Microsoft at CVPR 2020
Lieu: Virtual/Online
Tuesday, June 16
Oral 1.1A – 3D From a Single Image and Shape-From-X (1)
10:50 – 10:55 PDT
ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture (opens in new tab)
Sena Kiciroglu, Helge Rhodin, Sudipta Sinha (opens in new tab), Mathieu Salzmann, Pascal Fua
Video > (opens in new tab)
Oral 1.2A – 3D From Multiview and Sensors (1)
12:10 – 12:15 PDT
TextureFusion: High-Quality Texture Acquisition for Real-Time RGB-D Scanning (opens in new tab)
Joo Ho Lee, Hyunho Ha, Yue Dong (opens in new tab), Xin Tong, Min H. Kim
Video > (opens in new tab)
Oral 1.2C – Efficient Training and Inference
12:30 – 12:35 PDT
Towards Efficient Model Compression via Learned Global Ranking (opens in new tab)
Ting-Wu Chin, Ruizhou Ding, Cha Zhang (opens in new tab), Diana Marculescu
Video > (opens in new tab)
Oral 1.3A – 3D From a Single Image and Shape-From-X (2); 3D From Multiview and Sensors (2)
14:40 – 14:45 PDT
Why Having 10,000 Parameters in Your Camera Model Is Better Than Twelve (opens in new tab)
Thomas Schöps, Viktor Larsson, Marc Pollefeys (opens in new tab), Torsten Sattler
Video > (opens in new tab)
Oral 1.3C – Low-Level and Physics-Based Vision
14:25 – 14:30 PDT
Bringing Old Photos Back to Life (opens in new tab)
Ziyu Wan, Bo Zhang (opens in new tab), Dongdong Chen, Pan Zhang, Dong Chen (opens in new tab), Jing Liao, Fang Wen (opens in new tab)
Video > (opens in new tab)
14:30 – 14:35 PDT
A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising (opens in new tab)
Kaixuan Wei, Ying Fu, Jiaolong (opens in new tab) Yang, Hua Huang
Video > (opens in new tab)
Wednesday, June 17
Oral 2.1A – 3D From Multiview and Sensors (3)
10:15 – 10:20 PDT
RoutedFusion: Learning Real-Time Depth Map Fusion (opens in new tab)
Silvan Weder, Johannes Schönberger (opens in new tab), Marc Pollefeys (opens in new tab), Martin R. Oswald
Video > (opens in new tab)
Oral 2.1B – Face, Gesture, and Body Pose (1)
10:00 – 10:05 PDT
ReDA:Reinforced Differentiable Attribute for 3D Face Reconstruction (opens in new tab)
Wenbin Zhu, HsiangTao Wu, Zeyu Chen, Noranart Vesdapunt, Baoyuan Wang (opens in new tab)
Video > (opens in new tab)
10:20 – 10:25 PDT
Face X-ray for More General Face Forgery Detection (opens in new tab)
Lingzhi Li, Jianmin Bao (opens in new tab), Ting Zhang (opens in new tab), Hao Yang (opens in new tab), Dong Chen (opens in new tab), Fang Wen (opens in new tab), Baining Guo (opens in new tab)
Video > (opens in new tab)
10:55 – 11:00 PDT
Advancing High Fidelity Identity Swapping for Forgery Detection (opens in new tab)
Lingzhi Li, Jianmin Bao (opens in new tab), Hao Yang (opens in new tab), Dong Chen (opens in new tab), Fang Wen (opens in new tab)
Video > (opens in new tab)
Oral 2.2B – Motion and Tracking (1)
12:00 – 12:05 PDT
LSM: Learning Subspace Minimization for Low-level Vision (opens in new tab)
Chengzhou Tang, Lu Yuan (opens in new tab), Ping Tan
Video > (opens in new tab)
12:20 – 12:25 PDT
MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask (opens in new tab)
Shengyu Zhao, Yilun Sheng, Yue Dong, Eric Chang (opens in new tab), Yan Xu
Video > (opens in new tab)
12:25 – 12:30 PDT
Tracking by Instance Detection: A Meta-Learning Approach (opens in new tab)
Guangting Wang, Chong Luo (opens in new tab), Xiaoyan Sun, Zhiwei Xiong, Wenjun Zeng (opens in new tab)
Video > (opens in new tab)
Oral 2.1C – Image and Video Synthesis (1)
10:30 – 10:35 PDT
Cross-domain Correspondence Learning for Exemplar-based Image Translation (opens in new tab)
Pan Zhang, Bo Zhang (opens in new tab), Dong Chen (opens in new tab), Lu Yuan (opens in new tab), Fang Wen (opens in new tab)
Video > (opens in new tab)
10:35 – 10:40 PDT
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning (opens in new tab)
Yu Deng, Jiaolong Yang (opens in new tab), Dong Chen (opens in new tab), Fang Wen (opens in new tab), Xin Tong (opens in new tab)
Video > (opens in new tab)
Oral 2.3A – Face, Gesture, and Body Pose (3); Motion and Tracking (2)
14:15 – 14:20 PDT
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking (opens in new tab)
Jin Gao, Weiming Hu, Yan Lu (opens in new tab)
Video > (opens in new tab)
Oral 2.4C – Transfer/Low-Shot/Semi/Unsupervised Learning (2)
16:10 – 16:15 PDT
HyperSTAR: Task-Aware Hyperparameters for Deep Networks (opens in new tab)
Gaurav Mittal, Chang Liu, Nikolaos Karianakis, Victor Fragoso (opens in new tab), Mei Chen (opens in new tab), Yun Fu
Video > (opens in new tab)
Thursday, June 18
Oral 3.1B – Video Analysis and Understanding
9:05 – 9:10 PDT
Spatiotemporal Fusion in 3D CNNs: A Probabilistic View (opens in new tab)
Yizhou Zhou, Xiaoyan Sun, Chong Luo (opens in new tab), Zheng-Jun Zha, Wenjun Zeng (opens in new tab)
Video > (opens in new tab)
Oral 3.1C – Vision & Language
9:30 – 9:35 PDT
SQuINTing at VQA Models: Introspecting VQA Models with Sub-Questions (opens in new tab)
Ramprasaath Ramasamy Selvaraju, Purva Tendulkar, Devi Parikh, Eric Horvitz (opens in new tab), Marco Ribeiro (opens in new tab), Besmira Nushi (opens in new tab), Ece Kamar (opens in new tab)
Video > (opens in new tab)
9:40 – 9:45 PDT
Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation (opens in new tab)
Necati Cihan Camgoz, Simon Hadfield, Oscar Koller (opens in new tab), Richard Bowden
Video > (opens in new tab)
Oral 3.2A – Recognition (Detection, Categorization) (2)
11:25 – 11:30 PDT
Dynamic Convolution: Attention over Convolution Kernels (opens in new tab)
Yinpeng Chen (opens in new tab), Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan (opens in new tab), Zicheng Liu (opens in new tab)
Video > (opens in new tab)
Oral 3.2C – Machine Learning Architectures and Formulations
11:40 – 11:45 PDT
Local Context Normalization: Revisiting Local Normalization (opens in new tab)
Anthony Ortiz, Caleb Robinson, Md Mahmudulla Hassan, Dan Morris (opens in new tab), Olac Fuentes, Christopher Kiekintveld, Nebojsa Jojic (opens in new tab)
Video > (opens in new tab)