Alert button
Picture for Boyang Li

Boyang Li

Alert button

Evaluating and Mitigating Static Bias of Action Representations in the Background and the Foreground

Nov 23, 2022
Haoxin Li, Yue Wu, Yuan Liu, Hanwang Zhang, Boyang Li

Figure 1 for Evaluating and Mitigating Static Bias of Action Representations in the Background and the Foreground
Figure 2 for Evaluating and Mitigating Static Bias of Action Representations in the Background and the Foreground
Figure 3 for Evaluating and Mitigating Static Bias of Action Representations in the Background and the Foreground
Figure 4 for Evaluating and Mitigating Static Bias of Action Representations in the Background and the Foreground
Viaarxiv icon

A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture

Oct 20, 2022
Jiayun Luo, Boyang Li, Cyril Leung

Figure 1 for A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture
Figure 2 for A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture
Viaarxiv icon

Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training

Oct 17, 2022
Anthony Meng Huat Tiong, Junnan Li, Boyang Li, Silvio Savarese, Steven C. H. Hoi

Figure 1 for Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
Figure 2 for Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
Figure 3 for Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
Figure 4 for Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
Viaarxiv icon

Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation

Oct 06, 2022
Xu Guo, Boyang Li, Han Yu

Figure 1 for Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
Figure 2 for Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
Figure 3 for Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
Figure 4 for Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
Viaarxiv icon

MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection

Sep 28, 2022
Tianhao Wu, Boyang Li, Yihang Luo, Yingqian Wang, Chao Xiao, Ting Liu, Jungang Yang, Wei An, Yulan Guo

Figure 1 for MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
Figure 2 for MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
Figure 3 for MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
Figure 4 for MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
Viaarxiv icon

Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference

Jul 01, 2022
Yinan Zhang, Boyang Li, Yong Liu, You Yuan, Chunyan Miao

Figure 1 for Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference
Figure 2 for Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference
Figure 3 for Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference
Figure 4 for Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference
Viaarxiv icon

Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction

Jun 01, 2022
Jun Chen, Ming Hu, Boyang Li, Mohamed Elhoseiny

Figure 1 for Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction
Figure 2 for Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction
Figure 3 for Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction
Figure 4 for Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction
Viaarxiv icon

Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding

Mar 11, 2022
Yidan Sun, Qin Chao, Boyang Li

Figure 1 for Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding
Figure 2 for Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding
Figure 3 for Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding
Figure 4 for Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding
Viaarxiv icon

Improving Tail-Class Representation with Centroid Contrastive Learning

Oct 19, 2021
Anthony Meng Huat Tiong, Junnan Li, Guosheng Lin, Boyang Li, Caiming Xiong, Steven C. H. Hoi

Figure 1 for Improving Tail-Class Representation with Centroid Contrastive Learning
Figure 2 for Improving Tail-Class Representation with Centroid Contrastive Learning
Figure 3 for Improving Tail-Class Representation with Centroid Contrastive Learning
Figure 4 for Improving Tail-Class Representation with Centroid Contrastive Learning
Viaarxiv icon