Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Yu-Gang Jiang

Yu-Gang Jiang

Efficient Video Transformers with Spatial-Temporal Token Selection


Nov 23, 2021
Junke Wang, Xitong Yang, Hengduo Li, Zuxuan Wu, Yu-Gang Jiang

Figure 1 for Efficient Video Transformers with Spatial-Temporal Token Selection
Figure 2 for Efficient Video Transformers with Spatial-Temporal Token Selection
Figure 3 for Efficient Video Transformers with Spatial-Temporal Token Selection
Figure 4 for Efficient Video Transformers with Spatial-Temporal Token Selection

  Access Paper or Ask Questions

Semi-Supervised Vision Transformers


Nov 22, 2021
Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang

Figure 1 for Semi-Supervised Vision Transformers
Figure 2 for Semi-Supervised Vision Transformers
Figure 3 for Semi-Supervised Vision Transformers
Figure 4 for Semi-Supervised Vision Transformers
* 10 pages, 5 figures 
  Access Paper or Ask Questions

CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition


Nov 22, 2021
Tianlun Zheng, Zhineng Chen, Shancheng Fang, Hongtao Xie, Yu-Gang Jiang

Figure 1 for CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
Figure 2 for CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
Figure 3 for CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
Figure 4 for CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition

  Access Paper or Ask Questions

Attacking Video Recognition Models with Bullet-Screen Comments


Oct 29, 2021
Kai Chen, Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

Figure 1 for Attacking Video Recognition Models with Bullet-Screen Comments
Figure 2 for Attacking Video Recognition Models with Bullet-Screen Comments
Figure 3 for Attacking Video Recognition Models with Bullet-Screen Comments
Figure 4 for Attacking Video Recognition Models with Bullet-Screen Comments

  Access Paper or Ask Questions

Boosting the Transferability of Video Adversarial Examples via Temporal Translation


Oct 18, 2021
Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

Figure 1 for Boosting the Transferability of Video Adversarial Examples via Temporal Translation
Figure 2 for Boosting the Transferability of Video Adversarial Examples via Temporal Translation
Figure 3 for Boosting the Transferability of Video Adversarial Examples via Temporal Translation
Figure 4 for Boosting the Transferability of Video Adversarial Examples via Temporal Translation

  Access Paper or Ask Questions

Two-stage Visual Cues Enhancement Network for Referring Image Segmentation


Oct 09, 2021
Yang Jiao, Zequn Jie, Weixin Luo, Jingjing Chen, Yu-Gang Jiang, Xiaolin Wei, Lin Ma

Figure 1 for Two-stage Visual Cues Enhancement Network for Referring Image Segmentation
Figure 2 for Two-stage Visual Cues Enhancement Network for Referring Image Segmentation
Figure 3 for Two-stage Visual Cues Enhancement Network for Referring Image Segmentation
Figure 4 for Two-stage Visual Cues Enhancement Network for Referring Image Segmentation
* Accepted by ACM MM 2021 
  Access Paper or Ask Questions

Self-supervised Learning for Semi-supervised Temporal Language Grounding


Sep 23, 2021
Fan Luo, Shaoxiang Chen, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

Figure 1 for Self-supervised Learning for Semi-supervised Temporal Language Grounding
Figure 2 for Self-supervised Learning for Semi-supervised Temporal Language Grounding
Figure 3 for Self-supervised Learning for Semi-supervised Temporal Language Grounding
Figure 4 for Self-supervised Learning for Semi-supervised Temporal Language Grounding

  Access Paper or Ask Questions

Towards Transferable Adversarial Attacks on Vision Transformers


Sep 18, 2021
Zhipeng Wei, Jingjing Chen, Micah Goldblum, Zuxuan Wu, Tom Goldstein, Yu-Gang Jiang

Figure 1 for Towards Transferable Adversarial Attacks on Vision Transformers
Figure 2 for Towards Transferable Adversarial Attacks on Vision Transformers
Figure 3 for Towards Transferable Adversarial Attacks on Vision Transformers
Figure 4 for Towards Transferable Adversarial Attacks on Vision Transformers

  Access Paper or Ask Questions

A Multimodal Framework for Video Ads Understanding


Aug 29, 2021
Zejia Weng, Lingchen Meng, Rui Wang, Zuxuan Wu, Yu-Gang Jiang

Figure 1 for A Multimodal Framework for Video Ads Understanding
Figure 2 for A Multimodal Framework for Video Ads Understanding
Figure 3 for A Multimodal Framework for Video Ads Understanding
Figure 4 for A Multimodal Framework for Video Ads Understanding
* 4 pages; 2 figures; ACM MM 2021 workshop; Tencent Advertising Algorithm Competition ACM Multimedia 2021 Grand Challenge 
  Access Paper or Ask Questions

Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better


Aug 18, 2021
Bojia Zi, Shihao Zhao, Xingjun Ma, Yu-Gang Jiang

Figure 1 for Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better
Figure 2 for Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better
Figure 3 for Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better
Figure 4 for Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better

  Access Paper or Ask Questions

FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting


Aug 10, 2021
Junke Wang, Shaoxiang Chen, Zuxuan Wu, Yu-Gang Jiang

Figure 1 for FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting
Figure 2 for FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting
Figure 3 for FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting
Figure 4 for FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting

  Access Paper or Ask Questions

Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data


Jul 26, 2021
Yuqian Fu, Yanwei Fu, Yu-Gang Jiang

Figure 1 for Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
Figure 2 for Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
Figure 3 for Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
Figure 4 for Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
* Accepted by ACM Multimedia 2021 
  Access Paper or Ask Questions

Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos


Jul 25, 2021
Yuqian Fu, Yanwei Fu, Yu-Gang Jiang

Figure 1 for Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos
Figure 2 for Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos
Figure 3 for Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos
Figure 4 for Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos
* accpected by ICMR2021 
  Access Paper or Ask Questions

Cross-domain Contrastive Learning for Unsupervised Domain Adaptation


Jun 10, 2021
Rui Wang, Zuxuan Wu, Zejia Weng, Jingjing Chen, Guo-Jun Qi, Yu-Gang Jiang

Figure 1 for Cross-domain Contrastive Learning for Unsupervised Domain Adaptation
Figure 2 for Cross-domain Contrastive Learning for Unsupervised Domain Adaptation
Figure 3 for Cross-domain Contrastive Learning for Unsupervised Domain Adaptation
Figure 4 for Cross-domain Contrastive Learning for Unsupervised Domain Adaptation

  Access Paper or Ask Questions

VideoLT: Large-scale Long-tailed Video Recognition


May 06, 2021
Xing Zhang, Zuxuan Wu, Zejia Weng, Huazhu Fu, Jingjing Chen, Yu-Gang Jiang, Larry Davis

Figure 1 for VideoLT: Large-scale Long-tailed Video Recognition
Figure 2 for VideoLT: Large-scale Long-tailed Video Recognition
Figure 3 for VideoLT: Large-scale Long-tailed Video Recognition
Figure 4 for VideoLT: Large-scale Long-tailed Video Recognition
* 10 pages, 6 figures 
  Access Paper or Ask Questions

M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection


Apr 21, 2021
Junke Wang, Zuxuan Wu, Jingjing Chen, Yu-Gang Jiang

Figure 1 for M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection
Figure 2 for M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection
Figure 3 for M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection
Figure 4 for M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection

  Access Paper or Ask Questions

HMS: Hierarchical Modality Selection for Efficient Video Recognition


Apr 21, 2021
Zejia Weng, Zuxuan Wu, Hengduo Li, Yu-Gang Jiang

Figure 1 for HMS: Hierarchical Modality Selection for Efficient Video Recognition
Figure 2 for HMS: Hierarchical Modality Selection for Efficient Video Recognition
Figure 3 for HMS: Hierarchical Modality Selection for Efficient Video Recognition
Figure 4 for HMS: Hierarchical Modality Selection for Efficient Video Recognition

  Access Paper or Ask Questions

HMS: Hierarchical Modality Selectionfor Efficient Video Recognition


Apr 20, 2021
Zejia Weng, Zuxuan Wu, Hengduo Li, Yu-Gang Jiang

Figure 1 for HMS: Hierarchical Modality Selectionfor Efficient Video Recognition
Figure 2 for HMS: Hierarchical Modality Selectionfor Efficient Video Recognition
Figure 3 for HMS: Hierarchical Modality Selectionfor Efficient Video Recognition
Figure 4 for HMS: Hierarchical Modality Selectionfor Efficient Video Recognition

  Access Paper or Ask Questions

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space


Feb 06, 2021
Shihao Zhao, Xingjun Ma, Yisen Wang, James Bailey, Bo Li, Yu-Gang Jiang

Figure 1 for What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
Figure 2 for What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
Figure 3 for What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
Figure 4 for What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space

  Access Paper or Ask Questions

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection


Jan 05, 2021
Bojia Zi, Minghao Chang, Jingjing Chen, Xingjun Ma, Yu-Gang Jiang

Figure 1 for WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
Figure 2 for WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
Figure 3 for WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
Figure 4 for WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection

  Access Paper or Ask Questions

Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos


Dec 31, 2020
Zhi-Qin Zhan, Huazhu Fu, Yan-Yao Yang, Jingjing Chen, Jie Liu, Yu-Gang Jiang

Figure 1 for Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos
Figure 2 for Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos
Figure 3 for Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos
Figure 4 for Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos

  Access Paper or Ask Questions

Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition


Oct 20, 2020
Yuqian Fu, Li Zhang, Junke Wang, Yanwei Fu, Yu-Gang Jiang

Figure 1 for Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
Figure 2 for Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
Figure 3 for Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
Figure 4 for Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
* accepted by ACM Multimedia 2020 
  Access Paper or Ask Questions

Multi-modal Cooking Workflow Construction for Food Recipes


Aug 20, 2020
Liangming Pan, Jingjing Chen, Jianlong Wu, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Yu-Gang Jiang, Tat-Seng Chua

Figure 1 for Multi-modal Cooking Workflow Construction for Food Recipes
Figure 2 for Multi-modal Cooking Workflow Construction for Food Recipes
Figure 3 for Multi-modal Cooking Workflow Construction for Food Recipes
Figure 4 for Multi-modal Cooking Workflow Construction for Food Recipes
* This manuscript has been accepted at ACM MM 2020 
  Access Paper or Ask Questions

Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos


Jul 28, 2020
Shaoxiang Chen, Wenhao Jiang, Wei Liu, Yu-Gang Jiang

Figure 1 for Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos
Figure 2 for Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos
Figure 3 for Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos
Figure 4 for Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos

  Access Paper or Ask Questions

Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness


Jun 30, 2020
Linxi Jiang, Xingjun Ma, Zejia Weng, James Bailey, Yu-Gang Jiang

Figure 1 for Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness
Figure 2 for Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness
Figure 3 for Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness
Figure 4 for Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness
* 17 pages, 7 figues 
  Access Paper or Ask Questions

Long-Term Cloth-Changing Person Re-identification


May 27, 2020
Xuelin Qian, Wenxuan Wang, Li Zhang, Fangrui Zhu, Yanwei Fu, Tao Xiang, Yu-Gang Jiang, Xiangyang Xue

Figure 1 for Long-Term Cloth-Changing Person Re-identification
Figure 2 for Long-Term Cloth-Changing Person Re-identification
Figure 3 for Long-Term Cloth-Changing Person Re-identification
Figure 4 for Long-Term Cloth-Changing Person Re-identification
* 24 pages, 10 figures, 5 tables 
  Access Paper or Ask Questions