Search results
This is Zhijian “James” Hou (侯智健). 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 ...
Zhijian Hou, Chong-Wah Ngo (2021). CONQUER: Contextual query-aware ranking for video corpus moment retrieval . Proceedings of the 29th ACM International Conference on Multimedia .
Conquer: Contextual query-aware ranking for video corpus moment retrieval. Z Hou, CW Ngo, WK Chan. Proceedings of the 29th ACM International Conference on Multimedia, 3900-3908. , 2021. 33. 2021....
Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, Wing Kwong Chan, Chong-Wah Ngo, Zheng Shou, Nan Duan: An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022.
Hou, Z., Pan, Y., Yao, T. & Ngo, C., Nov 2019, Proceedings of TRECVID 2019. National Institute of Standards and Technology (NIST), (TREC Video Retrieval Evaluation, TRECVID). Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper. Scopus citations 1.
Jun 19, 2023 · TL;DR: GroundNLQ won the first place at the Ego4D Natural Language Queries Challenge at CVPR23. Technically, we leverage a two-stage pre-training strategy to train egocentric feature extractors and the grounding model on video narrations, and further fine-tune the model on annotated data.
I am a skilled AI researcher with a Ph.D. in computer science and six years of experience in cutting-edge AI research. My expertise lies in computer vision and natural language processing, especially video retrieval, with a proven track record of 4 peer-reviewed papers and 5 workshop papers in top conferences.