CVPR 2019 Oral Session 1-2C: Scenes & Representation

0:43 d-SNE: Domain Adaptation using Stochastic Neighborhood Embedding Xiang Xu (University of Houston); Xiong Zhou (amazon); Ragav Venkatesan (Amazon)*; Orchid Majumder (Amazon); Guru Swaminathan (Amazon)

6:01 Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation Yawei Luo (University of Technology Sydney)*; Liang Zheng (Australian National University); Tao Guan (Huazhong University of Science and Technology); Junqing Yu (Huazhong University of Science & Technology); Yi Yang (University of Technology, Sydney)

17:40 Local Feature Augmentation with Cross-Modality Context Zixin Luo (HKUST)*; Tianwei Shen (HKUST); Lei Zhou (HKUST); Jiahui Zhang (Tsinghua University); Yao Yao (The Hong Kong University of Science and Technology); Shiwei Li (HKUST); Tian Fang (HKUST); Long Quan (Hong Kong University of Science and Technology)

22:45 Large-scale Long-Tailed Recognition in an Open World Ziwei Liu (The Chinese University of Hong Kong)*; Zhongqi Miao (UC Berkeley); Xiaohang Zhan (The Chinese University of Hong Kong); Jiayun Wang (UC Berkeley / ICSI); Boqing Gong (Tencent AI Lab); Stella X Yu (UC Berkeley / ICSI)

27:50 AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data Liheng Zhang (University of Central Florida); Guo-Jun Qi (Huawei Cloud)*; Liqiang Wang (University of Central Florida); Jiebo Luo (University of Rochester)

35:35 SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks René Schuster (DFKI)*; Oliver Wasenmüller (DFKI); Christian Unger (BMW); Didier Stricker (DFKI)

40:30 Learning Correspondence from the Cycle-consistency of Time Xiaolong Wang (CMU)*; Allan Jabri (UC Berkeley); Alexei A Efros (UC Berkeley)

45:45 AE^2-Nets: Autoencoder in Autoencoder Networks Changqing Zhang (Tianjin university)*; liu yeqing (Tianjin University ); Huazhu Fu (Inception Institute of Artificial Intelligence)

55:10 Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach Proteek Roy (Michigan State University); Vishnu Boddeti (Michigan State University)*

1:00:10 Learning Spatial Common Sense with Geometry-Aware Recurrent Networks Hsiao-Yu Tung (Carnegie Mellon University)*; Ricson Cheng (Carnegie Mellon University); Katerina Fragkiadaki (Carnegie Mellon University)

1:05:13 Structured Knowledge Distillation for Semantic Segmentation Yifan Liu (University of Adelaide); Ke Chen (Microsoft); Chris Liu (Microsoft); Zengchang Qin (Intelligent Computing & Machine Learning Lab, School of ASEE, Beihang University); Zhenbo Luo ( Samsung Research Institute China-Beijing); Jingdong Wang (Microsoft Research)*

1:13:33 Scan2CAD: Learning CAD Model Alignment in RGB-D Scans Armen Avetisyan (Technical University of Munich)*; Manuel Dahnert (Technical University of Munich); Angela Dai (Technical University of Munich); Manolis Savva (Simon Fraser University); Angel X Chang (Eloquent Labs); Matthias Niessner (Technical University of Munich)

1:18:37 Towards Scene Understanding: Unsupervised Monocular Depth Estimation with Semantic-aware Representation Po-Yi Chen (National Taiwan University); Alexander H. Liu (National Taiwan University); Yen-Cheng Liu (Georgia Institute of Technology); Yu-Chiang Frank Wang (National Taiwan University)*

1:23:35 Tell Me Where I Am: Object-level Scene Context Prediction Xiaotian Qiao (City University of Hong Kong); Quanlong Zheng (City University of HongKong); Ying Cao (City University of Hong Kong)*; Rynson W.H. Lau (City University of Hong Kong)

1:31:52 Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation He Wang (Stanford University); Srinath Sridhar (Stanford University)*; Jingwei Huang (Stanford University); Julien Valentin (Google); Shuran Song (Princeton); Leonidas Guibas (Stanford University)

1:36:55 Supervised Fitting of Geometric Primitives to 3D Point Clouds Lingxiao Li (Stanford University)*; Minhyuk Sung (Stanford University); Anastasia Dubrovina (Stanford); Li Yi (Stanford); Leonidas Guibas (Stanford University)

1:42:00 Do Better ImageNet Models Transfer Better? Simon Kornblith (Google)*; Jon Shlens (Google); Quoc Le (Google Brain)