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

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

FLAG: Adversarial Data Augmentation for Graph Neural Networks


Oct 19, 2020
Kezhi Kong, Guohao Li, Mucong Ding, Zuxuan Wu, Chen Zhu, Bernard Ghanem, Gavin Taylor, Tom Goldstein

Figure 1 for FLAG: Adversarial Data Augmentation for Graph Neural Networks
Figure 2 for FLAG: Adversarial Data Augmentation for Graph Neural Networks
Figure 3 for FLAG: Adversarial Data Augmentation for Graph Neural Networks
Figure 4 for FLAG: Adversarial Data Augmentation for Graph Neural Networks

  Access Paper or Ask Questions

Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization


Sep 21, 2020
Manli Shu, Zuxuan Wu, Micah Goldblum, Tom Goldstein

Figure 1 for Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization
Figure 2 for Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization
Figure 3 for Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization
Figure 4 for Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization

  Access Paper or Ask Questions

Preparing for the Worst: Making Networks Less Brittle with Adversarial Batch Normalization


Sep 18, 2020
Manli Shu, Zuxuan Wu, Micah Goldblum, Tom Goldstein

Figure 1 for Preparing for the Worst: Making Networks Less Brittle with Adversarial Batch Normalization
Figure 2 for Preparing for the Worst: Making Networks Less Brittle with Adversarial Batch Normalization
Figure 3 for Preparing for the Worst: Making Networks Less Brittle with Adversarial Batch Normalization
Figure 4 for Preparing for the Worst: Making Networks Less Brittle with Adversarial Batch Normalization

  Access Paper or Ask Questions

Recognizing Instagram Filtered Images with Feature De-stylization


Dec 30, 2019
Zhe Wu, Zuxuan Wu, Bharat Singh, Larry S. Davis

Figure 1 for Recognizing Instagram Filtered Images with Feature De-stylization
Figure 2 for Recognizing Instagram Filtered Images with Feature De-stylization
Figure 3 for Recognizing Instagram Filtered Images with Feature De-stylization
Figure 4 for Recognizing Instagram Filtered Images with Feature De-stylization
* Accepted in AAAI 2020 as an oral presentation paper 
  Access Paper or Ask Questions

Learning from Noisy Anchors for One-stage Object Detection


Dec 11, 2019
Hengduo Li, Zuxuan Wu, Chen Zhu, Caiming Xiong, Richard Socher, Larry S. Davis

Figure 1 for Learning from Noisy Anchors for One-stage Object Detection
Figure 2 for Learning from Noisy Anchors for One-stage Object Detection
Figure 3 for Learning from Noisy Anchors for One-stage Object Detection
Figure 4 for Learning from Noisy Anchors for One-stage Object Detection

  Access Paper or Ask Questions

LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition


Dec 03, 2019
Zuxuan Wu, Caiming Xiong, Yu-Gang Jiang, Larry S. Davis

Figure 1 for LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Figure 2 for LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Figure 3 for LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Figure 4 for LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
* NeurIPS 2019 
  Access Paper or Ask Questions

Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors


Oct 31, 2019
Zuxuan Wu, Ser-Nam Lim, Larry Davis, Tom Goldstein

Figure 1 for Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
Figure 2 for Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
Figure 3 for Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
Figure 4 for Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors

  Access Paper or Ask Questions

ACE: Adapting to Changing Environments for Semantic Segmentation


Apr 12, 2019
Zuxuan Wu, Xin Wang, Joseph E. Gonzalez, Tom Goldstein, Larry S. Davis

Figure 1 for ACE: Adapting to Changing Environments for Semantic Segmentation
Figure 2 for ACE: Adapting to Changing Environments for Semantic Segmentation
Figure 3 for ACE: Adapting to Changing Environments for Semantic Segmentation
Figure 4 for ACE: Adapting to Changing Environments for Semantic Segmentation

  Access Paper or Ask Questions

An Analysis of Pre-Training on Object Detection


Apr 11, 2019
Hengduo Li, Bharat Singh, Mahyar Najibi, Zuxuan Wu, Larry S. Davis

Figure 1 for An Analysis of Pre-Training on Object Detection
Figure 2 for An Analysis of Pre-Training on Object Detection
Figure 3 for An Analysis of Pre-Training on Object Detection
Figure 4 for An Analysis of Pre-Training on Object Detection

  Access Paper or Ask Questions

M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning


Apr 03, 2019
Peng Zhou, Long Mai, Jianming Zhang, Ning Xu, Zuxuan Wu, Larry S. Davis

Figure 1 for M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
Figure 2 for M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
Figure 3 for M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
Figure 4 for M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning

  Access Paper or Ask Questions

The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation


Mar 05, 2019
Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira

Figure 1 for The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
Figure 2 for The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
Figure 3 for The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
Figure 4 for The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
* CVPR 2019 (Oral), our code is available at https://github.com/chihyaoma/regretful-agent 
  Access Paper or Ask Questions

Compatible and Diverse Fashion Image Inpainting


Feb 04, 2019
Xintong Han, Zuxuan Wu, Weilin Huang, Matthew R. Scott, Larry S. Davis

Figure 1 for Compatible and Diverse Fashion Image Inpainting
Figure 2 for Compatible and Diverse Fashion Image Inpainting
Figure 3 for Compatible and Diverse Fashion Image Inpainting
Figure 4 for Compatible and Diverse Fashion Image Inpainting

  Access Paper or Ask Questions

Self-Monitoring Navigation Agent via Auxiliary Progress Estimation


Jan 10, 2019
Chih-Yao Ma, Jiasen Lu, Zuxuan Wu, Ghassan AlRegib, Zsolt Kira, Richard Socher, Caiming Xiong

Figure 1 for Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Figure 2 for Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Figure 3 for Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Figure 4 for Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
* ICLR 2019, code is available at https://github.com/chihyaoma/selfmonitoring-agent 
  Access Paper or Ask Questions

AdaFrame: Adaptive Frame Selection for Fast Video Recognition


Nov 29, 2018
Zuxuan Wu, Caiming Xiong, Chih-Yao Ma, Richard Socher, Larry S. Davis

Figure 1 for AdaFrame: Adaptive Frame Selection for Fast Video Recognition
Figure 2 for AdaFrame: Adaptive Frame Selection for Fast Video Recognition
Figure 3 for AdaFrame: Adaptive Frame Selection for Fast Video Recognition
Figure 4 for AdaFrame: Adaptive Frame Selection for Fast Video Recognition

  Access Paper or Ask Questions

VITON: An Image-based Virtual Try-on Network


Jun 12, 2018
Xintong Han, Zuxuan Wu, Zhe Wu, Ruichi Yu, Larry S. Davis

Figure 1 for VITON: An Image-based Virtual Try-on Network
Figure 2 for VITON: An Image-based Virtual Try-on Network
Figure 3 for VITON: An Image-based Virtual Try-on Network
Figure 4 for VITON: An Image-based Virtual Try-on Network

  Access Paper or Ask Questions

DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation


Apr 16, 2018
Zuxuan Wu, Xintong Han, Yen-Liang Lin, Mustafa Gkhan Uzunbas, Tom Goldstein, Ser Nam Lim, Larry S. Davis

Figure 1 for DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
Figure 2 for DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
Figure 3 for DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
Figure 4 for DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation

  Access Paper or Ask Questions

BlockDrop: Dynamic Inference Paths in Residual Networks


Apr 12, 2018
Zuxuan Wu, Tushar Nagarajan, Abhishek Kumar, Steven Rennie, Larry S. Davis, Kristen Grauman, Rogerio Feris

Figure 1 for BlockDrop: Dynamic Inference Paths in Residual Networks
Figure 2 for BlockDrop: Dynamic Inference Paths in Residual Networks
Figure 3 for BlockDrop: Dynamic Inference Paths in Residual Networks
Figure 4 for BlockDrop: Dynamic Inference Paths in Residual Networks
* CVPR 2018 
  Access Paper or Ask Questions