Microsoft at ECCV 2020
Location: Virtual/Online
Monday, August 24
06:00 – 08:00 | Poster Session 1
Convolutional Occupancy Networks – #1016
Songyou Peng, Michael Niemeyer, Lars Morten Mescheder, Marc Pollefeys, Andreas Geiger
Privacy Preserving Structure-from-Motion – #1031
Marcel Geppert, Viktor Larsson, Pablo Speciale, Johannes L. Schönberger, Marc Pollefeys
Multi-View Optimization of Local Feature Geometry – #1050
Mihai Dusmanu, Johannes L. Schönberger, Marc Pollefeys
Handcrafted Outlier Detection Revisited – #1077
Luca Cavalli, Viktor Larsson, Martin R. Oswald, Torsten Sattler, Marc Pollefeys
Calibration-free Structure-from-Motion with Calibrated Radial Trifocal Tensors – #1088
Viktor Larsson, Nicolas Zobernig, Kasim Taskin, Marc Pollefeys
Online Invariance Selection for Local Feature Descriptors – #1109
Rémi Pautrat, Viktor Larsson, Martin R. Oswald, Marc Pollefeys
13:20 – 14:20 | Spotlight Session – 3D geometry & reconstruction
Calibration-free Structure-from-Motion with Calibrated Radial Trifocal Tensors – #1088
Viktor Larsson, Nicolas Zobernig, Kasim Taskin, Marc Pollefeys
Convolutional Occupancy Networks – #1016
Songyou Peng, Michael Niemeyer, Lars Morten Mescheder, Marc Pollefeys, Andreas Geiger
14:00 – 16:00 | Poster Session 2
Convolutional Occupancy Networks – #1016
Songyou Peng, Michael Niemeyer, Lars Morten Mescheder, Marc Pollefeys, Andreas Geiger
Privacy Preserving Structure-from-Motion – #1031
Marcel Geppert, Viktor Larsson, Pablo Speciale, Johannes L. Schönberger, Marc Pollefeys
Multi-View Optimization of Local Feature Geometry – #1050
Mihai Dusmanu, Johannes L. Schönberger, Marc Pollefeys
Handcrafted Outlier Detection Revisited – #1077
Luca Cavalli, Viktor Larsson, Martin R. Oswald, Torsten Sattler, Marc Pollefeys
Calibration-free Structure-from-Motion with Calibrated Radial Trifocal Tensors – #1088
Viktor Larsson, Nicolas Zobernig, Kasim Taskin, Marc Pollefeys
Online Invariance Selection for Local Feature Descriptors – #1109
Rémi Pautrat, Viktor Larsson, Martin R. Oswald, Marc Pollefeys
16:50 – 17:50 | Oral Session – 3D geometry & reconstruction
The Phong Surface: Efficient 3D Model Fitting using Lifted Optimization – #4316
Jingjing Shen, Thomas J. Cashman, Qi Ye, Tim Hutton, Toby Sharp, Federica Bogo, Andrew William Fitzgibbon, Jamie Shotton
Tuesday, August 25
00:00 – 02:00 | Poster Session 3
Invertible Image Rescaling – #2015
Mingqing Xiao, Shuxin Zheng, Chang Liu, Yaolong Wang, Di He, Guolin Ke, Jiang Bian, Zhouchen Lin, Tie-Yan Liu
Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation – #2037
Fangyun Wei, Xiao Sun, Hongyang Li, Jingdong Wang, Stephen Lin
SegFix: Model-Agnostic Boundary Refinement for Segmentation – #2057
Yuhui Yuan, Jingyi Xie, Xilin Chen, Jingdong Wang
SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach – #2079
Ailing Zeng, Xiao Sun, Fuyang Huang, Minhao Liu, Qiang Xu, Stephen Lin
Disentangled Non-local Neural Networks – #2088
Minghao Yin, Zhuliang Yao, Yue Cao, Xiu Li, Zheng Zhang, Stephen Lin, Han Hu
Object-based Illumination Estimation with Rendering-aware Neural Networks – #2092
Guojun Chen, Stephen Lin, Xin Tong, Xin Wei, Yue Dong
Infrastructure-based Multi-Camera Calibration using Radial Projections – #2108
Yukai Lin, Viktor Larsson, Marcel Geppert, Zuzana Kukelova, Marc Pollefeys, Torsten Sattler
Detecting Human-Object Interactions with Action Co-occurrence Priors – #2165
Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, In So Kweon
A Closer Look at Local Aggregation Operators in Point Cloud Analysis – #2184
Ze Liu, Han Hu, Yue Cao, Zheng Zhang, Xin Tong
Mind the Discriminability: Asymmetric Adversarial Domain Adaptation – #2198
Han Zou, Lihua Xie, Yuxun Zhou, Zhaoyang Zeng, Jianfei Yang
UNITER: UNiversal Image-TExt Representation Learning – #2242
Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, Jingjing Liu
06:00 – 08:00 | Poster Session 4
Invertible Image Rescaling – #2015
Mingqing Xiao, Shuxin Zheng, Chang Liu, Yaolong Wang, Di He, Guolin Ke, Jiang Bian, Zhouchen Lin, Tie-Yan Liu
Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation – #2037
Fangyun Wei, Xiao Sun, Hongyang Li, Jingdong Wang, Stephen Lin
SegFix: Model-Agnostic Boundary Refinement for Segmentation – #2057
Yuhui Yuan, Jingyi Xie, Xilin Chen, Jingdong Wang
SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach – #2079
Ailing Zeng, Xiao Sun, Fuyang Huang, Minhao Liu, Qiang Xu, Stephen Lin
Disentangled Non-local Neural Networks – #2088
Minghao Yin, Zhuliang Yao, Yue Cao, Xiu Li, Zheng Zhang, Stephen Lin, Han Hu
Object-based Illumination Estimation with Rendering-aware Neural Networks – #2092
Guojun Chen, Stephen Lin, Xin Tong, Xin Wei, Yue Dong
Infrastructure-based Multi-Camera Calibration using Radial Projections – #2108
Yukai Lin, Viktor Larsson, Marcel Geppert, Zuzana Kukelova, Marc Pollefeys, Torsten Sattler
Detecting Human-Object Interactions with Action Co-occurrence Priors – #2165
Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, In So Kweon
A Closer Look at Local Aggregation Operators in Point Cloud Analysis – #2184
Ze Liu, Han Hu, Yue Cao, Zheng Zhang, Xin Tong
Mind the Discriminability: Asymmetric Adversarial Domain Adaptation – #2198
Han Zou, Lihua Xie, Yuxun Zhou, Zhaoyang Zeng, Jianfei Yang
UNITER: UNiversal Image-TExt Representation Learning – #2242
Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, Jingjing Liu
08:00 – 09:00 | Oral Session – Looking at humans
VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment – #3016
Hanyue Tu, Chunyu Wang, Wenjun Zeng
08:50 – 09:50 | Spotlight Session – Segmentation & scene interpretation and description, language
Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models – #4439
Jize Cao, Zhe Gan, Yu Cheng, Licheng Yu, Yen-Chun Chen, Jingjing Liu
Object-Contextual Representations for Semantic Segmentation – #3147
Yuhui Yuan, Xilin Chen, Jingdong Wang
14:00 – 16:00 | Poster Session 5
Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting – #2334
Bindita Chaudhuri, Noranart Vesdapunt, Linda Shapiro, Baoyuan Wang
High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images – #2387
Stephan J. Garbin, Marek Kowalski, Matthew Johnson,Jamie Shotton
14:15 – 15:00 | Industry Session
Research at Microsoft’s Mixed Reality & AI Labs in Europe
Federica Bogo, Jamie Shotton, Matthew Johnson
16:00 – 17:00 | Spotlight Session – Learning Methods
Negative Margin Matters: Understanding Margin in Few-shot Classification – #4078
Bin Liu, Yue Cao, Yutong Lin, Qi Li, Zheng Zhang, Mingsheng Long, Han Hu
Wednesday, August 26
00:00 – 02:00 | Poster Session 6
Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting – #2334
Bindita Chaudhuri, Noranart Vesdapunt, Linda Shapiro, Baoyuan Wang
High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images – #2387
Stephan J. Garbin, Marek Kowalski, Matthew Johnson,Jamie Shotton
GIQA: Generated Image Quality Assessment – #3037
Shuyang Gu, Jianmin Bao, Dong Chen, Fang Wen
Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation – #3068
Zhenda Xie, Zheng Zhang, Xizhou Zhu, Gao Huang, Stephen Lin
Learning Joint Spatial-Temporal Transformations for Video Inpainting – #3079
Yanhong Zeng, Jianlong Fu, Hongyang Chao
Design and Interpretation of Universal Adversarial Patches in Face Detection – #3081
Xiao Yang, Fangyun Wei, Hongyang Zhang, Jun Zhu
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning – #3161
Xinwei Sun, Yilun Xu, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang
02:50 – 03:50 | Spotlight Session – Looking at humans
Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting – #2334
Bindita Chaudhuri, Noranart Vesdapunt, Linda Shapiro, Baoyuan Wang
06:00 – 08:00 | Poster Session 7
GIQA: Generated Image Quality Assessment – #3037
Shuyang Gu, Jianmin Bao, Dong Chen, Fang Wen
Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation – #3068
Zhenda Xie, Zheng Zhang, Xizhou Zhu, Gao Huang, Stephen Lin
Learning Joint Spatial-Temporal Transformations for Video Inpainting – #3079
Yanhong Zeng, Jianlong Fu, Hongyang Chao
Design and Interpretation of Universal Adversarial Patches in Face Detection – #3081
Xiao Yang, Fangyun Wei, Hongyang Zhang, Jun Zhu
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning – #3161
Xinwei Sun, Yilun Xu, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang
CONFIG: Controllable Neural Face Image Generation – #3172
Marek Kowalski, Stephan J. Garbin, Virginia Estellers, Tadas Baltrušaitis, Matthew Johnson, Jamie Shotton
13:20 – 14:20 | Oral Session – Video & action understanding
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning – #3161
Xinwei Sun, Yilun Xu, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang
14:00 – 16:00 | Poster Session 8
CONFIG: Controllable Neural Face Image Generation – #3172
Marek Kowalski, Stephan J. Garbin, Virginia Estellers, Tadas Baltrušaitis, Matthew Johnson, Jamie Shotton
Who left the dogs out? 3D Animal Reconstruction with Expectation Maximization in the Loop – #3242
Benjamin Biggs, Oliver Boyne, James Charles, Andrew Fitzgibbon, Roberto Cipolla
Label-similarity Curriculum Learning – #3310
Urun Dogan, Aniket Anand Deshmukh, Marcin Machura, Christian Igel
16:00 – 17:00 | Oral Session – Low level vision
Online Invariance Selection for Local Feature Descriptors – #1109
Rémi Pautrat, Viktor Larsson, Martin R. Oswald, Marc Pollefeys
16:50 – 17:50 | Oral Session – Low level vision
Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation – #3068
Zhenda Xie, Zheng Zhang, Xizhou Zhu, Gao Huang, Stephen Lin
Thursday, August 27
00:00 – 02:00 | Poster Session 9
Who left the dogs out? 3D Animal Reconstruction with Expectation Maximization in the Loop – #3242
Benjamin Biggs, Oliver Boyne, James Charles, Andrew Fitzgibbon, Roberto Cipolla
Label-similarity Curriculum Learning – #3310
Urun Dogan, Aniket Anand Deshmukh, Marcin Machura, Christian Igel
Global Distance-distributions Separation for Unsupervised Person Re-identification – #4006
Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
Efficient Semantic Video Segmentation with Per-frame Inference – #4031
Yifan Liu, Chunhua Shen, Changqian Yu, Jingdong Wang
Negative Margin Matters: Understanding Margin in Few-shot Classification – #4078
Bin Liu, Yue Cao, Yutong Lin, Qi Li, Zheng Zhang, Mingsheng Long, Han Hu
Dense RepPoints: Representing Visual Objects with Dense Point Sets – #4148
Ze Yang, Yinghao Xu, Han Xue, Zheng Zhang, Raquel Urtasun, Liwei Wang, Stephen Lin, Han Hu
Ocean: Object-aware Anchor-free Tracking – #4153
Zhipeng Zhang, Houwen Peng, Jianlong Fu, Bing Li, Weiming Hu
06:00 – 08:00 | Poster Session 10
Global Distance-distributions Separation for Unsupervised Person Re-identification – #4006
Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
Efficient Semantic Video Segmentation with Per-frame Inference – #4031
Yifan Liu, Chunhua Shen, Changqian Yu, Jingdong Wang
Negative Margin Matters: Understanding Margin in Few-shot Classification – #4078
Bin Liu, Yue Cao, Yutong Lin, Qi Li, Zheng Zhang, Mingsheng Long, Han Hu
Dense RepPoints: Representing Visual Objects with Dense Point Sets – #4148
Ze Yang, Yinghao Xu, Han Xue, Zheng Zhang, Raquel Urtasun, Liwei Wang, Stephen Lin, Han Hu
Ocean: Object-aware Anchor-free Tracking – #4153
Zhipeng Zhang, Houwen Peng, Jianlong Fu, Bing Li, Weiming Hu
08:50 – 09:50 | Oral Session – Image and video synthesis
Invertible Image Rescaling – #2015
Mingqing Xiao, Shuxin Zheng, Chang Liu, Yaolong Wang, Di He, Guolin Ke, Jiang Bian, Zhouchen Lin, Tie-Yan Liu
12:30 – 13:30 | Oral Session – Geometry, mapping and tracking
Multi-View Optimization of Local Feature Geometry – #1050
Mihai Dusmanu, Johannes L. Schönberger, Marc Pollefeys
13:20 – 14:20 | Oral Session – Geometry, mapping and tracking
Privacy Preserving Structure-from-Motion – #1031
Marcel Geppert, Viktor Larsson, Pablo Speciale, Johannes L. Schönberger, Marc Pollefeys
14:00 – 16:00 | Poster Session 11
The Phong Surface: Efficient 3D Model Fitting using Lifted Optimization – #4316
Jingjing Shen, Thomas J. Cashman, Qi Ye, Tim Hutton, Toby Sharp, Federica Bogo, Andrew William Fitzgibbon, Jamie Shotton
JNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling – #4337
Noranart Vesdapunt, Mitch Rundle, HsiangTao Wu, Baoyuan Wang
Dynamic ReLU – #4347
Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan, Zicheng Liu
AutoSimulate: (Quickly) Learning Synthetic Data Generation – #4363
Harkirat Singh Behl, Atılım Güneş Baydin, Ran Gal, Philip Torr, Vibhav Vineet
Mining self-similarity: Label super-resolution with epitomic representations – #4394
Kolya Malkin, Anthony Ortiz, Caleb Robinson, Nebojsa Jojic
Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer – #4395
Yuanyi Zhong, Jianfeng Wang, Jian Peng, Lei Zhang
DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search – #4416
Xiyang Dai, Dongdong Chen, Mengchen Liu, Yinpeng Chen, Lu Yuan
Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models – #4439
Jize Cao, Zhe Gan, Yu Cheng, Licheng Yu, Yen-Chun Chen, Jingjing Liu
Oscar: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks – #4446
Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, Yejin Choi, Jianfeng Gao
Friday, August 28
00:00 – 02:00 | Poster Session 12
The Phong Surface: Efficient 3D Model Fitting using Lifted Optimization – #4316
Jingjing Shen, Thomas J. Cashman, Qi Ye, Tim Hutton, Toby Sharp, Federica Bogo, Andrew William Fitzgibbon, Jamie Shotton
JNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling – #4337
Noranart Vesdapunt, Mitch Rundle, HsiangTao Wu, Baoyuan Wang
Dynamic ReLU – #4347
Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan, Zicheng Liu
AutoSimulate: (Quickly) Learning Synthetic Data Generation – #4363
Harkirat Singh Behl, Atılım Güneş Baydin, Ran Gal, Philip Torr, Vibhav Vineet
Mining self-similarity: Label super-resolution with epitomic representations – #4394
Kolya Malkin, Anthony Ortiz, Caleb Robinson, Nebojsa Jojic
Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer – #4395
Yuanyi Zhong, Jianfeng Wang, Jian Peng, Lei Zhang
DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search – #4416
Xiyang Dai, Dongdong Chen, Mengchen Liu, Yinpeng Chen, Lu Yuan
Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models – #4439
Jize Cao, Zhe Gan, Yu Cheng, Licheng Yu, Yen-Chun Chen, Jingjing Liu
Oscar: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks – #4446
Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, Yejin Choi, Jianfeng Gao