Chaoxi Xu

Institute of Computing Technology, Chinese Academy of Sciences

Engineer • 2020.7 — Present

I work as an algorithm engineer in the Media Synthesis & Forensics Lab. As a core member of the team, I participated in the development of media forgery detection system and equipment, which was recognized with the 2022 World Leading Internet Scientific and Technology Achievements award. My current work focus is on several areas as following, and you are welcome to visit our WeChat mini-program to learn more.

• Fake news detection
• Speech synthesis and forensics
• Pre-trained large model generated text detection

Vistel

Algorithm Engineer Intern • 2018.11 — 2019.8

I has been working on the automatic grading algorithm of nuclear cataract opacities, and proposed a fully deep learning method for grading. The research paper were early accepted by the top conference on medical image analysis (MICCAI 2019).

School of Information, Renmin University of China

Computer Application Technology, Master • 2017 — 2020

School of Information, Renmin University of China

Computer Science and Technology, Bachelor • 2013 — 2017

[9] Jianfeng Dong, Xirong Li, Chaoxi Xu, Xun Yang, Gang Yang, Xun Wang, Meng Wang. Dual Encoding for Video Retrieval by Text. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 (CCF A, IF=24.314)

[8] Xirong Li, Fangming Zhou, Chaoxi Xu, Jiaqi Ji, Gang Yang. SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries. IEEE Transactions on Multimedia (TMM), 2021 (CCF B, IF=8.182)

[7] Jakub Lokoč, Tomáš Souček, Patrik Veselý, František Mejzlík, Jiaqi Ji, Chaoxi Xu, Xirong Li. A W2VV++ Case Study with Automated and Interactive Text-to-Video Retrieval. ACM Multimedia (ACMMM), 2020 (CCF A)

[6] Jianfeng Dong, Xun Wang, Leimin Zhang, Chaoxi Xu, Gang Yang, Xirong Li. Feature Re-Learning with Data Augmentation for Video Relevance Prediction. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2019 (CCF A, IF=9.235)

[5] Xirong Li, Chaoxi Xu, Gang Yang, Zhineng Chen, Jianfeng Dong. W2VV++: Fully Deep Learning for Ad-hoc Video Search. ACM Multimedia (ACMMM), 2019 (CCF-A)

[4] Chaoxi Xu, Xiangjia Zhu, Wenwen He, Yi Lu, Xixi He, Zongjiang Shang, Jun Wu, Keke Zhang, Yinglei Zhang, Xianfang Rong, Zhennan Zhao, Lei Cai, Dayong Ding, Xirong Li. Fully Deep Learning for Slit-lamp Photo based Nuclear Cataract Grading. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2019 (CCF B, early accept)

[3] Jianfeng Dong, Xirong Li, Chaoxi Xu, Shouling Ji, Yuan He, Gang Yang, Xun Wang. Dual encoding for zero-example video retrieval. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (CCF A)

[2] Xirong Li, Chaoxi Xu, Xiaoxu Wang, Weiyu Lan, Zhengxiong Jia, Gang Yang, Jieping Xu. COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval. IEEE Transactions on Multimedia (TMM), 2019 (CCF B, IF=8.182)

[1] Jianfeng Dong, Xirong Li, Chaoxi Xu, Gang Yang, Xun Wang. Feature re-learning with data augmentation for content-based video recommendation. ACM Multimedia (ACMMM), 2018 (Grand challenge paper)