---
title: "IEEE Computer Society Conference on Computer Vision and"
description: "All 602 papers of IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2015 · page 1 of 7, the most cited first…"
canonical: "https://research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [IEEE Computer Society Conference on…](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/) / [2015](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/) / papers

# IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2015: all accepted papers

602 papers · page 1 of 7 · the most cited first · [← IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2015](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/)

**1** [2](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/papers/page/2/) … [7](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/papers/page/7/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/papers/page/2/)

1. **[Going deeper with convolutions ↗](https://doi.org/10.1109/cvpr.2015.7298594)**Christian Szegedy, Wei Liu, Yangqing Jia et al.*45,832 citations*
2. **[Fully convolutional networks for semantic segmentation ↗](https://doi.org/10.1109/cvpr.2015.7298965)**Jonathan Long, Evan Shelhamer, Trevor Jackson Darrell*36,250 citations*
3. **[FaceNet: A unified embedding for face recognition and clustering](https://md.research.elamur.ai/free/en/papers/schroff-2015-facenet-unified-embedding-face-recognition/)**Florian Schroff, Dmitry Kalenichenko, James Philbin*11,681 citations · our summary*
4. **[Show and tell: A neural image caption generator ↗](https://doi.org/10.1109/cvpr.2015.7298935)**Oriol Vinyals, Alexander Toshev, Samy Bengio et al.*6,124 citations*
5. **[Long-term recurrent convolutional networks for visual recognition and description ↗](https://doi.org/10.1109/cvpr.2015.7298878)**Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama et al.*5,009 citations*
6. **[Deep visual-semantic alignments for generating image descriptions ↗](https://doi.org/10.1109/cvpr.2015.7298932)**Andrej Karpathy, Li Fei-Fei*4,749 citations*
7. **[CIDEr: Consensus-based image description evaluation ↗](https://doi.org/10.1109/cvpr.2015.7299087)**Ramakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh*4,649 citations*
8. **[3D ShapeNets: A deep representation for volumetric shapes ↗](https://doi.org/10.1109/cvpr.2015.7298801)**Zhirong Wu, Shuran Song, Aditya Khosla et al.*4,550 citations*
9. **[Single image super-resolution from transformed self-exemplars ↗](https://doi.org/10.1109/cvpr.2015.7299156)**Jia‐Bin Huang, Abhishek Singh, Narendra Ahuja*3,472 citations*
10. **[Deep neural networks are easily fooled: High confidence predictions for unrecognizable images ↗](https://doi.org/10.1109/cvpr.2015.7298640)**Anh Nguyen, Jason Yosinski, Jeff Clune*3,187 citations*
11. **[ActivityNet: A large-scale video benchmark for human activity understanding ↗](https://doi.org/10.1109/cvpr.2015.7298698)**Fabian Caba Heilbron, Victor A Escorcia, Bernard Ghanem et al.*2,535 citations*
12. **[Object scene flow for autonomous vehicles ↗](https://doi.org/10.1109/cvpr.2015.7298925)**Moritz Menze, Andreas Geiger*2,183 citations*
13. **[Person re-identification by Local Maximal Occurrence representation and metric learning ↗](https://doi.org/10.1109/cvpr.2015.7298832)**Shengcai Liao, Yang Hu, Xiangyu Zhu et al.*2,091 citations*
14. **[Beyond short snippets: Deep networks for video classification ↗](https://doi.org/10.1109/cvpr.2015.7299101)**Joe Yue-Hei Ng, Matthew Hausknecht, Sudheendra Vijayanarasimhan et al.*2,062 citations*
15. **[Hierarchical recurrent neural network for skeleton based action recognition ↗](https://doi.org/10.1109/cvpr.2015.7298714)**Yong Du, Wei Wang, Liang Wang*1,895 citations*
16. **[SUN RGB-D: A RGB-D scene understanding benchmark suite ↗](https://doi.org/10.1109/cvpr.2015.7298655)**Shuran Song, Samuel P. Lichtenberg, Jianxiong Xiao*1,860 citations*
17. **[Understanding deep image representations by inverting them ↗](https://doi.org/10.1109/cvpr.2015.7299155)**Aravindh Mahendran, Andrea Vedaldi*1,771 citations*
18. **[Convolutional neural networks at constrained time cost ↗](https://doi.org/10.1109/cvpr.2015.7299173)**Kaiming He, Jian Sun*1,510 citations*
19. **[Hypercolumns for object segmentation and fine-grained localization ↗](https://doi.org/10.1109/cvpr.2015.7298642)**Bharath Hariharan, Pablo Arbeláez, Ross Girshick et al.*1,475 citations*
20. **[Learning to compare image patches via convolutional neural networks ↗](https://doi.org/10.1109/cvpr.2015.7299064)**Sergey Zagoruyko, Nikos Komodakis A*1,412 citations*
21. **[A convolutional neural network cascade for face detection ↗](https://doi.org/10.1109/cvpr.2015.7299170)**Haoxiang Li, Zhe Lin, Xiaohui Shen et al.*1,363 citations*
22. **[Efficient object localization using Convolutional Networks ↗](https://doi.org/10.1109/cvpr.2015.7298664)**Jonathan Tompson, Ross Goroshin, Arjun Jain et al.*1,309 citations*
23. **[From captions to visual concepts and back ↗](https://doi.org/10.1109/cvpr.2015.7298754)**Hao Fang, Saurabh Gupta, Forrest Iandola et al.*1,287 citations*
24. **[An improved deep learning architecture for person re-identification ↗](https://doi.org/10.1109/cvpr.2015.7299016)**Ejaz Ahmed, Michael Jones, Tim K. Marks*1,248 citations*
25. **[Supervised Discrete Hashing ↗](https://doi.org/10.1109/cvpr.2015.7298598)**Fumin Shen, Chunhua Shen, Wei Liu et al.*1,231 citations*
26. **[Multispectral pedestrian detection: Benchmark dataset and baseline ↗](https://doi.org/10.1109/cvpr.2015.7298706)**Soonmin Hwang, Jaesik Park, Nam Il Kim et al.*1,187 citations*
27. **[Action recognition with trajectory-pooled deep-convolutional descriptors ↗](https://doi.org/10.1109/cvpr.2015.7299059)**Limin Wang, Yu Qiao, Xiaoou Tang*1,176 citations*
28. **[Visual saliency based on multiscale deep features ↗](https://doi.org/10.1109/cvpr.2015.7299184)**Guanbin Li, Yizhou Yu*1,163 citations*
29. **[Cross-scene crowd counting via deep convolutional neural networks ↗](https://doi.org/10.1109/cvpr.2015.7298684)**Cong Zhang, Hongsheng Li, Xiaogang Wang et al.*1,121 citations*
30. **[Image retrieval using scene graphs ↗](https://doi.org/10.1109/cvpr.2015.7298990)**Justin M. Johnson, Ranjay Krishna, Michael M. Stark et al.*1,076 citations*
31. **[Saliency detection by multi-context deep learning ↗](https://doi.org/10.1109/cvpr.2015.7298731)**Rui Zhao, Wanli Ouyang, Hongsheng Li et al.*995 citations*
32. **[Recurrent convolutional neural network for object recognition ↗](https://doi.org/10.1109/cvpr.2015.7298958)**Ming Xuan Liang, Xiaolin Hu*976 citations*
33. **[Long-term correlation tracking ↗](https://doi.org/10.1109/cvpr.2015.7299177)**Chao Ma, Xiaokang Yang, Chongyang Zhang et al.*959 citations*
34. **[DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time ↗](https://doi.org/10.1109/cvpr.2015.7298631)**Richard A. Newcombe, Dieter Fox, Steven M. Seitz*940 citations*
35. **[Deeply learned face representations are sparse, selective, and robust ↗](https://doi.org/10.1109/cvpr.2015.7298907)**Yi Jie Sun, Xiaogang Wang, Xiaoou Tang*939 citations*
36. **[Learning from massive noisy labeled data for image classification ↗](https://doi.org/10.1109/cvpr.2015.7298885)**Tong Xiao, Tian Xia, Yi Yang et al.*907 citations*
37. **[Learning a convolutional neural network for non-uniform motion blur removal ↗](https://doi.org/10.1109/cvpr.2015.7298677)**Jian Zhong Sun, Wenfei Cao, Zongben Xu et al.*906 citations*
38. **[Deep convolutional neural fields for depth estimation from a single image ↗](https://doi.org/10.1109/cvpr.2015.7299152)**Fayao Liu, Chunhua Shen, Guosheng Lin*871 citations*
39. **[Simultaneous feature learning and hash coding with deep neural networks ↗](https://doi.org/10.1109/cvpr.2015.7298947)**Hanjiang Lai, Yan Pan, Ye Liu et al.*866 citations*
40. **[Is object localization for free? - Weakly-supervised learning with convolutional neural networks ↗](https://doi.org/10.1109/cvpr.2015.7298668)**Maxime Oquab, Léon Bottou, Ivan Laptev A et al.*865 citations*
41. **[A large-scale car dataset for fine-grained categorization and verification ↗](https://doi.org/10.1109/cvpr.2015.7299023)**Linjie Yang, Ping Luo, Chen Change Loy et al.*825 citations*
42. **[MatchNet: Unifying feature and metric learning for patch-based matching ↗](https://doi.org/10.1109/cvpr.2015.7298948)**Xufeng Han, Thomas Leung, Yangqing Jia et al.*825 citations*
43. **[Computing the stereo matching cost with a convolutional neural network ↗](https://doi.org/10.1109/cvpr.2015.7298767)**Jure Žbontar, Yann LeCun*796 citations*
44. **[The application of two-level attention models in deep convolutional neural network for fine-grained image classification ↗](https://doi.org/10.1109/cvpr.2015.7298685)**Tianjun Xiao, Yichong Xu, Kuiyuan Yang et al.*771 citations*
45. **[Diversity-induced Multi-view Subspace Clustering ↗](https://doi.org/10.1109/cvpr.2015.7298657)**Xiaochun Cao, Changqing Zhang, Huazhu Fu et al.*767 citations*
46. **[Appearance-based gaze estimation in the wild ↗](https://doi.org/10.1109/cvpr.2015.7299081)**Xucong Zhang, Yusuke Sugano, Mario Fritz et al.*763 citations*
47. **[Evaluation of output embeddings for fine-grained image classification ↗](https://doi.org/10.1109/cvpr.2015.7298911)**Zeynep Akata, Scott Reed, Daniel Walter et al.*752 citations*
48. **[SALICON: Saliency in Context ↗](https://doi.org/10.1109/cvpr.2015.7298710)**Ming Xin Jiang, Shengsheng Huang, Juanyong Duan et al.*702 citations*
49. **[Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A ↗](https://doi.org/10.1109/cvpr.2015.7298803)**Brendan F. Klare, Ben Klein, Emma Taborsky et al.*701 citations*
50. **[EpicFlow: Edge-preserving interpolation of correspondences for optical flow ↗](https://doi.org/10.1109/cvpr.2015.7298720)**Jérôme Revaud, Philippe Weinzaepfel, Zaïd Harchaoui et al.*697 citations*
51. **[Sparse Convolutional Neural Networks ↗](https://doi.org/10.1109/cvpr.2015.7298681)**Baoyuan Liu, Min Wang, Hassan Foroosh et al.*680 citations*
52. **[Deep networks for saliency detection via local estimation and global search ↗](https://doi.org/10.1109/cvpr.2015.7298938)**Lijun Wang, Huchuan Lu, Xiang Ruan et al.*676 citations*
53. **[From image-level to pixel-level labeling with Convolutional Networks ↗](https://doi.org/10.1109/cvpr.2015.7298780)**Pedro O. Pinheiro, Ronan Collobert*673 citations*
54. **[Deep filter banks for texture recognition and segmentation ↗](https://doi.org/10.1109/cvpr.2015.7299007)**Mircea Cimpoi, Subhransu Maji, Andrea Vedaldi*646 citations*
55. **[MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking ↗](https://doi.org/10.1109/cvpr.2015.7298675)**Zhibin Hong, Zhe Chen, Chaohui Wang et al.*644 citations*
56. **[Learning to generate chairs with convolutional neural networks ↗](https://doi.org/10.1109/cvpr.2015.7298761)**Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox*635 citations*
57. **[TVSum: Summarizing web videos using titles ↗](https://doi.org/10.1109/cvpr.2015.7299154)**Yale Song, Jordi Vallmitjana, Amanda J. Stent et al.*623 citations*
58. **[Fast and accurate image upscaling with super-resolution forests ↗](https://doi.org/10.1109/cvpr.2015.7299003)**Samuel Schulter, Christian Leistner, Horst Bischof*618 citations*
59. **[Effective face frontalization in unconstrained images ↗](https://doi.org/10.1109/cvpr.2015.7299058)**Tal Hassner, Shai Harel, Eran Paz et al.*600 citations*
60. **[Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection ↗](https://doi.org/10.1109/cvpr.2015.7298658)**Grant Van Horn, Steve Branson, Ryan J. Farrell et al.*592 citations*
61. **[Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs ↗](https://doi.org/10.1109/cvpr.2015.7298715)**Bo Li, Chunhua Shen, Yuchao Dai et al.*590 citations*
62. **[Modeling video evolution for action recognition ↗](https://doi.org/10.1109/cvpr.2015.7299176)**Basura Fernando, Efstratios Gavves, Jose Oramas M. et al.*569 citations*
63. **[Deep semantic ranking based hashing for multi-label image retrieval ↗](https://doi.org/10.1109/cvpr.2015.7298763)**Fang Ping Zhao, Yongzhen Huang, Liang Wang et al.*564 citations*
64. **[Robust reconstruction of indoor scenes ↗](https://doi.org/10.1109/cvpr.2015.7299195)**Sungjoon Choi, Qian-Yi Zhou, Vladlen Koltun*555 citations*
65. **[High-fidelity Pose and Expression Normalization for face recognition in the wild ↗](https://doi.org/10.1109/cvpr.2015.7298679)**Xiangyu Zhu, Zhen Lei, Junjie Yan et al.*550 citations*
66. **[Deep hashing for compact binary codes learning ↗](https://doi.org/10.1109/cvpr.2015.7298862)**Venice Erin Liong, Jiwen Lu, Gang Wang et al.*542 citations*
67. **[Semantics-preserving hashing for cross-view retrieval ↗](https://doi.org/10.1109/cvpr.2015.7299011)**Zijia Lin, Guiguang Ding, Mingqing Hu et al.*542 citations*
68. **[24/7 place recognition by view synthesis ↗](https://doi.org/10.1109/cvpr.2015.7298790)**Akihiko Torii, Relja Arandjelović, Josef Šivic et al.*536 citations*
69. **[Finding action tubes ↗](https://doi.org/10.1109/cvpr.2015.7298676)**Georgia Gkioxari, Jitendra Malik*528 citations*
70. **[DeepEdge: A multi-scale bifurcated deep network for top-down contour detection ↗](https://doi.org/10.1109/cvpr.2015.7299067)**Gedas Bertasius, Jianbo Shi, Lorenzo Torresani*525 citations*
71. **[Saliency-aware geodesic video object segmentation ↗](https://doi.org/10.1109/cvpr.2015.7298961)**Wenguan Wang, Jianbing Shen, Fatih Porikli*524 citations*
72. **[DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection ↗](https://doi.org/10.1109/cvpr.2015.7299024)**Wei Shen, Xinggang Wang, Yan Wang et al.*515 citations*
73. **[Material recognition in the wild with the Materials in Context Database ↗](https://doi.org/10.1109/cvpr.2015.7298970)**Sean Bell, Paul Upchurch, Noah Snavely et al.*501 citations*
74. **[Mind's eye: A recurrent visual representation for image caption generation ↗](https://doi.org/10.1109/cvpr.2015.7298856)**Xinlei Chen, C. Lawrence Zitnick*498 citations*
75. **[Superpixel segmentation using Linear Spectral Clustering ↗](https://doi.org/10.1109/cvpr.2015.7298741)**Zhengqin Li, Jiansheng Chen*479 citations*
76. **[Fine-grained recognition without part annotations ↗](https://doi.org/10.1109/cvpr.2015.7299194)**Jonathan Krause, Hailin Jin, Jianchao Yang et al.*466 citations*
77. **[Towards Open World Recognition ↗](https://doi.org/10.1109/cvpr.2015.7298799)**Abhijit Bendale, Terrance Boult*461 citations*
78. **[Saliency detection via Cellular Automata ↗](https://doi.org/10.1109/cvpr.2015.7298606)**Yao Qin, Huchuan Lu, Yiqun Xu et al.*460 citations*
79. **[Accurate depth map estimation from a lenslet light field camera ↗](https://doi.org/10.1109/cvpr.2015.7298762)**Hae‐Gon Jeon, Jaesik Park, Gyeongmin Choe et al.*453 citations*
80. **[Face alignment by coarse-to-fine shape searching ↗](https://doi.org/10.1109/cvpr.2015.7299134)**Shizhan Zhu, Cheng Li, Chen Change Loy et al.*450 citations*
81. **[Towards unified depth and semantic prediction from a single image ↗](https://doi.org/10.1109/cvpr.2015.7298897)**Peng Wang, Xiaohui Shen, Zhe Lin et al.*447 citations*
82. **[Feedforward semantic segmentation with zoom-out features ↗](https://doi.org/10.1109/cvpr.2015.7298959)**Mohammadreza Mostajabi, Payman Yadollahpour, Gregory Shakhnarovich*436 citations*
83. **[A dataset for Movie Description ↗](https://doi.org/10.1109/cvpr.2015.7298940)**Anna Rohrbach, Marcus Rohrbach, Niket Tandon et al.*435 citations*
84. **[A discriminative CNN video representation for event detection ↗](https://doi.org/10.1109/cvpr.2015.7298789)**Zhongwen Xu, Yi Ping Yang, Alexander G. Hauptmann*435 citations*
85. **[DeepID-Net: Deformable deep convolutional neural networks for object detection ↗](https://doi.org/10.1109/cvpr.2015.7298854)**Wanli Ouyang, Xiaogang Wang, Xingyu Zeng et al.*430 citations*
86. **[Convolutional feature masking for joint object and stuff segmentation ↗](https://doi.org/10.1109/cvpr.2015.7299025)**Jifeng Dai, Kaiming He, Jian Sun*422 citations*
87. **[Pose-conditioned joint angle limits for 3D human pose reconstruction ↗](https://doi.org/10.1109/cvpr.2015.7298751)**Ijaz Akhter, Michael J. Black*418 citations*
88. **[Cascaded hand pose regression ↗](https://doi.org/10.1109/cvpr.2015.7298683)**Xiao Na Sun, Yichen Wei, Shuang Liang et al.*414 citations*
89. **[Deformable part models are convolutional neural networks ↗](https://doi.org/10.1109/cvpr.2015.7298641)**Ross Girshick, Forrest Iandola, Trevor Jackson Darrell et al.*411 citations*
90. **[Pedestrian detection aided by deep learning semantic tasks ↗](https://doi.org/10.1109/cvpr.2015.7299143)**Yonglong Tian, Ping Luo, Xiaogang Wang et al.*407 citations*
91. **[Learning deep representations for ground-to-aerial geolocalization ↗](https://doi.org/10.1109/cvpr.2015.7299135)**Tsung-Yi Lin, Yin Cui, Serge Belongie et al.*401 citations*
92. **[Video summarization by learning submodular mixtures of objectives ↗](https://doi.org/10.1109/cvpr.2015.7298928)**Michael Gygli, Helmut Gräbner, Luc Van Gool*397 citations*
93. **[Deep correlation for matching images and text ↗](https://doi.org/10.1109/cvpr.2015.7298966)**Fei Yan, Krystian Mikolajczyk*395 citations*
94. **[Real-time part-based visual tracking via adaptive correlation filters ↗](https://doi.org/10.1109/cvpr.2015.7299124)**Ting Liu, Gang Wang, Qingxiong Yang*392 citations*
95. **[Filtered channel features for pedestrian detection ↗](https://doi.org/10.1109/cvpr.2015.7298784)**Shanshan Zhang, Rodrigo Benenson, Bernt Schiele*390 citations*
96. **[Deep multiple instance learning for image classification and auto-annotation ↗](https://doi.org/10.1109/cvpr.2015.7298968)**Jiajun Wu, Yinan Yu, Chang Huang et al.*386 citations*
97. **[Learning to rank in person re-identification with metric ensembles ↗](https://doi.org/10.1109/cvpr.2015.7298794)**Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Hengel*385 citations*
98. **[Scene labeling with LSTM recurrent neural networks ↗](https://doi.org/10.1109/cvpr.2015.7298977)**Wonmin Byeon, Thomas Michael Breuel, Federico Raue et al.*375 citations*
99. **[In defense of color-based model-free tracking ↗](https://doi.org/10.1109/cvpr.2015.7298823)**Horst Possegger, Thomas Mauthner, Horst Bischof*365 citations*
100. **[Jointly learning heterogeneous features for RGB-D activity recognition ↗](https://doi.org/10.1109/cvpr.2015.7299172)**Jian–Fang Hu, Wei‐Shi Zheng, Jianhuang Lai et al.*358 citations*

**1** [2](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/papers/page/2/) … [7](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/papers/page/7/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/papers/page/2/)

- [← back to](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2015/) — IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2015