Yiheng Zhang

Explaining Cross-Domain Recognition with Interpretable Deep Classifier

Nov 15, 2022
Yiheng Zhang, Ting Yao, Zhaofan Qiu, Tao Mei

Figure 2 for Explaining Cross-Domain Recognition with Interpretable Deep Classifier

Figure 3 for Explaining Cross-Domain Recognition with Interpretable Deep Classifier

Figure 4 for Explaining Cross-Domain Recognition with Interpretable Deep Classifier

Access Paper or Ask Questions

Lightweight and Progressively-Scalable Networks for Semantic Segmentation

Jul 27, 2022
Yiheng Zhang, Ting Yao, Zhaofan Qiu, Tao Mei

Figure 2 for Lightweight and Progressively-Scalable Networks for Semantic Segmentation

Figure 3 for Lightweight and Progressively-Scalable Networks for Semantic Segmentation

Figure 4 for Lightweight and Progressively-Scalable Networks for Semantic Segmentation

Access Paper or Ask Questions

Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation

Jun 13, 2022
Yingwei Pan, Yehao Li, Yiheng Zhang, Qi Cai, Fuchen Long, Zhaofan Qiu, Ting Yao, Tao Mei

Figure 2 for Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation

Figure 3 for Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation

Figure 4 for Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation

* Accepted by ICLR 2022 Workshop on Generalizable Policy Learning in Physical World. Top-performing systems for both no interaction and no restriction tracks in SAPIEN ManiSkill Challenge 2021. The source code and model are publicly available at: https://github.com/caiqi/Silver-Bullet-3D/

Access Paper or Ask Questions

Motion-Focused Contrastive Learning of Video Representations

Jan 11, 2022
Rui Li, Yiheng Zhang, Zhaofan Qiu, Ting Yao, Dong Liu, Tao Mei

Figure 2 for Motion-Focused Contrastive Learning of Video Representations

Figure 3 for Motion-Focused Contrastive Learning of Video Representations

Figure 4 for Motion-Focused Contrastive Learning of Video Representations

* ICCV 2021 (Oral); Code is publicly available at: https://github.com/YihengZhang-CV/MCL-Motion-Focused-Contrastive-Learning

Access Paper or Ask Questions