Embedded Files
I am a principal research scientist and research director at Tencent. My research interests focus on multimodal understanding, computational imaging and computer vision, with applications in generative AI, multimedia and e-commerce multimodal understanding, mobile photography and videography.
I received PhD degree from CASIA supervised by Prof. Changping Liu, simultaneously interned at Hanvon Technology for 5 years, and bachelor's degree from BUAA. Before joining Tencent again, I worked as a senior research scientist at Wechat AI , then a research leader in Megvii (Face++) under the supervision of Dr. Jian Sun for a period of time. Meanwhile, I have been briefly visiting Rose Lab in NTU, Singapore for a while.
I served as a conference reviewer for AAAI, MM, CVPR, ICCV, ECCV, BMVC. etc. and journal reviewer for TPAMI, TMM, etc.
News
News
2025.6: One paper is accepted by ICCV 2025.
2023.12: One paper is accepted by AAAI 2024.
2023.7: One paper is accepted by ICCV 2023.
2023.2: One paper is accepted by CVPR 2023 (spotlight).
2023.1: Our team won 13 first places in scene text detection and text recognition.
2022.12: Our team won second place in VCR(Visual Commonsense Reasoning).
2022.12: Our team won second place in Wechat Bigdada Challenge.
2022.12: Our team won first place in Robust Vision Challenge.
2022.9: Our team won 2 first places in video-text description and video-text retrieval of TRECVID.
2022.7: One paper is accepted by TMM.
2022.7: One paper is accepted by ECCV 2022.
2022.2: Three papers are accepted by CVPR 2022 (1 oral).
2022.2: Our team won first place in Middlebury and first place in ETH3D.
...
Page updated
Google Sites
Report abuse