About Me

Hi, there 👋. I am Zelong Zeng (曾泽龙 / 曽澤龍).

I’m currently a Researcher at SenseTime Japan (センスタイムジャパン), where I work on deep learning and computer vision related to autonomous driving technology. I received my PhD degree from the Graduate School of IST at the University of Tokyo in March 2023, advised by Prof. Shin’ichi Satoh. Before that, I received my Master’s degrees from the University of Tokyo in 2020 and the bachelor’s degree from Shandong University in 2016.

Research interest: Object detection / segmentation related to autonomous driving, image retrieval and metric learning. If you are seeking any form of academic cooperation or intership, please feel free to email me at zengzelong@sensetime.jp

🔥 News

2024.07: 🎉🎉 One our paper (anomaly segmentation in autonomous vehicles) is accpted to ECCV 2024.
2024.03: 🎉🎉 One our paper (metic learning) is accpted to Viusal Intelligence 2024.
2023.04: I join SenseTime Japan (センスタイムジャパン) as a AI Researcher in Tokyo.
2023.03: 🎉🎉 I successfully received my PhD degree from the University of Tokyo!
2023.03: I released the code (PLCD and OBD-SD) of my two papers in Github.

📝 Publications

ECCV 2024 Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes, Zelong Zeng, Kaname Tomite| Code Video
Visual Intelligence 2024 Improving deep metric learning via self-distillation and online batch diffusion process, Zelong Zeng, Fan Yang, Hong Liu, Shin’ichi Satoh, Visual Intelligence 2024 | Code
IEEE TMM 2022 Geo-localization via ground-to-satellite cross-view image retrieval, Zelong Zeng, Zheng Wang, Fan Yang, Shin’ichi Satoh, IEEE Transactions on Multimedia 2022 | Code
ACM-MM 2020 Progressive Domain Adaptation for Robot Vision Person Re-identification, Zijun Sha, Zelong Zeng (co-first author), Zheng Wang, Yoichi Natori, Yasuhiro Taniguchi, Shin’ichi Satoh, ACM Multimedia 2020 | Demo
IEEE TMM 2020 Illumination-adaptive person re-identification, Zelong Zeng, Zhixiang Wang, Zheng Wang, Shin’ichi Satoh, IEEE Transactions on Multimedia 2020

📄 Preprints

Preprint 2022 Improving Generalization of Metric Learning via Listwise Self-distillation, Zelong Zeng, Fan Yang, Zheng Wang, Shin’ichi Satoh | Code

📖 Educations

2020.04 - 2023.03, Ph.D in Information and Communication Engineering, The University of Tokyo, Japan
2018.04 - 2020.03, M.E in Information and Communication Engineering, The University of Tokyo, Japan
2012.09 - 2016.06, B.E, in Mechanical,Electrical & Information Engineering, Shandong University, China

💼 Experience

2021.04 - 2023.03, Research Assistant in Mercari R4D and RIISE, Japan
2021.04 - 2023.03, Research Assistant in The Graduate School of IST, The University of Tokyo, Japan
2020.02 - 2020.08, Research Intern in Honda R&D, Japan

📄 Services

PC Member/Reviewer: IEEE TPAMI, IEEE TNNLS, IEEE TGRS, ICMR 2022/2023/2024, ACCV 2022

Zelong Zeng