Table of Contents

• Group NormalizationYuxin Wu, Kaiming He. 3-19 [doi]
• Deep Expander Networks: Efficient Deep Networks from Graph TheoryAmeya Prabhu, Girish Varma, Anoop M. Namboodiri. 20-36 [doi]
• Towards Realistic PredictorsPei Wang, Nuno Vasconcelos. 37-53 [doi]
• Learning SO(3) Equivariant Representations with Spherical CNNsCarlos Esteves, Christine Allen-Blanchette, Ameesh Makadia, Kostas Daniilidis. 54-70 [doi]
• Learnable PINs: Cross-modal Embeddings for Person IdentityArsha Nagrani, Samuel Albanie, Andrew Zisserman. 73-89 [doi]
• Separating Reflection and Transmission Images in the WildPatrick Wieschollek, Orazio Gallo, Jinwei Gu, Jan Kautz. 90-105 [doi]
• Object Level Visual Reasoning in VideosFabien Baradel, Natalia Neverova, Christian Wolf 0001, Julien Mille, Greg Mori. 106-122 [doi]
• Maximum Margin Metric Learning over Discriminative Nullspace for Person Re-identificationT. M. Feroz Ali, Subhasis Chaudhuri. 123-141 [doi]
• Incremental Multi-graph Matching via Diversity and Randomness Based Graph ClusteringTianshu Yu, Junchi Yan, Wei Liu, Baoxin Li. 142-158 [doi]
• Visual Text CorrectionAmir Mazaheri, Mubarak Shah. 159-175 [doi]
• Generalizing a Person Retrieval Model Hetero- and HomogeneouslyZhun Zhong, Liang Zheng 0001, Shaozi Li, Yi Yang 0001. 176-192 [doi]
• Domain Adaptation Through Synthesis for Unsupervised Person Re-identificationSlawomir Bak, Peter Carr 0001, Jean-François Lalonde. 193-209 [doi]
• SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial NetworkYancheng Bai, Yongqiang Zhang, Mingli Ding, Bernard Ghanem. 210-226 [doi]
• Facial Expression Recognition with Inconsistently Annotated DatasetsJiabei Zeng, Shiguang Shan, Xilin Chen. 227-243 [doi]
• Stroke Controllable Fast Style Transfer with Adaptive Receptive FieldsYongcheng Jing, Yang Liu, Yezhou Yang, Zunlei Feng, Yizhou Yu, Dacheng Tao, Mingli Song. 244-260 [doi]
• Towards End-to-End License Plate Detection and Recognition: A Large Dataset and BaselineZhenbo Xu, Wei Yang, Ajin Meng, Nanxue Lu, Huan Huang, Changchun Ying, Liusheng Huang. 261-277 [doi]
• Learning Warped Guidance for Blind Face RestorationXiaoming Li, Ming Liu 0018, Yuting Ye, Wangmeng Zuo, Liang Lin, Ruigang Yang. 278-296 [doi]
• Face De-spoofing: Anti-spoofing via Noise ModelingAmin Jourabloo, Yaojie Liu, Xiaoming Liu. 297-315 [doi]
• Unsupervised Hard Example Mining from Videos for Improved Object DetectionSouYoung Jin, Aruni RoyChowdhury, Huaizu Jiang, Ashish Singh, Aditya Prasad, Deep Chakraborty, Erik G. Learned-Miller. 316-333 [doi]
• BiSeNet: Bilateral Segmentation Network for Real-Time Semantic SegmentationChangqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang. 334-349 [doi]
• Pose Proposal NetworksTaiki Sekii. 350-366 [doi]
• Less Is More: Picking Informative Frames for Video CaptioningYangyu Chen, Shuhui Wang, Weigang Zhang, Qingming Huang. 367-384 [doi]
• Cross-Modal and Hierarchical Modeling of Video and TextBowen Zhang, Hexiang Hu, Fei Sha. 385-401 [doi]
• Tracking Emerges by Colorizing VideosCarl Vondrick, Abhinav Shrivastava, Alireza Fathi, Sergio Guadarrama, Kevin Murphy 0002. 402-419 [doi]
• SkipNet: Learning Dynamic Routing in Convolutional NetworksXin Wang, Fisher Yu, Zi-Yi Dou, Trevor Darrell, Joseph E. Gonzalez. 420-436 [doi]
• Person Search in Videos with One Portrait Through Visual and Temporal LinksQingqiu Huang, WenTao Liu, Dahua Lin. 437-454 [doi]
• Decouple Learning for Parameterized Image OperatorsQingnan Fan, Dongdong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen. 455-471 [doi]
• Triplet Loss in Siamese Network for Object TrackingXingping Dong, Jianbing Shen. 472-488 [doi]
• Point-to-Point Regression PointNet for 3D Hand Pose EstimationLiuhao Ge, Zhou Ren, Junsong Yuan. 489-505 [doi]
• DOCK: Detecting Objects by Transferring Common-Sense KnowledgeKrishna Kumar Singh, Santosh Kumar Divvala, Ali Farhadi, Yong Jae Lee. 506-522 [doi]
• Multi-scale Spatially-Asymmetric Recalibration for Image ClassificationYan Wang, Lingxi Xie, Siyuan Qiao, Ya Zhang, Wenjun Zhang, Alan L. Yuille. 523-539 [doi]
• Choose Your Neuron: Incorporating Domain Knowledge Through Neuron-ImportanceRamprasaath R. Selvaraju, Prithvijit Chattopadhyay, Mohamed Elhoseiny, Tilak Sharma, Dhruv Batra, Devi Parikh, Stefan Lee. 540-556 [doi]
• Fully Motion-Aware Network for Video Object DetectionShiyao Wang, Yucong Zhou, Junjie Yan, Zhidong Deng. 557-573 [doi]
• Generative Semantic Manipulation with Mask-Contrasting GANXiaodan Liang, Hao Zhang, Liang Lin, Eric Xing. 574-590 [doi]
• Interpolating Convolutional Neural Networks Using Batch NormalizationGratianus Wesley Putra Data, Kirjon Ngu, David William Murray, Victor Adrian Prisacariu. 591-606 [doi]
• Toward Characteristic-Preserving Image-Based Virtual Try-On NetworkBochao Wang, Huabin Zheng, Xiaodan Liang, Yimin Chen, Liang Lin, Meng Yang. 607-623 [doi]
• Deep Cross-Modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-Based 3D Shape RetrievalJiaxin Chen, Yi Fang. 624-640 [doi]
• RIDI: Robust IMU Double IntegrationHang Yan, Qi Shan, Yasutaka Furukawa. 641-656 [doi]
• Training Binary Weight Networks via Semi-Binary DecompositionQinghao Hu, Gang Li 0015, Peisong Wang, Yifan Zhang 0001, Jian Cheng 0001. 657-673 [doi]
• Focus, Segment and Erase: An Efficient Network for Multi-label Brain Tumor SegmentationXuan Chen, JunHao Liew, Wei Xiong 0001, Chee-Kong Chui, Sim Heng Ong. 674-689 [doi]
• X2Face: A Network for Controlling Face Generation Using Images, Audio, and Pose CodesOlivia Wiles, A. Sophia Koepke, Andrew Zisserman. 690-706 [doi]
• Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene UnderstandingChristos Sakaridis, Dengxin Dai, Simon Hecker, Luc Van Gool. 707-724 [doi]
• Deep Adaptive Attention for Joint Facial Action Unit Detection and Face AlignmentZhiwen Shao, Zhilei Liu, Jianfei Cai, Lizhuang Ma. 725-740 [doi]
• Deep Pictorial Gaze EstimationSeonwook Park, Adrian Spurr, Otmar Hilliges. 741-757 [doi]
• Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global MatchingJohannes L. Schönberger, Sudipta N. Sinha, Marc Pollefeys. 758-775 [doi]
• Incremental Non-Rigid Structure-from-Motion with Unknown Focal LengthThomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool. 776-793 [doi]
• r2p2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path ForecastingNicholas Rhinehart, Kris M. Kitani, Paul Vernaza. 794-811 [doi]
• Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360 ^\circ ∘ Panoramic ImageryGrégoire Payen de La Garanderie, Amir Atapour Abarghouei, Toby P. Breckon. 812-830 [doi]
• Cross-Modal Ranking with Soft Consistency and Noisy Labels for Robust RGB-T TrackingChenglong Li 0002, Chengli Zhu, Yan Huang 0008, Jin Tang, Liang Wang. 831-847 [doi]