Alert button
Picture for Song-Chun Zhu

Song-Chun Zhu

Alert button

Representation Learning: A Statistical Perspective

Nov 26, 2019
Jianwen Xie, Ruiqi Gao, Erik Nijkamp, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Representation Learning: A Statistical Perspective
Figure 2 for Representation Learning: A Statistical Perspective
Figure 3 for Representation Learning: A Statistical Perspective
Figure 4 for Representation Learning: A Statistical Perspective
Viaarxiv icon

Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns

Nov 26, 2019
Jianwen Xie, Ruiqi Gao, Zilong Zheng, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns
Figure 2 for Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns
Figure 3 for Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns
Figure 4 for Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns
Viaarxiv icon

Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning

Nov 25, 2019
Mark Edmonds, Xiaojian Ma, Siyuan Qi, Yixin Zhu, Hongjing Lu, Song-Chun Zhu

Figure 1 for Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning
Figure 2 for Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning
Figure 3 for Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning
Figure 4 for Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning
Viaarxiv icon

DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare

Oct 09, 2019
Yuanlu Xu, Song-Chun Zhu, Tony Tung

Figure 1 for DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare
Figure 2 for DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare
Figure 3 for DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare
Figure 4 for DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare
Viaarxiv icon

Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patterns

Sep 26, 2019
Jianwen Xie, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patterns
Figure 2 for Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patterns
Figure 3 for Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patterns
Figure 4 for Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patterns
Viaarxiv icon

X-ToM: Explaining with Theory-of-Mind for Gaining Justified Human Trust

Sep 15, 2019
Arjun R. Akula, Changsong Liu, Sari Saba-Sadiya, Hongjing Lu, Sinisa Todorovic, Joyce Y. Chai, Song-Chun Zhu

Figure 1 for X-ToM: Explaining with Theory-of-Mind for Gaining Justified Human Trust
Figure 2 for X-ToM: Explaining with Theory-of-Mind for Gaining Justified Human Trust
Figure 3 for X-ToM: Explaining with Theory-of-Mind for Gaining Justified Human Trust
Figure 4 for X-ToM: Explaining with Theory-of-Mind for Gaining Justified Human Trust
Viaarxiv icon

Towards Interpretable Image Synthesis by Learning Sparsely Connected AND-OR Networks

Sep 10, 2019
Xianglei Xing, Tianfu Wu, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Towards Interpretable Image Synthesis by Learning Sparsely Connected AND-OR Networks
Figure 2 for Towards Interpretable Image Synthesis by Learning Sparsely Connected AND-OR Networks
Figure 3 for Towards Interpretable Image Synthesis by Learning Sparsely Connected AND-OR Networks
Figure 4 for Towards Interpretable Image Synthesis by Learning Sparsely Connected AND-OR Networks
Viaarxiv icon

Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning

Sep 04, 2019
Lifeng Fan, Wenguan Wang, Siyuan Huang, Xinyu Tang, Song-Chun Zhu

Figure 1 for Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
Figure 2 for Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
Figure 3 for Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
Figure 4 for Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
Viaarxiv icon

Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense

Sep 04, 2019
Yixin Chen, Siyuan Huang, Tao Yuan, Siyuan Qi, Yixin Zhu, Song-Chun Zhu

Figure 1 for Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
Figure 2 for Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
Figure 3 for Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
Figure 4 for Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
Viaarxiv icon