Zuxuan Wu

School of Computer Science

Fudan University, Shanghai, China

Email: zxwu AT fudan dot edu dot cn

I am an Assistant Professor in School of Computer Science at Fudan University, and a member of the Fudan Vision and Learning Laboratory. I recieved my Ph.D. in Computer Science from the University of Maryland with Prof. Larry Davis in 2020. My research interests are in computer vision and deep learning. My current research particularly focuses on large-scale video understanding, computationally efficient frameworks and robust deep neural networks.

I'm currently looking for students with strong coding skills who are excited to design algorithms for visual understanding. If you are interested in working with me, please send me an email.

Publication [Google Scholar]

OmniVL: One Foundation Model for Image-Language and Video-Language Tasks. [pdf]
Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, Dec., 2022.
Junke Wang, Dongdong Chen, Zuxuan Wu, Chong Luo, Luowei Zhou, Yucheng Zhao, Yujia Xie, Ce Liu, Yu-Gang Jiang, Lu Yuan

Semi-Supervised Vision Transformers. [pdf][code]
European Conference on Computer Vision (ECCV), Tel Aviv, October, 2022.
Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang

Efficient Video Transformers with Spatial-Temporal Token Selection. [pdf][code]
European Conference on Computer Vision (ECCV), Tel Aviv, October, 2022.
Junke Wang, Xitong Yang, Hengduo Li, Li Liu, Zuxuan Wu, Yu-Gang Jiang

Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors. [pdf][code]
European Conference on Computer Vision (ECCV), Tel Aviv, October, 2022.
Zhen Xing, Hengduo Li, Zuxuan Wu, Yu-Gang Jiang

BEVT: BERT Pretraining of Video Transformers. [pdf][code]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, June, 2022
Rui Wang, Dongdong Chen, Zuxuan Wu, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Yu-Gang Jiang, Luowei Zhou, Lu Yuan

Cross-Modal Transferable Adversarial Attacks from Images to Videos. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, June, 2022
Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, June, 2022
Lingchen Meng, Hengduo Li, Bor-Chun Chen, Shiyi Lan, Zuxuan Wu, Yu-Gang Jiang, Ser-Nam Lim

ObjectFormer for Image Manipulation Detection and Localization. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, June, 2022
Junke Wang, Zuxuan Wu, Jingjing Chen, Xintong Han, Abhinav Shrivastava, Ser-Nam Lim, Yu-Gang Jiang

Flag: Adversarial data augmentation for graph neural networks. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, June, 2022
Kezhi Kong, Guohao Li, Mucong Ding, Zuxuan Wu, Chen Zhu, Bernard Ghanem, Gavin Taylor, Tom Goldstein

Boosting the Transferability of Video Adversarial Examples via Temporal Translation. [pdf]
The AAAI Conference on Artificial Intelligence (AAAI), Virtual, Feb., 2022
Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

Attacking Video Recognition Models with Bullet-Screen Comments. [pdf]
The AAAI Conference on Artificial Intelligence (AAAI), Virtual, Feb., 2022
Kaichen, Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

Towards transferable adversarial attacks on vision transformers. [pdf]
The AAAI Conference on Artificial Intelligence (AAAI), Virtual, Feb., 2022
Zhipeng Wei, Jingjing Chen, Micah Goldblum, Zuxuan Wu, Tom Goldstein, Yu-Gang Jiang

Rethinking Pseudo Labels for Semi-Supervised Object Detection. [pdf]
The AAAI Conference on Artificial Intelligence (AAAI), Virtual, Feb., 2022
Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry Davis

Encoding Robustness to Image Style via Adversarial Feature Perturbations. [pdf]
Advances in Neural Information Processing Systems (NeurIPS), Virtual, Dec., 2021.
Manli Shu, Zuxuan Wu, Micah Goldblum, Tom Goldstein

Deep Video Inpainting Detection. [pdf]
British Machine Vision Conference (BMVC), Virtual, Oct., 2021
Peng Zhou, Ning Yu, Zuxuan Wu, Larry Davis, Abhinav Shrivastava, Ser-Nam Lim

GTA: Global Temporal Attention for Video Action Understanding. [pdf]
British Machine Vision Conference (BMVC), Virtual, Oct., 2021
Bo He, Xitong Yang, Zuxuan Wu, Hao Chen, Ser-Nam Lim, Abhinav Shrivastava

VideoLT: Large-scale Long-tailed Video Recognition. [pdf]
International Conference on Computer Vision (ICCV), Virtual, Oct., 2021
Xing Zhang, Zuxuan Wu, Zejia Weng, Huazhu Fu, Jingjing Chen, Yu-Gang Jiang, Larry Davis

Exploring Visual Engagement Signals for Representation Learning. [pdf]
International Conference on Computer Vision (ICCV), Virtual, Oct., 2021
Menglin Jia, Zuxuan Wu, Austin Reiter, Claire Cardie, Serge Belongie, Ser-Nam Lim

2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, June, 2021
Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S. Davis

Intentonomy: a Dataset and Study towards Human Intent Understanding [pdf][code]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, June, 2021 (Oral)
Menglin Jia, Zuxuan Wu, Austin Reiter, Claire Cardie, Serge Belongie, Ser-Nam Lim

Efficient Object Embedding for Manipulated Image Retrieval [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, June, 2021
Bor-Chun Chen, Zuxuan Wu, Larry S. Davis, Ser-Nam Lim

Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors. [pdf][code]
European Conference on Computer Vision (ECCV), Virtual, August, 2020.
Zuxuan Wu, Ser-Nam Lim, Larry S. Davis, Tom Goldstein

Learning from Noisy Anchors for One-stage Object Detection. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, June, 2020
Hengduo Li, Zuxuan Wu, Chen Zhu, Caiming Xiong, Richard Socher, Larry S. Davis

LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition. [pdf][code]
Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, Dec., 2019.
Zuxuan Wu, Caiming Xiong, Yu-Gang Jiang, Larry S. Davis

FiNet: Compatible and Diverse Fashion Image Inpainting. [pdf]
International Conference on Computer Vision (ICCV), Seoul, Korea, Oct., 2019. (Oral)
Xintong Han, Zuxuan Wu, Weilin Huang, Matthew R. Scott, Larry S. Davis

ACE: Adapting to Changing Environments for Semantic Segmentation. [pdf]
International Conference on Computer Vision (ICCV), Seoul, Korea, Oct., 2019.
Zuxuan Wu, Xin Wang, Joseph E. Gonzalez, Tom Goldstein, Larry S. Davis

AdaFrame: Adaptive Frame Selection for Fast Video Recognition. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, June, 2019
Zuxuan Wu, Caiming Xiong, Chih-Yao Ma, Richard Socher, Larry S Davis

The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, June, 2019.
Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira

Visual Content Recognition by Exploiting Semantic Feature Map with Attention and Multi-task Learning.[pdf]
ACM Trans. Multimedia Comput. Commun (ACM TOMM), vol. 15, issue 1, pp. 6:1-6:22, 2019.
Rui-Wei Zhao, Qi Zhang, Zuxuan Wu, Jianguo Li, Yu-Gang Jiang

Self-Monitoring Navigation Agent via Auxiliary Progress Estimation. [pdf]
International Conference on Learning Representations (ICLR), New Orleans, USA, May, 2019.
Chih-Yao Ma, Jiasen Lu, Zuxuan Wu, Ghassan AlRegib, Zsolt Kira, Richard Socher, Caiming Xiong

DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation. [pdf][code]
European Conference on Computer Vision (ECCV), Munich, Germany, September, 2018.
Zuxuan Wu, Xintong Han, Yen-Liang Lin, Mustafa Gkhan Uzunbas, Tom Goldstein, Ser Nam Lim, Larry S. Davis

BlockDrop: Dynamic Inference Paths in Residual Networks. [pdf][code]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, June, 2018. (Spotlight)
Zuxuan Wu*, Tushar Nagarajan*, Abhishek Kumar, Steven Rennie, Larry S. Davis, Kristen Grauman, Rogerio Feris
(* denotes equal contribution)

VITON: An Image-based Virtual Try-on Network. [pdf][code]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, June, 2018. (Spotlight)
Xintong Han, Zuxuan Wu, Zhe Wu, Ruichi Yu, Larry S. Davis

Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks. [pdf]
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 40, Issue 2, pp. 352-364, 2018.
Yu-Gang Jiang, Zuxuan Wu, Jun Wang, Xiangyang Xue, Shih-Fu Chang
Fudan-Columbia Video Dataset (FCVID), one of the largest public Web video datasets with manual annotations.

Deep Learning for Video Classification and Video Captioning. [pdf]
In Frontiers of Multimedia Research, Shih-Fu Chang (Ed.), ACM Morgan & Claypool, New York, NY, USA, pp. 3-29, 2018
Zuxuan Wu, Ting Yao, Yanwei Fu, Yu-Gang Jiang

Surveying 100+ recent literatures on video classification and captioning with deep learning.

Weakly-Supervised Spatial Context Networks. [pdf]
arXiv preprint arXiv:1704.02998
Zuxuan Wu, Larry S. Davis, Leonid Sigal

Automatic Spatially-aware Fashion Concept Discovery. [pdf]
International Conference on Computer Vision (ICCV), Venice, Italy, Oct., 2017.
Xintong Han, Zuxuan Wu, Phoenix Huang, Xiao Zhang, Menglong Zhu, Yuan Li, Yang Zhao, Larry S. Davis

Learning Fashion Compatibility with Bidirectional LSTMs. [pdf]
ACM Multimedia (ACM MM), Mountain View, USA, Oct., 2017.
Xintong Han, Zuxuan Wu, Yu-Gang Jiang, Larry S. Davis

Learning Semantic Feature Map for Visual Content Recognition. [pdf]
ACM Multimedia (ACM MM), Mountain View, USA, Oct., 2017.
Rui-Wei Zhao, Zuxuan Wu, Jianguo Li, Yu-Gang Jiang

Harnessing Object and Scene Semantics for Large-Scale Video Understanding. [pdf]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, June, 2016. (Spotlight)
Zuxuan Wu, Yanwei Fu, Yu-Gang Jiang, Leonid Sigal

Featured in Tech2, ACM Technews

Multi-Stream Multi-Class Fusion of Deep Networks for Video Classification. [pdf]
ACM Multimedia (ACM MM), Amsterdam, the Netherlands, Oct., 2016. (Oral Paper)
Zuxuan Wu, Yu-Gang Jiang, Xi Wang, Hao Ye, Xiangyang Xue

Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification. [pdf]
ACM Multimedia (ACM MM), Brisbane, Australia, Oct., 2015. (Oral Paper)
Zuxuan Wu, Xi Wang, Yu-Gang Jiang, Hao Ye, Xiangyang Xue

Obtain 91.3% accuracy on the UCF-101 dataset.

Evaluating Two-Stream CNN for Video Classification. [pdf][motion CNN model]
ACM International Conference on Multimedia Retrieval (ICMR), Shanghai, China, June, 2015
Hao Ye, Zuxuan Wu, Rui-Wei Zhao, Xi Wang, Yu-Gang Jiang, Xiangyang Xue

Exploring Inter-feature and Inter-class Relationships with Deep Neural Networks for Video Classification. [pdf]
ACM Multimedia (ACM MM), Orlando, USA, Nov., 2014. (Oral Paper)
Zuxuan Wu, Yu-Gang Jiang, Jun Wang, Jian Pu, Xiangyang Xue

Honors

2017.12	Snap Inc. Fellowship
2016.08	Dean's Fellowship
2015.10	National Graduate Scholarship of China
2015.08	Google Excellent Student Award
2015.07	ACM Student Travel Grant
2014.10	National Graduate Scholarship of China
2014.08	ACM Student Travel Grant
2013.06	Shanghai Outstanding Graduates
2012.12	Shanghai Scholarship