Bowen Zhang
PhD student
Theoretical & Empirical Data Science (TEDS) Lab
University of Southern California
Email :zbwglory [at]

About Me (Resume)

I am a PhD student with Prof. Fei Sha in the TEDS lab of Department of Computer Science at University of Southern California.

Previously, I obtained my M.Eng. and B.Eng. degree from Tongji University. My advisor is Prof. Hanli Wang. I was a visiting student of Multimedia Research Center at Shenzhen Institute of Advanced Technology under the supervision of Prof. Yu Qiao.


  • Apr. 22, 2019 : ECCV 2018's code is released. Check it out!
  • Aug. 14, 2018 : One paper has been accepted by EMNLP 2018.
  • Aug. 14, 2018 : One paper has been accepted by ECCV 2018.
  • Jan. 9, 2018: The extension of CVPR'16 paper is accepted by IEEE TIP.
  • July 26, 2017: Our team (CUHK team) obtains the 2nd place for untrimmed video classification, trimmed video classification, and action localization at ActivityNet Challenge 2017. [Result]
  • March 21, 2017: I will join Prof. Fei Sha's group at University of Southern California 2017 Fall.
  • July 9, 2016: Project website for CVPR paper is online.
  • June 16, 2016: Our team obtains the 1st place for untrimmed video classification at ActivityNet Challenge 2016. [Result]
  • March 1, 2016: One CVPR'16 paper has been accepted.

Recent Publications (Full List) (Google Scholar)

Visual Storytelling via Predicting Anchor Word Embeddings in the Stories
Bowen Zhang, Hexiang Hu, and Fei Sha
ICCV 2019 Workshop on Closing the Loop Between Vision and Language, 2019.
[ Paper ]
Topic Augmented Generator for Abstractive Summarization
Melissa Ailem, Bowen Zhang, and Fei Sha
arxiv 1908.07026 (Short version is on BayLearn 2019).
[ Paper ]
A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images
Melissa Ailem, Bowen Zhang, Aurélien Bellet, Pascal Denis, and Fei Sha
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
[ Paper ]
Cross-Modal and Hierarchical Modeling of Video and Text
Bowen Zhang*, Hexiang Hu*, and Fei Sha
European Conference on Computer Vision (ECCV), 2018.
[ Paper ] [Project page] [Code]
Real-Time Action Recognition with Deeply-Transferred Motion Vector CNNs
Bowen Zhang, Limin Wang, Zhe Wang, Yu Qiao and Hanli Wang
IEEE Transaction on Image Processing (TIP), 2018. (Extension of CVPR'16)
[ Paper ]
Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition
Zhe Wang, Limin Wang, Yali Wang, Bowen Zhang, and Yu Qiao
IEEE Transaction on Image Processing (TIP), 2017.
[ Paper ] [ Code& Model ]
Real-time Action Recognition with Enhanced Motion Vector CNNs
Bowen Zhang, Limin Wang, Zhe Wang, Yu Qiao, and Hanli Wang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
Real-time action recogntion with high performance.
[ Paper ] [ Project page ]
CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
Yuanjun Xiong, Limin Wang, Zhe Wang, Bowen Zhang, Hang Song, Wei Li, Dahua Lin, Yu Qiao, Luc Van Gool, and Xiaoou Tang
ActivityNet Large Scale Activity Recognition Challenge, in conjuction with CVPR, 2016.
[ Paper ] [ Code ]



Limin Wang (ETH Zurich), Zhe Wang (UCI), Yandong Wen (CMU), Tong He (Adelaide), Sheng Guo (Malong), Kaipeng Zhang (NTU, Taiwan)

Last Updated on Dec. 2019

Published with GitHub Pages