Table of Contents

• Query-Focused Extractive Video SummarizationAidean Sharghi, Boqing Gong, Mubarak Shah. 3-19 [doi]
• Temporal Segment Networks: Towards Good Practices for Deep Action RecognitionLimin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao 0001, Dahua Lin, Xiaoou Tang, Luc Van Gool. 20-36 [doi]
• PlaNet - Photo Geolocation with Convolutional Neural NetworksTobias Weyand, Ilya Kostrikov, James Philbin. 37-55 [doi]
• Detecting Text in Natural Image with Connectionist Text Proposal NetworkZhi Tian, Weilin Huang, Tong He, Pan He, Yu Qiao 0001. 56-72 [doi]
• Face Recognition Using a Unified 3D Morphable ModelGuosheng Hu, Fei Yan, Chi-Ho Chan, Weihong Deng, William J. Christmas, Josef Kittler, Neil M. Robertson. 73-89 [doi]
• Augmented Feedback in Semantic Segmentation Under Image Level SupervisionXiaojuan Qi, Zhengzhe Liu, Jianping Shi, Hengshuang Zhao, Jiaya Jia. 90-105 [doi]
• Linear Depth Estimation from an Uncalibrated, Monocular Polarisation ImageWilliam A. P. Smith, Ravi Ramamoorthi, Silvia Tozza. 109-125 [doi]
• Online Variational Bayesian Motion AveragingGuillaume Bourmaud. 126-142 [doi]
• Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural FieldsSeungryong Kim, Kihong Park, Kwanghoon Sohn, Stephen Lin. 143-159 [doi]
• ObjectNet3D: A Large Scale Database for 3D Object RecognitionYu Xiang, Wonhui Kim, Wei Chen, Jingwei Ji, Christopher Bongsoo Choy, Hao Su, Roozbeh Mottaghi, Leonidas J. Guibas, Silvio Savarese. 160-176 [doi]
• Branching Gaussian Processes with Applications to Spatiotemporal Reconstruction of 3D TreesKyle Simek, Ravishankar Palanivelu, Kobus Barnard. 177-193 [doi]
• Tracking CompletionYao Sui, Guanghui Wang, Yafei Tang, Li Zhang. 194-209 [doi]
• Inter-battery Topic Representation LearningCheng Zhang, Hedvig Kjellström, Carl Henrik Ek. 210-226 [doi]
• Online Adaptation for Joint Scene and Object ClassificationJawadul H. Bappy, Sujoy Paul, Amit K. Roy Chowdhury. 227-243 [doi]
• Real-Time Facial Segmentation and Performance Capture from RGB InputShunsuke Saito, Tianye Li, Hao Li. 244-261 [doi]
• Learning Temporal Transformations from Time-Lapse VideosYipin Zhou, Tamara L. Berg. 262-277 [doi]
• Interactive Image Segmentation Using Constrained Dominant SetsEyasu Zemene, Marcello Pelillo. 278-294 [doi]
• Deep Markov Random Field for Image ModelingZhirong Wu, Dahua Lin, Xiaoou Tang. 295-312 [doi]
• A Symmetry Prior for Convex Variational 3D ReconstructionPablo Speciale, Martin R. Oswald, Andrea Cohen, Marc Pollefeys. 313-328 [doi]
• SPLeaP: Soft Pooling of Learned Parts for Image ClassificationPraveen Kulkarni, Frédéric Jurie, Joaquin Zepeda, Patrick Pérez, Louis Chevallier. 329-345 [doi]
• Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose EstimationQi Ye, Shanxin Yuan, Tae-Kyun Kim. 346-361 [doi]
• VolumeDeform: Real-Time Volumetric Non-rigid ReconstructionMatthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger. 362-379 [doi]
• \pi Match: Monocular vSLAM and Piecewise Planar Reconstruction Using Fast Plane CorrespondencesCarolina Raposo, João P. Barreto. 380-395 [doi]
• Peripheral Expansion of Depth Information via Layout Estimation with Fisheye CameraAlejandro Pérez-Yus, Gonzalo López-Nicolás, José Jesús Guerrero. 396-412 [doi]
• Built-in Foreground/Background Prior for Weakly-Supervised Semantic SegmentationFatemehsadat Saleh, Mohammad Sadegh Ali Akbarian, Mathieu Salzmann, Lars Petersson, Stephen Gould, Jose M. Alvarez. 413-432 [doi]
• It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera VideosPia Bideau, Erik G. Learned-Miller. 433-449 [doi]
• Kernelized Subspace Ranking for Saliency DetectionTiantian Wang, Lihe Zhang, Huchuan Lu, Chong Sun, Jinqing Qi. 450-466 [doi]
• Depth-Aware Motion MagnificationJulian F. P. Kooij, Jan C. van Gemert. 467-482 [doi]
• Stacked Hourglass Networks for Human Pose EstimationAlejandro Newell, Kaiyu Yang, Jia Deng. 483-499 [doi]
• Real-Time Large-Scale Dense 3D Reconstruction with Loop ClosureOlaf Kähler, Victor Adrian Prisacariu, David W. Murray. 500-516 [doi]
• Pixel-Level Domain TransferDonggeun Yoo, Namil Kim, Sunggyun Park, Anthony S. Paek, In-So Kweon. 517-532 [doi]
• Accelerating Convolutional Neural Networks with Dominant Convolutional Kernel and Knowledge Pre-regressionZhenyang Wang, Zhidong Deng, Shiyao Wang. 533-548 [doi]
• Learning Social Etiquette: Human Trajectory Understanding In Crowded ScenesAlexandre Robicquet, Amir Sadeghian, Alexandre Alahi, Silvio Savarese. 549-565 [doi]
• Bayesian Image Based 3D Pose EstimationMarta Sanzari, Valsamis Ntouskos, Fiora Pirri. 566-582 [doi]
• Efficient and Robust Semi-supervised Learning Over a Sparse-Regularized GraphHang Su, Jun Zhu, Zhaozheng Yin, Yinpeng Dong, Bo Zhang. 583-598 [doi]
• Novel Coplanar Line-Points Invariants for Robust Line Matching Across ViewsQi Jia, Xinkai Gao, Xin Fan, Zhongxuan Luo, Haojie Li, Ziyao Chen. 599-611 [doi]
• Sparse Representation Based Complete Kernel Marginal Fisher Analysis Framework for Computational Art Painting CategorizationAjit Puthenputhussery, Qingfeng Liu, Chengjun Liu. 612-627 [doi]
• 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object ReconstructionChristopher Bongsoo Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, Silvio Savarese. 628-644 [doi]
• Cascaded Continuous Regression for Real-Time Incremental Face TrackingEnrique Sánchez-Lozano, Brais Martínez, Georgios Tzimiropoulos, Michel F. Valstar. 645-661 [doi]
• Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter LearningYao Sui, Ziming Zhang, Guanghui Wang, Yafei Tang, Li Zhang. 662-678 [doi]
• Deep Self-correlation Descriptor for Dense Cross-Modal CorrespondenceSeungryong Kim, Dongbo Min, Stephen Lin, Kwanghoon Sohn. 679-695 [doi]
• Structured Matching for Phrase LocalizationMingzhe Wang, Mahmoud Azab, Noriyuki Kojima, Rada Mihalcea, Jia Deng. 696-711 [doi]
• Crossing-Line Crowd Counting with Two-Phase Deep Neural NetworksZhuoyi Zhao, Hongsheng Li, Rui Zhao, Xiaogang Wang. 712-726 [doi]
• Revisiting Visual Question Answering BaselinesAllan Jabri, Armand Joulin, Laurens van der Maaten. 727-739 [doi]
• Unsupervised CNN for Single View Depth Estimation: Geometry to the RescueRavi Garg, B. G. Vijay Kumar, Gustavo Carneiro, Ian D. Reid 0001. 740-756 [doi]
• A Continuous Optimization Approach for Efficient and Accurate Scene FlowZhaoyang Lv, Chris Beall, Pablo F. Alcantarilla, Fuxin Li, Zsolt Kira, Frank Dellaert. 757-773 [doi]
• Improving Multi-frame Data Association with Sparse Representations for Robust Near-online Multi-object TrackingLoïc Fagot-Bouquet, Romaric Audigier, Yoann Dhome, Frédéric Lerasle. 774-790 [doi]
• Gated Siamese Convolutional Neural Network Architecture for Human Re-identificationRahul Rama Varior, Mrinal Haloi, Gang Wang. 791-808 [doi]
• Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNsYoubao Tang, Xiangqian Wu. 809-825 [doi]