Alert button
Picture for Gangshan Wu

Gangshan Wu

Alert button

Sketch and Refine: Towards Fast and Accurate Lane Detection

Jan 26, 2024
Chao Chen, Jie Liu, Chang Zhou, Jie Tang, Gangshan Wu

Viaarxiv icon

Asymmetric Masked Distillation for Pre-Training Small Foundation Models

Nov 06, 2023
Zhiyu Zhao, Bingkun Huang, Sen Xing, Gangshan Wu, Yu Qiao, Limin Wang

Viaarxiv icon

Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation

Aug 25, 2023
Jiaming Zhang, Yutao Cui, Gangshan Wu, Limin Wang

Figure 1 for Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation
Figure 2 for Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation
Figure 3 for Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation
Figure 4 for Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation
Viaarxiv icon

DPL: Decoupled Prompt Learning for Vision-Language Models

Aug 19, 2023
Chen Xu, Yuhan Zhu, Guozhen Zhang, Haocheng Shen, Yixuan Liao, Xiaoxin Chen, Gangshan Wu, Limin Wang

Viaarxiv icon

Robust Object Modeling for Visual Tracking

Aug 09, 2023
Yidong Cai, Jie Liu, Jie Tang, Gangshan Wu

Figure 1 for Robust Object Modeling for Visual Tracking
Figure 2 for Robust Object Modeling for Visual Tracking
Figure 3 for Robust Object Modeling for Visual Tracking
Figure 4 for Robust Object Modeling for Visual Tracking
Viaarxiv icon

Lightweight Super-Resolution Head for Human Pose Estimation

Jul 31, 2023
Haonan Wang, Jie Liu, Jie Tang, Gangshan Wu

Figure 1 for Lightweight Super-Resolution Head for Human Pose Estimation
Figure 2 for Lightweight Super-Resolution Head for Human Pose Estimation
Figure 3 for Lightweight Super-Resolution Head for Human Pose Estimation
Figure 4 for Lightweight Super-Resolution Head for Human Pose Estimation
Viaarxiv icon

MaxSR: Image Super-Resolution Using Improved MaxViT

Jul 14, 2023
Bincheng Yang, Gangshan Wu

Figure 1 for MaxSR: Image Super-Resolution Using Improved MaxViT
Figure 2 for MaxSR: Image Super-Resolution Using Improved MaxViT
Figure 3 for MaxSR: Image Super-Resolution Using Improved MaxViT
Figure 4 for MaxSR: Image Super-Resolution Using Improved MaxViT
Viaarxiv icon

MixFormerV2: Efficient Fully Transformer Tracking

May 25, 2023
Yutao Cui, Tianhui Song, Gangshan Wu, Limin Wang

Figure 1 for MixFormerV2: Efficient Fully Transformer Tracking
Figure 2 for MixFormerV2: Efficient Fully Transformer Tracking
Figure 3 for MixFormerV2: Efficient Fully Transformer Tracking
Figure 4 for MixFormerV2: Efficient Fully Transformer Tracking
Viaarxiv icon

Video Frame Interpolation with Densely Queried Bilateral Correlation

Apr 26, 2023
Chang Zhou, Jie Liu, Jie Tang, Gangshan Wu

Figure 1 for Video Frame Interpolation with Densely Queried Bilateral Correlation
Figure 2 for Video Frame Interpolation with Densely Queried Bilateral Correlation
Figure 3 for Video Frame Interpolation with Densely Queried Bilateral Correlation
Figure 4 for Video Frame Interpolation with Densely Queried Bilateral Correlation
Viaarxiv icon

Efficient Video Action Detection with Token Dropout and Context Refinement

Apr 17, 2023
Lei Chen, Zhan Tong, Yibing Song, Gangshan Wu, Limin Wang

Figure 1 for Efficient Video Action Detection with Token Dropout and Context Refinement
Figure 2 for Efficient Video Action Detection with Token Dropout and Context Refinement
Figure 3 for Efficient Video Action Detection with Token Dropout and Context Refinement
Figure 4 for Efficient Video Action Detection with Token Dropout and Context Refinement
Viaarxiv icon