass Half Full: Reasoning About Liquid Containers, Their Volume and Content. 1889-1898
37. Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding. 1899-1907
38. Identity-Aware Textual-Visual Matching with Latent Co-attention. 1908-1917
39. Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-Temporal Path Proposals. 1918-1927
40. Learning from Noisy Labels with Distillation. 1928-1936
41. DSOD: Learning Deeply Supervised Object Detectors from Scratch. 1937-1945
42. Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues. 1946-1955
43. Chained Cascade Network for Object Detection. 1956-1964
44. VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition. 1965-1973
45. Unsupervised Learning of Important Objects from First-Person Videos. 1974-1982
46. An Analysis of Visual Question Answering Algorithms. 1983-1991
47. A Two Stream Siamese Convolutional Neural Network for Person Re-identification. 1992-2000
48. Joint Learning of Object and Action Detectors. 2001-2010
49. No More Discrimination: Cross City Adaptation of Road Scene Segmenters. 2011-2020
50. Open Vocabulary Scene Parsing. 2021-2029
51. Learned Watershed: End-to-End Learning of Seeded Segmentation. 2030-2038
52. Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes. 2039-2049
53. Scale-Adaptive Convolutions for Scene Parsing. 2050-2058
54. Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption. 2059-2069
55. Multi-task Self-Supervised Visual Learning. 2070-2079
56. A Self-Balanced Min-Cut Algorithm for Image Clustering. 2080-2088
57. Is Second-Order Information Helpful for Large-Scale Visual Recognition? 2089-2097
58. Factorized Bilinear Models for Image Recognition. 2098-2106
59. Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs. 2107-2115
60. Truncating Wide Networks Using Binary Tree Architectures. 2116-2124
61. Bringing Background into the Foreground: Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation. 2125-2135
62. View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data. 2136-2145
63. Joint Discovery of Object States and Manipulation Actions. 2146-2155
64. What Actions are Needed for Understanding Human Actions in Videos? 2156-2165
65. Lattice Long Short-Term Memory for Human Action Recognition. 2166-2175
66. Common Action Discovery and Localization in Unconstrained Videos. 2176-2185
67. Pixel-Level Matching for Video Object Segmentation Using Convolutional Neural Networks. 2186-2195
68. Am I a Baller? Basketball Performance Assessment from First-Person Videos. 2196-2204
69. Deep Cropping via Attention Box Prediction and Aesthetics Assessment. 2205-2213
70. Raster-to-Vector: Revisiting Floorplan Transformation. 2214-2222
71. Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework. 2223-2231
72. Vision for X & Computational Photography Spotlight Session 3
73. Playing for Benchmarks. 2232-2241
74. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. 2242-2251
75. GANs for Biological Image Synthesis. 2252-2261
76. Learning to Synthesize a 4D RGBD Light Field from a Single Image. 2262-2270
77. Neural EPI-Volume Networks for Shape from Light Field. 2271-2279
78. Material Editing Using a Physically Based Rendering Network. 2280-2288
79. Turning Corners into Cameras: Principles and Methods. 2289-2297
80. Linear Differential Constraints for Photo-Polarimetric Height Estimation. 2298-2306

Poster Session 4

1. Polynomial Solvers for Saturated Ideals. 2307-2316
2. Shape Inpainting Using 3D Generative Adversarial Network and Recurrent Convolutional Networks. 2317-2325
3. SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis. 2326-2334
4. Making Minimal Solvers for Absolute Pose Estimation Compact and Robust. 2335-2343
5. 3D Surface Detail Enhancement from a Single Normal Map. 2344-2352
6. RMPE: Regional Multi-person Pose Estimation. 2353-2362
7. Online Video Object Detection Using Association LSTM. 2363-2371
8. PolyFit: Polygonal Surface Reconstruction from Point Clouds. 2372-2380
9. Progressive Large Scale-Invariant Image Matching in Scale Space. 2381-2390
10. Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map. 2391-2400
11. Multi-view Non-rigid Refinement and Normal Selection for High Quality 3D Reconstruction. 2401-2409
12. Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection. 2410-2419
13. Depth and Image Restoration from Light Field in a Scattering Medium. 2420-2429
14. Video Reflection Removal Through Spatio-Temporal Optimization. 2430-2438
15. Efficient Online Local Metric Adaptation via Negative Samples for Person Re-identification. 2439-2447
16. Stepwise Metric Promotion for Unsupervised Video Person Re-identification. 2448-2457
17. Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis. 2458-2467
18. Group Re-identification via Unsupervised Transfer of Sparse Features Encoding. 2468-2477
19. Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification. 2478-2487
20. Decoder Network over Lightweight Reconstructed Feature for Fast Semantic Style Transfer. 2488-2496
21. Blind Image Deblurring with Outlier Handling. 2497-2505
22. Paying Attention to Descriptions Generated by Image Captioning Models. 2506-2515
23. Fast Image Processing with Fully-Convolutional Networks. 2516-2525
24. Robust Video Super-Resolution with Learned Temporal Dynamics. 2526-2534
25. Should We Encode Rain Streaks in Video as Deterministic or Stochastic? 2535-2544
26. Joint Bi-layer Optimization for Single-Image Rain Streak Removal. 2545-2553
27. Low-Dimensionality Calibration through Local Anisotropic Scaling for Robust Hand Model Personalization. 2554-2562
28. Non-Markovian Globally Consistent Multi-object Tracking. 2563-2573
29. CREST: Convolutional Residual Learning for Visual Tracking. 2574-2583
30. Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations. 2584-2592
31. Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios? 2593-2602
32. Performance Guaranteed Network Acceleration via High-Order Residual Quantization. 2603-2611
33. Deep Metric Learning with Angular Loss. 2612-2620
34. Compositional Human Pose Regression. 2621-2630
35. MUTAN: Multimodal Tucker Fusion for Visual Question Answering. 2631-2639
36. Revisiting IM2GPS in the Deep Learning Era. 2640-2649
37. Scene Parsing with Global Context Embedding. 2650-2658
38. A Simple Yet Effective Baseline for 3d Human Pose Estimation. 2659-2668
39. Dual-Glance Model for Deciphering Social Relationships. 2669-2678
40. Sketching with Style: Visual Search with Sketches and Aesthetic Context. 2679-2687
41. Point Set Registration with Global-Local Correspondence and Transformation Estimation. 2688-2696
42. SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-training on Indoor Segmentation? 2697-2706
43. A Unified Model for Near and Remote Sensing. 2707-2716
44. Directionally Convolutional Networks for 3D Shape Segmentation. 2717-2726
45. AMAT: Medial Axis Transform for Natural Images. 2727-2736
46. Deep Dual Learning for Semantic Image Segmentation. 2737-2745
47. Regional Interactive Image Segmentation Networks. 2746-2754
48. Learning Efficient Convolutional Networks through Network Slimming. 2755-2763
49. CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training. 2764-2773
50. Universal Adversarial Perturbations Against Semantic Image Segmentation. 2774-2783
51. Associative Domain Adaptation. 2784-2792
52. Introspective Neural Networks for Generative Modeling. 2793-2802
53. Towards a Unified Compositional Model for Visual Pattern Modeling. 2803-2812
54. Least Squares Generative Adversarial Networks. 2813-2821
55. Centered Weight Normalization in Accelerating Training of Deep Neural Networks. 2822-2830
56. Deep Growing Learning. 2831-2839
57. Smart Mining for Deep Metric Learning. 2840-2848
58. Temporal Generative Adversarial Nets with Singular Value Clipping. 2849-2858
59. Sampling Matters in Deep Embedding Learning. 2859-2867
60. DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. 2868-2876
61. Learning View-Invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras. 2877-2885
62. MarioQA: Answering Questions by Watching Gameplay Videos. 2886-2894
63. SBGAR: Semantics Based Group Activity Recognition. 2895-2904
64. Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video. 2905-2913
65. Unmasking the Abnormal Events in Video. 2914-2922
66. Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection. 2923-2932
67. Temporal Action Detection with Structured Segment Networks. 2933-2942
68. Jointly Recognizing Object Fluents and Tasks in Egocentric Videos. 2943-2951
69. Transferring Objects: Joint Inference of Container and Human Pose. 2952-2960
70. Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention. 2961-2969

Recognition 2 Oral Session 4

1. Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning. 2970-2979
2. Mask R-CNN. 2980-2988
3. Towards Diverse and Natural Image Descriptions via a Conditional GAN. 2989-2998
4. Focal Loss for Dense Object Detection. 2999-3007
5. Inferring and Executing Programs for Visual Reasoning. 3008-3017

Spotlight Session 4

1. Visual Forecasting by Imitating Dynamics in Natural Sequences. 3018-3027
2. TorontoCity: Seeing the World with a Million Eyes. 3028-3036
3. Low-Shot Visual Recognition by Shrinking and Hallucinating Features. 3037-3046
4. A Coarse-Fine Network for Keypoint Localization. 3047-3056
5. Detect to Track and Track to Detect. 3057-3065
6. Single Shot Text Detector with Regional Attention. 3066-3074
7. SubUNets: End-to-End Hand Shape and Continuous Sign Language Recognition. 3075-3084
8. A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition. 3085-3093

Poster Session 5

1. Probabilistic Structure from Motion with Objects (PSfMO). 3094-3103
2. A 3D Morphable Model of Craniofacial Shape and Texture Variation. 3104-3112
3. Multi-view Dynamic Shape Refinement Using Local Temporal Integration. 3113-3122
4. Learning Hand Articulations by Hallucinating Heat Distribution. 3123-3132
5. Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting. 3133-3141
6. Robust Hand Pose Estimation during the Interaction with an Unknown Object. 3142-3151
7. Detailed Surface Geometry and Albedo Recovery from RGB-D Video under Natural Illumination. 3152-3161
8. Monocular Free-Head 3D Gaze Tracking with Deep Learning and Geometry Constraints. 3162-3171
9. Filter Selection for Hyperspectral Estimation. 3172-3180
10. A Microfacet-Based Reflectance Model for Photometric Stereo with Highly Specular Surfaces. 3181-3189
11. Detecting Faces Using Inside Cascaded Contextual CNN. 3190-3198
12. A Novel Space-Time Representation on the Positive Semidefinite Cone for Facial Expression Recognition. 3199-3208
13. DeepCoder: Semi-Parametric Variational Autoencoders for Automatic Facial Action Coding. 3209-3218
14. Pose-Invariant Face Alignment with a Single CNN. 3219-3228
15. Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings. 3229-3238
16. Deeply-Learned Part-Aligned Representations for Person Re-identification. 3239-3248
17. Semantic Line Detection and Its Applications. 3249-3257
18. A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing. 3258-3267
19. Revisiting Cross-Channel Information Transfer for Chromatic Aberration Correction. 3268-3276
20. High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits. 3277-3286
21. Learning Visual Attention to Identify People with Autism Spectrum Disorder. 3287-3296
22. DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks. 3297-3305
23. Non-uniform Blind Deblurring by Reblurring. 3306-3314
24. Misalignment-Robust Joint Filter for Cross-Modal Image Pairs. 3315-3324
25. Low-Rank Tensor Completion: A Pseudo-Bayesian Learning Approach. 3325-3333
26. DeepCD: Learning Deep Complementary Descriptors for Patch Representations. 3334-3342
27. Beyond Standard Benchmarks: Parameterizing Performance Evaluation in Visual Object Tracking. 3343-3351
28. The Pose Knows: Video Forecasting by Generating Pose Futures. 3352-3361
29. What will Happen Next? Forecasting Player Moves in Sports Videos. 3362-3371
30. Robust Kronecker-Decomposable Component Analysis for Low-Rank Modeling. 3372-3381
31. Recurrent Topic-Transition GAN for Visual Paragraph Generation. 3382-3391
32. A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images. 3392-3400
33. Weakly Supervised Object Localization Using Things and Stuff Transfer. 3401-3410
34. Single Image Action Recognition Using Semantic Body Part Actions. 3411-3419
35. Incremental Learning of Object Detectors without Catastrophic Forgetting. 3420-3429
36. Generative Adversarial Networks Conditioned by Brain Signals. 3430-3438
37. Learning to Disambiguate by Asking Discriminative Questions. 3439-3448
38. Interpretable Explanations of Black Boxes by Meaningful Perturbation. 3449-3457
39. DeepRoadMapper: Extracting Road Topology from Aerial Images. 3458-3466
40. Monocular 3D Human Pose Estimation by Predicting Depth on Joints. 3467-3475
41. Large-Scale Image Retrieval with Attentive Deep Local Features. 3476-3485
42. Deep Globally Constrained MRFs for Human Pose Estimation. 3486-3495
43. Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning. 3496-3505
44. Multi-label Learning of Part Detectors for Heavily Occluded Pedestrian Detection. 3506-3515
45. SGN: Sequential Grouping Networks for Instance Segmentation. 3516-3524
46. Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors. 3525-3533
47. Aesthetic Critiques Generation for Photos. 3534-3543
48. Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization. 3544-3553
49. Two-Phase Learning for Weakly Supervised Object Localization. 3554-3563
50. Curriculum Dropout. 3564-3572
51. Predictor Combination at Test Time. 3573-3581
52. Guided Perturbations: Self-Corrective Behavior in Convolutional Neural Networks. 3582-3590
53. Learning Robust Visual-Semantic Embeddings. 3591-3600
54. PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories. 3601-3610
55. Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses. 3611-3620
56. CDTS: Collaborative Detection, Tracking, and Segmentation for Online Multiple Object Segmentation in Videos. 3621-3629
57. Temporal Superpixels Based on Proximity-Weighted Patch Matching. 3630-3638
58. Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge. 3639-3647
59. TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals. 3648-3656
60. Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction. 3657-3666
61. Leveraging Weak Semantic Relevance for Complex Video Event Classification. 3667-3676
62. Weakly Supervised Summarization of Web Videos. 3677-3686
63. FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras. 3687-3696
64. Fast Face-Swap Using Convolutional Neural Networks. 3697-3705
65. Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images. 3706-3715

Face and Human Behaviour Analysis Oral Session 5

1. First-Person Activity Forecasting with Online Inverse Reinforcement Learning. 3716-3725
2. Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources. 3726-3734
3. MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction. 3735-3744
4. RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos. 3745-3754
5. Temporal Non-volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition. 3755-3763

Spotlight Session 5

1. Attribute-Enhanced Face Recognition with Neural Tensor Fusion Networks. 3764-3773
2. Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro. 3774-3782
3. Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks with Spatiotemporal Transformer Modules. 3783-3791
4. Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition. 3792-3800
5. Learning Discriminative Aggregation Network for Video-Based Face Recognition. 3801-3810
6. Synergy between Face Alignment and Tracking via Discriminative Global Consensus Optimization. 3811-3819
7. SVDNet for Pedestrian Retrieval. 3820-3828
8. Towards More Accurate Iris Recognition Using Deeply Learned Spatially Corresponding Features. 3829-3838

Poster Session 6

1. Semantically Informed Multiview Surface Refinement. 3839-3847
2. BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth.3848-3856
3. Modeling Urban Scenes from Pointclouds. 3857-3866
4. Parameter-Free Lens Distortion Calibration of Central Cameras. 3867-3875
5. Pose Guided RGBD Feature Learning for 3D Object Pose Estimation. 3876-3884
6. Efficient Global Illumination for Morphable Models. 3885-3893
7. Low Compute and Fully Parallel Computer Vision with HashMatch. 3894-3903
8. Dense Non-rigid Structure-from-Motion and Shading with Unknown Albedos. 3904-3912
9. From Point Clouds to Mesh Using Regression. 3913-3922
10. Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras. 3923-3931
11. Space-Time Localization and Mapping. 3932-3941
12. Benchmarking Single-Image Reflection Removal Algorithms. 3942-3950
13. Attention-Aware Deep Reinforcement Learning for Video Face Recognition. 3951-3960
14. Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation. 3961-3970
15. Deep Facial Action Unit Recognition from Partially Labeled Data. 3971-3979
16. Pose-Driven Deep Convolutional Model for Person Re-identification. 3980-3989
17. Recognition of Action Units in the Wild with Deep Nets and a New Global-Local Loss. 3990-3999
18. Faster than Real-Time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses. 4000-4009
19. Towards Large-Pose Face Frontalization in the Wild. 4010-4019
20. A Joint Intrinsic-Extrinsic Prior Model for Retinex. 4020-4029
21. Going Unconstrained with Rolling Shutter Deblurring. 4030-4038
22. A Stagewise Refinement Model for Detecting Salient Objects in Images. 4039-4048
23. From Square Pieces to Brick Walls: The Next Challenge in Solving Jigsaw Puzzles. 4049-4057
24. Online Video Deblurring via Dynamic Temporal Blending Network. 4058-4067
25. Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector. 4068-4076
26. Fast Multi-image Matching via Density-Based Clustering. 4077-4086
27. Characterizing and Improving Stability in Neural Style Transfer. 4087-4096
28. Cross-Modal Deep Variational Hashing. 4097-4105
29. Spatial Memory for Context Reasoning in Object Detection. 4106-4116
30. Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval. 4117-4126
31. Learning a Recurrent Residual Fusion Network for Multimodal Matching. 4127-4136
32. Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition. 4137-4145
33. CoupleNet: Coupling Global Structure with Local Parts for Object Detection. 4146-4154
34. Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training. 4155-4164
35. Drone-Based Object Counting by Spatially Regularized Regional Proposal Network. 4165-4173
36. BlitzNet: A Real-Time Deep Network for Scene Understanding. 4174-4182
37. Situation Recognition with Graph Neural Networks. 4183-4192
38. Learning Visual N-Grams from Web Data. 4193-4202
39. Attention-Based Multimodal Fusion for Video Description. 4203-4212
40. Learning the Latent "Look": Unsupervised Discovery of a Style-Coherent Embedding from Fashion Images. 4213-4222
41. Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks. 4223-4232
42. Learning Discriminative Latent Attributes for Zero-Shot Classification. 4233-4242
43. PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN. 4243-4251
44. Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation. 4252-4260
45. Deep Free-Form Deformation Network for Object-Mask Registration. 4261-4269
46. Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering. 4270-4279
47. Learning Discriminative αβ-Divergences for Positive Definite Matrices. 4280-4289
48. Consensus Convolutional Sparse Coding. 4290-4298
49. Domain-Adaptive Deep Network Compression. 4299-4307
50. Self-Supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos. 4308-4317
51. Approximate Grassmannian Intersections: Subspace-Valued Subspace Learning. 4318-4326
52. Side Information in Robust Principal Component Analysis: Algorithms and Applications. 4327-4335
53. Summarization and Classification of Wearable Camera Streams by Learning the Distributions over Deep Features of Out-of-Sample Image Sequences. 4336-4344
54. Unsupervised Learning from Video to Detect Foreground Objects in Single Images. 4345-4353
55. Supplementary Meta-Learning: Towards a Dynamic Model for Deep Neural Networks. 4354-4363
56. Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision. 4364-4372
57. Active Learning for Human Pose Estimation. 4373-4382
58. Interleaved Group Convolutions. 4383-4392
59. Learning-Based Cloth Material Recovery from Video. 4393-4403
60. Unsupervised Video Understanding by Reconciliation of Posture Similarities. 4404-4414
61. Action Tubelet Detector for Spatio-Temporal Action Localization. 4415-4423
62. AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture. 4424-4433
63. Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings. 4434-4442
64. Neural Ctrl-F: Segmentation-Free Query-by-String Word Spotting in Handwritten Manuscript Collections. 4443-4452

Video Analysis Oral Session 6

1. Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions. 4453-4462
2. Semantic Video CNNs Through Representation Warping. 4463-4472
3. Video Frame Synthesis Using Deep Voxel Flow. 4473-4481
4. Detail-Revealing Deep Video Super-Resolution. 4482-4490
5. Learning Video Object Segmentation with Visual Memory. 4491-4500

Low-Level Vision Oral Session 7

1. EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis. 4501-4510
2. Makeup-Go: Blind Reversion of Portrait Edit. 4511-4519
3. Shadow Detection with Conditional Generative Adversarial Networks. 4520-4528
4. Learning High Dynamic Range from Outdoor Panoramas. 4529-4538
5. DCTM: Discrete-Continuous Transformation Matching for Semantic Flow. 4539-4548

Spotlight Session 6

1. MemNet: A Persistent Memory Network for Image Restoration. 4549-4557
2. Structure-Measure: A New Way to Evaluate Foreground Maps. 4558-4567
3. Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting. 4568-4577
4. Practical and Efficient Multi-view Matching. 4578-4586
5. Unrolled Memory Inner-Products: An Abstract GPU Operator for Efficient Vision-Related Computations. 4587-4595
6. Learning to Push the Limits of Efficient FFT-Based Image Deconvolution. 4596-4604
7. Learning Spread-Out Local Feature Descriptors. 4605-4613
8. Visual Odometry for Pixel Processor Arrays. 4614-4622

Poster Session 7

1. Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence. 4623-4631
2. 2D-Driven 3D Object Detection in RGB-D Images. 4632-4640
3. Ray Space Features for Plenoptic Structure-from-Motion. 4641-4649
4. Depth Estimation Using Structured Light Flow - Analysis of Projected Pattern Flow on an Object's Surface. 4650-4658
5. Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames. 4659-4667
6. Optimal Transformation Estimation with Semantic Cues. 4668-4677
7. Dynamics Enhanced Multi-camera Motion Segmentation from Unsynchronized Videos. 4678-4686
8. Taking the Scenic Route to 3D: Optimising Reconstruction from Moving Cameras. 4687-4695
9. FLaME: Fast Lightweight Mesh Estimation Using Variational Smoothing on Delaunay Graphs. 4696-4704
10. Efficient Algorithms for Moral Lineage Tracing. 4705-4714
11. From RGB to Spectrum for Natural Scenes via Manifold-Based Mapping. 4715-4723
12. DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs. 4724-4732
13. Learning Dense Facial Correspondences in Unconstrained Images. 4733-4742
14. Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification. 4743-4752
15. Automatic Content-Aware Projection for 360° Videos. 4753-4761
16. Blur-Invariant Deep Learning for Blind-Deblurring. 4762-4770
17. Non-linear Convolution Filters for CNN-Based Learning. 4771-4779
18. AOD-Net: All-in-One Dehazing Network. 4780-4788
19. Simultaneous Detection and Removal of High Altitude Clouds from an Image. 4789-4798
20. Understanding Low- and High-Level Contributions to Fixation Prediction. 4799-4808
21. Image Super-Resolution Using Dense Skip Connections. 4809-4817
22. Convergence Analysis of MAP Based Blur Kernel Estimation. 4818-4826
23. Blob Reconstruction Using Unilateral Second Order Gaussian Kernels with Application to High-ISO Long-Exposure Image Denoising. 4827-4835
24. Deep Generative Adversarial Compression Artifact Removal. 4836-4845
25. Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism. 4846-4855
26. Mutual Enhancement for Detection of Multiple Logos in Sports Videos. 4856-4865
27. Referring Expression Generation and Comprehension via Attributes. 4866-4874
28. RoomNet: End-to-End Room Layout Estimation. 4875-4884
29. SSH: Single Stage Headless Face Detector. 4885-4894
30. AnnArbor: Approximate Nearest Neighbors Using Arborescence Coding. 4895-4903
31. Boosting Image Captioning with Attributes. 4904-4912
32. Learning to Estimate 3D Hand Pose from Single RGB Images. 4913-4921
33. Locally-Transferred Fisher Vectors for Texture Classification. 4922-4930
34. Object-Level Proposals. 4931-4939
35. Extreme Clicking for Efficient Object Annotation. 4940-4949
36. WordSup: Exploiting Word Annotations for Character Based Text Detection. 4950-4959
37. Illuminating Pedestrians via Simultaneous Detection and Segmentation. 4960-4969
38. Generalized Orderless Pooling Performs Implicit Salient Matching. 4970-4979
39. Exploiting Spatial Structure for Localizing Manipulated Image Regions. 4980-4989
40. RDFNet: RGB-D Multi-level Residual Feature Fusion for Indoor Semantic Segmentation. 4990-4999
41. The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes. 5000-5009
42. Self-Organized Text Detection with Minimal Post-processing via Border Learning. 5010-5019
43. Sparse Exact PGA on Riemannian Manifolds. 5020-5028
44. Tensor RPCA by Bayesian CP Factorization with Complex Noise. 5029-5038
45. Multimodal Gaussian Process Latent Variable Models with Harmonization. 5039-5047
46. Segmentation-Aware Convolutional Networks Using Local Attention Masks. 5048-5057
47. Rotation Equivariant Vector Field Networks. 5058-5067
48. ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression. 5068-5076
49. AutoDIAL: Automatic Domain Alignment Layers. 5077-5085
50. Focusing Attention: Towards Accurate Text Recognition in Natural Images. 5086-5094
51. Unsupervised Object Segmentation in Video by Efficient Selection of Highly Probable Positive Features. 5095-5103
52. Nonparametric Variational Auto-Encoders for Hierarchical Representation Learning. 5104-5112
53. Dense and Low-Rank Gaussian CRFs Using Deep Embeddings. 5113-5122
54. A Multimodal Deep Regression Bayesian Network for Affective Video Content Analyses. 5123-5132
55. Moving Object Detection in Time-Lapse or Motion Trigger Image Sequences Using Low-Rank and Invariant Sparse Decomposition. 5133-5141
56. A Multilayer-Based Framework for Online Background Subtraction with Freely Moving Cameras. 5142-5151
57. Dynamic Label Graph Matching for Unsupervised Video Re-identification. 5152-5160
58. Spatiotemporal Modeling for Crowd Counting in Videos. 5161-5169
59. Personalized Cinemagraphs Using Semantic Understanding and Collaborative Learning. 5170-5179
60. What is Around the Camera? 5180-5188
61. Recognition 3 Oral Session 8
62. Weakly-Supervised Learning of Visual Relations. 5189-5198
63. BIER - Boosting Independent Embeddings Robustly. 5199-5208
64. 3D Graph Neural Networks for RGBD Semantic Segmentation. 5209-5218
65. Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition. 5219-5227
66. Learning 3D Object Categories by Looking Around Them. 5228-5237

Spotlight Session 7

1. Quantitative Evaluation of Confidence Measures in a Machine Learning World. 5238-5247
2. Towards End-to-End Text Spotting with Convolutional Recurrent Neural Networks. 5248-5256
3. DeepSetNet: Predicting Sets with Deep Neural Networks. 5257-5266
4. Learning from Video and Text via Large-Scale Discriminative Clustering. 5267-5276
5. TALL: Temporal Activity Localization via Language Query. 5277-5285
6. End-to-End Face Detection and Cast Grouping in Movies Using Erdös-Rényi Clustering. 5286-5295
7. Active Decision Boundary Annotation with Deep Generative Models. 5296-5305
8. Convolutional Dictionary Learning via Local Processing. 5306-5314

Poster Session 8

1. Editable Parametric Dense Foliage from 3D Capture. 5315-5324
2. Refractive Structure-from-Motion Through a Flat Refractive Interface. 5325-5333
3. Submodular Trajectory Optimization for Aerial 3D Scanning. 5334-5343
4. Camera Calibration by Global Constraints on the Motion of Silhouettes. 5344-5353
5. Deltille Grids for Geometric Camera Calibration. 5354-5362
6. A Lightweight Single-Camera Polarization Compass with Covariance Estimation. 5363-5371
7. Reflectance Capture Using Univariate Sampling of BRDFs. 5372-5380
8. Estimating Defocus Blur via Rank of Local Patches. 5381-5389
9. RGB-Infrared Cross-Modality Person Re-identification. 5390-5399
10. Intrinsic 3D Dynamic Surface Tracking based on Dynamic Ricci Flow and Teichmüller Map. 5400-5408
11. Multi-scale Deep Learning Architectures for Person Re-identification. 5409-5418
12. Range Loss for Deep Face Recognition with Long-Tailed Training Data. 5419-5428
13. Face Sketch Matching via Coupled Deep Transform Learning. 5429-5438
14. Realistic Dynamic Facial Textures from a Single Image Using GANs. 5439-5448
15. Pixel Recursive Super Resolution. 5449-5458
16. Recurrent Color Constancy. 5459-5467
17. Saliency Pattern Detection by Ranking Structured Trees. 5468-5477
18. Monocular Video-Based Trailer Coupler Detection Using Multiplexer Convolutional Neural Network. 5478-5486
19. Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking. 5487-5495
20. Non-rigid Object Tracking via Deformable Patches Using Shape-Preserved KCF and Level Sets. 5496-5504
21. A Discriminative View of MRF Pre-processing Algorithms. 5505-5514
22. Offline Handwritten Signature Modeling and Verification Based on Archetypal Analysis. 5515-5524
23. Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization. 5525-5533
24. Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks. 5534-5542
25. Deeper, Broader and Artier Domain Generalization. 5543-5551
26. Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval. 5552-5561
27. Soft-NMS - Improving Object Detection with One Line of Code. 5562-5570
28. Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images. 5571-5580
29. Video Scene Parsing with Predictive Feature Learning. 5581-5589
30. Understanding and Mapping Natural Beauty. 5590-5599
31. Human Pose Estimation Using Global and Local Normalization. 5600-5608
32. HashNet: Deep Learning to Hash by Continuation. 5609-5618
33. Scaling the Scattering Transform: Deep Hybrid Networks. 5619-5628
34. Flip-Invariant Motion Representation. 5629-5638
35. Scene Categorization with Spectral Features. 5639-5649
36. Image2song: Song Retrieval via Bridging Image Content and Lyric Words. 5650-5659
37. Deep Functional Maps: Structured Prediction for Dense Shape Correspondence. 5660-5668
38. Training Deep Networks to be Spatially Sensitive. 5669-5678
39. 3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds. 5679-5688
40. Semi Supervised Semantic Segmentation Using Generative Adversarial Network. 5689-5697
41. Efficient Low Rank Tensor Ring Completion. 5698-5706
42. Semantic Image Synthesis via Adversarial Learning. 5707-5715
43. Unified Deep Supervised Domain Adaptation and Generalization. 5716-5726
44. Temporal Context Network for Activity Localization in Videos. 5727-5736
45. Interpretable Transformations with Encoder-Decoder Networks. 5737-5746
46. Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization. 5747-5756
47. Deep Scene Image Classification with the MFAFVNet. 5757-5765
48. Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks. 5766-5774
49. Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics. 5775-5783
50. Joint Prediction of Activity Labels and Starting Times in Untrimmed Videos. 5784-5793
51. R-C3D: Region Convolutional 3D Network for Temporal Activity Detection. 5794-5803
52. Localizing Moments in Video with Natural Language. 5804-5813
53. TORNADO: A Spatio-Temporal Convolutional Regression Network for Video Action Proposal. 5814-5822
54. Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos. 5823-5832
55. Learning Action Recognition Model from Depth and Skeleton Videos. 5833-5842
56. The "Something Something" Video Database for Learning and Evaluating Visual Common Sense. 5843-5851
57. GPLAC: Generalizing Vision-Based Robotic Skills Using Weakly Labeled Images. 5852-5861
58. Semi-Global Weighted Least Squares in Image Filtering. 5862-5870
59. Scale Recovery for Monocular Visual Odometry Using Depth Estimated with Deep Convolutional Neural Fields. 5871-5879

Machine Learning Oral Session 9

1. Deep Adaptive Image Clustering. 5880-5888
2. One Network to Solve Them All - Solving Linear Inverse Problems Using Deep Projection Models. 5889-5898
3. Representation Learning by Learning to Count. 5899-5907
4. StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks. 5908-5916
5. Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos. 5917-5925

https://dblp.uni-trier.de/db/conf/iccv/iccv2017.html

这600多篇论文应该如何归类呢？其实看topic，或者看摘要就可以了。一般摘要即点明了主题，说明了一切。假设一篇摘要200字的话，那么600篇就是12万字。

从第一篇看起