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 Zuxuan Wu

Zuxuan Wu

Rethinking Nearest Neighbors for Visual Classification


Dec 17, 2021
Menglin Jia, Bor-Chun Chen, Zuxuan Wu, Claire Cardie, Serge Belongie, Ser-Nam Lim

Figure 1 for Rethinking Nearest Neighbors for Visual Classification
Figure 2 for Rethinking Nearest Neighbors for Visual Classification
Figure 3 for Rethinking Nearest Neighbors for Visual Classification
Figure 4 for Rethinking Nearest Neighbors for Visual Classification
* Modified paragraph spacing 
  Access Paper or Ask Questions

Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation


Dec 15, 2021
Tianyi Liu, Zuxuan Wu, Wenhan Xiong, Jingjing Chen, Yu-Gang Jiang

Figure 1 for Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation
Figure 2 for Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation
Figure 3 for Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation
Figure 4 for Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation

  Access Paper or Ask Questions

Cross-Modal Transferable Adversarial Attacks from Images to Videos


Dec 10, 2021
Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

Figure 1 for Cross-Modal Transferable Adversarial Attacks from Images to Videos
Figure 2 for Cross-Modal Transferable Adversarial Attacks from Images to Videos
Figure 3 for Cross-Modal Transferable Adversarial Attacks from Images to Videos
Figure 4 for Cross-Modal Transferable Adversarial Attacks from Images to Videos

  Access Paper or Ask Questions

BEVT: BERT Pretraining of Video Transformers


Dec 02, 2021
Rui Wang, Dongdong Chen, Zuxuan Wu, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Yu-Gang Jiang, Luowei Zhou, Lu Yuan

Figure 1 for BEVT: BERT Pretraining of Video Transformers
Figure 2 for BEVT: BERT Pretraining of Video Transformers
Figure 3 for BEVT: BERT Pretraining of Video Transformers
Figure 4 for BEVT: BERT Pretraining of Video Transformers

  Access Paper or Ask Questions

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition


Nov 30, 2021
Lingchen Meng, Hengduo Li, Bor-Chun Chen, Shiyi Lan, Zuxuan Wu, Yu-Gang Jiang, Ser-Nam Lim

Figure 1 for AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
Figure 2 for AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
Figure 3 for AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
Figure 4 for AdaViT: Adaptive Vision Transformers for Efficient Image Recognition

  Access Paper or Ask Questions

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

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

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

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

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

Rethinking Pseudo Labels for Semi-Supervised Object Detection


Jun 01, 2021
Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S. Davis

Figure 1 for Rethinking Pseudo Labels for Semi-Supervised Object Detection
Figure 2 for Rethinking Pseudo Labels for Semi-Supervised Object Detection
Figure 3 for Rethinking Pseudo Labels for Semi-Supervised Object Detection
Figure 4 for Rethinking Pseudo Labels for Semi-Supervised Object Detection

  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

M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers


Apr 30, 2021
Tianrui Guan, Jun Wang, Shiyi Lan, Rohan Chandra, Zuxuan Wu, Larry Davis, Dinesh Manocha

Figure 1 for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
Figure 2 for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
Figure 3 for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
Figure 4 for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers

  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

Exploring Visual Engagement Signals for Representation Learning


Apr 15, 2021
Menglin Jia, Zuxuan Wu, Austin Reiter, Claire Cardie, Serge Belongie, Ser-Nam Lim

Figure 1 for Exploring Visual Engagement Signals for Representation Learning
Figure 2 for Exploring Visual Engagement Signals for Representation Learning
Figure 3 for Exploring Visual Engagement Signals for Representation Learning
Figure 4 for Exploring Visual Engagement Signals for Representation Learning

  Access Paper or Ask Questions

THAT: Two Head Adversarial Training for Improving Robustness at Scale


Mar 25, 2021
Zuxuan Wu, Tom Goldstein, Larry S. Davis, Ser-Nam Lim

Figure 1 for THAT: Two Head Adversarial Training for Improving Robustness at Scale
Figure 2 for THAT: Two Head Adversarial Training for Improving Robustness at Scale
Figure 3 for THAT: Two Head Adversarial Training for Improving Robustness at Scale
Figure 4 for THAT: Two Head Adversarial Training for Improving Robustness at Scale

  Access Paper or Ask Questions

Deep Video Inpainting Detection


Jan 26, 2021
Peng Zhou, Ning Yu, Zuxuan Wu, Larry S. Davis, Abhinav Shrivastava, Ser-Nam Lim

Figure 1 for Deep Video Inpainting Detection
Figure 2 for Deep Video Inpainting Detection
Figure 3 for Deep Video Inpainting Detection
Figure 4 for Deep Video Inpainting Detection

  Access Paper or Ask Questions

2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition


Dec 29, 2020
Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S. Davis

Figure 1 for 2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
Figure 2 for 2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
Figure 3 for 2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
Figure 4 for 2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition

  Access Paper or Ask Questions

GTA: Global Temporal Attention for Video Action Understanding


Dec 15, 2020
Bo He, Xitong Yang, Zuxuan Wu, Hao Chen, Ser-Nam Lim, Abhinav Shrivastava

Figure 1 for GTA: Global Temporal Attention for Video Action Understanding
Figure 2 for GTA: Global Temporal Attention for Video Action Understanding
Figure 3 for GTA: Global Temporal Attention for Video Action Understanding
Figure 4 for GTA: Global Temporal Attention for Video Action Understanding

  Access Paper or Ask Questions

Intentonomy: a Dataset and Study towards Human Intent Understanding


Nov 11, 2020
Menglin Jia, Zuxuan Wu, Austin Reiter, Claire Cardie, Serge Belongie, Ser-Nam Lim

Figure 1 for Intentonomy: a Dataset and Study towards Human Intent Understanding
Figure 2 for Intentonomy: a Dataset and Study towards Human Intent Understanding
Figure 3 for Intentonomy: a Dataset and Study towards Human Intent Understanding
Figure 4 for Intentonomy: a Dataset and Study towards Human Intent Understanding

  Access Paper or Ask Questions