About Me [中文]
- I’m a 3rd-year Ph.D. student in Computer Science at the Information School at the Renmin University of China. And I have been advised by Prof. Xirong Li from 2019 to now. I received my B.S. and M.E. degrees from Chongqing University of Posts and Telecommunications, Chongqing, China, in 2016 and 2019, respectively.
- My research interests mainly focus on cross-modal computing, to be specific, image/video caption, text-to-video retrieval, and attack on cross-modal retrieval. I am mainly involved in an international leading benchmark evaluation for video retrieval by text, named TRECVID Ad-hoc Video Search, which has been funded by NIST. In addition, I have been paying more attention to how to use large-scale pre-trained visual-language models to achieve better performance in those downstream tasks recently.
- Contact me: caz@ruc.edu.cn or jewelchen229@gmail.com
Publications
- Fan Hu*, Aozhu Chen*, Ziyue Wang*, Fangming Zhou, Xirong Li.
Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval. ECCV, 2022.
- Ziyue Wang*, Aozhu Chen*, Fan Hu, Xirong Li.
Learn to Understand Negation in Video Retrieval. ACMMM, 2022.
- Aozhu Chen*, Fan Hu*, Zihan Wang, Fangming Zhou, Xirong Li.
What Matters for Ad-hoc Video Search? A Large-scale Evaluation on TRECVID. ViRal’21@ICCV 2021, 2021.
- Chengbo Dong, Xinru Chen, Aozhu Chen, Fan Hu, Zihan Wang, Xirong Li.
Multi-Level Visual Representation with Semantic-Reinforced Learning for Video Captioning. ACM MM(Grand Challenge Track), 2021.
- Aozhu Chen, Xinyi Huang, Hailan Lin, Xirong Li.
Towards Annotation-Free Evaluation of Cross-Lingual Image Captioning. ACM MM Asia, 2020.
- MengZhou, Xianhua Zeng, Aozhu Chen.
Deep Forest Hashing for Image Retrieval. Pattern Recognition, 2019.
- Xianhua Zeng,Aozhu Chen, MengZhou.
Color perception algorithm of medical images using density peak-based hierarchical clustering. Biomedical Signal Processing and Control, 2019.
- Zeng Xianhua, Chen Aozhu, He Shanshan.
Color Perception Algorithm of Medical Images Using Multi-features Fusion. Journal of Computer-Aided Design & Computer Graphics, 2018.
Competition experience
- MM’21 Grand Challenge: Pretraining for video captioning, top 3
- 2021 TREC Video Retrieval Evaluation (TRECVID) AVS, top 3
- 2020 TREC Video Retrieval Evaluation (TRECVID) AVS, top 2
Honor
National Scholarships 2018.