Zhijian "James" Hou

Zhijian "James" Hou

Research-related job hunting

City University of Hong Kong

Biography

Hello! This is Zhijian “James” Hou (δΎ―ζ™Ίε₯). I obtained a Ph.D. degree in Computer Science Department at City University of Hong Kong, advised by Prof. Chong-Wah Ngo and Prof. Wing-Kwong Chan. Prior to CityU, I obtained my bachelor’s degree from Shandong University in China, with guidance from Prof. Liqiang Nie.

I do research at the intersection of video and language. I am broadly interested in video analysis and synthesis using natural language as the interface. During the graduate study, I delved into the task of temporal sentence grounding in videos, which aims to localize video segments that correspond semantically to natural language queries in untrimmed videos.

Interests
  • Video and Language
  • Long-form Video Understanding
  • Multi-modal Foundation Models
Education
  • PhD in Computer Science, 2023

    City University of Hong Kong

  • BSc in Computer Science, 2018

    Shandong University, China

News

Publications

(2023). CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

Cite DOI URL code

(2023). (Un) likelihood Training for Interpretable Embedding. ACM Transactions on Information Systems.

Cite

(2023). Groundnlq@ ego4d natural language queries challenge 2023. arXiv preprint arXiv:2306.15255.

Cite code

(2022). An efficient coarse-to-fine alignment framework@ ego4d natural language queries challenge 2022. arXiv preprint arXiv:2211.08776.

Cite code

(2022). Reinforcement learning-based interactive video search. International Conference on Multimedia Modeling.

Cite

Experience

 
 
 
 
 
City University of Hong Kong
Graduate Researcher
September 2018 – October 2023 Hong Kong
  • Designed algorithms for spatial-temporal action localization in surveillance videos.
  • Developed techniques for language grounding in multi-modal video content.
  • Innovated on algorithms for ad-hoc video retrieval.

Advisor: Prof. Chong-Wah Ngo and Prof. Wing-Kwong Chan

 
 
 
 
 
Microsoft Research Asia
Research Intern
April 2022 – June 2023 Beijing
  • Designed algorithms for language grounding in long-form (egocentric) videos.

Advisor: Senior Researcher, Lei Ji

 
 
 
 
 
Shandong University
Research Assistant
September 2017 – June 2018 China
  • Developed algorithms for user recommendation in online question answering platforms.

Advisor: Prof. Liqiang Nie