About me
I completed my Ph.D. study (President PhD Fellowship Holder), supervised by Prof. Shuicheng Yan and Prof. Mike Shou, at Institute of Data Science of National University of Singapore. I also work closely with Dr. Xiangyu Xu, Prof. Huazhu Fu, and Prof. Jun Liu. My current research interests lie in AIGC (text-to-image/video/3D) and Multi-modal Large Language Models (MLLMs). My previous work is about (Privacy-Preserving) Action Recognition, Self-supervised Representation Learning, Person/Vehicle Re-identification and Facial Expression Recognition.
I am building a team (about 10 persons) conducting research on AIGC and Multi-modal Large Language Models (MLLMs). Full-time researchers, visiting students and remote cooperations are very welcome!
Internship: I worked as a research scientist intern at Sea AI Lab and Shanghai AI Lab.
Academic services: I am a regular reviwer for IEEE TPAMI, ICCV23, NeurIPS23, IEEE TNNLS, IEEE TIP and Neurocomputing.
I was a visiting scholar in VISLab supervised by Prof. Ziming Zhang at Worcester Polytechnic Institute from Nov. 2019 to Apr. 2021. Before that, I worked as a RA supervised by Prof. Dinggang Shen at UNC Chapel Hill from Aug. 2018 to Oct. 2019. I graduated with a Master degree from School of EECS at Peking University in Jul. 2018. And I received my Bachelor degree from School of EE of Xidian University in Jul. 2015.
Recent news
- [May 2024] I successfully pass my Ph.D. defense and receive my certificate!
- [Apr. 2024] My paper "Instant3D: Instant Text-to-3D Generation" is accepted by International Journal of Computer Vision.
- [Feb. 2024] I received many cooperation invitations from famous industrial institutes, like Gaorong Capital and Huawei after we proposed a novel fast text-to-3D generation paradigm in our manuscript "Instant3D: Instant Text-to-3D Generation".
- [Jan. 2024] I am very pleased to give an invited talk, hosted by Prof. Hehe Fan, about 3D AIGC at School of Computer Science, Zhejiang University, Hangzhou.
- [Nov. 2023] My paper "EDR-FER: Discriminative and Robust Representation Learning for Facial Expression Recognition" is accepted by IEEE Transactions on Multimedia.
- [Oct. 2023] My paper "Exploiting Multi-view Part-wise Correlation via an Efficient Transformer for Vehicle Re-Identification" published on IEEE Transactions on Multimedia has been selected as ESI Highly Cited Papers for several times.
- [Apr. 2023] Our paper "FakePoI: A Large-scale Fake Person of Interest Video Detection Benchmark and a Strong Baseline" is accepted by IEEE Transactions on CSVT.
- [Jun. 2022] I am very pleased to give an invited online talk about Facial Expression Recognition at School of Science, Harbin Institute of Technology, Shenzhen.
- [Dec. 2021] My paper "Exploiting Multi-view Part-wise Correlation via an Efficient Transformer for Vehicle Re-Identification" is accepted by IEEE Transactions on Multimedia.
- [Jul. 2021] My paper "Self-supervised Geometric Features Discovery with Interpretable Attention for Vehicle Re-Identification and Beyond" is accepted by ICCV 2021 as a poster paper!
- [Apr. 2021] I complete my RA work at WPI!
- [Mar. 2021] I am awarded a four-year's PhD fellowship from National University of Singapore!
- [Oct. 2020] Two papers are accepted by ICPR 2020!
- [Aug. 2020] The video demo of my MTMC results on AI City Challenge 2020 is here!
- [Jul. 2020] Our paper on "3D LiDAR Odometry Estimation" has been accepted for presentation at the ACM Multimedia 2020 conference!
- [Jun. 2020] My results on AI City Challenge 2020 Track3: City-Scale Multi-Camera Vehicle Tracking rank 1st on the official leaderboard, which surpass the second ones by very large margins! Please check the screenshot of the ranking results!
- [Nov. 2019] I start my research work on person/vehicle re-identification at Worcester Polytechnic Institute in MA, US.
- [Aug. 2018] I start my RA work on medical image processing at UNC-Chapel Hill in NC, US.
- [Jul. 2018] I complete my Master study in Peking University successfully!
