I am a Senior Applied Scientist at Adobe Firefly. Before that I worked at Amazon AGI Foundations and AWS AI Labs where I was part of the team that launched Titan Image Generator. I received my PhD at University of Maryland, College Park in 2020, advised by Professor Rama Chellappa. I received my Master degree from Shanghai Jiao Tong University and Bachelor degree from Dalian University of Technology. I interned at Waymo, Adobe Research, Palo Alto Research Center, and Siemens Healthineers during my PhD. I work on foundation models for generative AI including auto-regressive modeling for vision-language multi-modality learning and text-to-image/video generation and editing.
News
[Nov. 2023] Titan Image Generator is launched in AWS re:Invent 2023! (Amazon Science Blog, Press coverage: TC, theverge, gizmodo, venturebeat)
[Feb. 2023] PlolyFormer is accepted by CVPR 2023.
Publications
Xi Chen, Zhifei Zhang, He Zhang, Yuqian Zhou, Soo Ye Kim, Qing Liu, Yijun Li, Jianming Zhang, Nanxuan Zhao, Yilin Wang, Hui Ding, Zhe Lin, Hengshuang Zhao
Preprint, 2024
[paper][project page]
PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
Jiang Liu*, Hui Ding*, Zhaowei Cai, Yuting Zhang, Ravi Kumar Satzoda, Vijay Mahadevan, R. Manmatha, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. (* Equal Contribution)
Learning Self-Consistency for Deepfake Detection
Tianchen Zhao, Xiang Xu, Mingze Xu, Hui Ding, Yuanjun Xiong, and Wei Xia International Conference on Computer Vision (ICCV), 2021. (Oral)
[paper]
Occlusion-Adaptive Deep Network for Robust Facial Expression Recognition
Hui Ding, Peng Zhou and Rama Chellappa International Joint Conference on Biometrics (IJCB), 2020. (Oral)
[paper]
ExprGAN: Facial Expression Editing with Controllable Expression Intensity
Hui Ding, Kumar Sricharan and Rama Chellappa Association for the Advancement of Artificial Intelligence (AAAI), 2018. (Oral)
A Deep Cascade Network for Unaligned Face Attribute Classification
Hui Ding, Hao Zhou, Shaohua Kevin Zhou and Rama Chellappa Association for the Advancement of Artificial Intelligence (AAAI), 2018. (Spotlight)
[paper]
Facenet2expnet: Regularizing a deep face recognition net for expression recognition
Hui Ding, Shaohua Kevin Zhou and Rama Chellappa, IEEE International Conference on Automatic Face Gesture Recognition (FG), 2017. [paper][model][poster]
Hui Ding, Chen He, and Lingge Jiang, “Performance Analysis of Fixed Gain MIMO Relay Systems in the Presence of Co-Channel Interference”, IEEE Commun. Lett., vol. 16, no. 7, pp. 1133-1136, Jul. 2012.
Hui Ding, Chen He, and Lingge Jiang, “Performance of Multi-antenna Systems with Fixed Gain AF Relay in the Presence of Co-Channel Interference”, 2012 IEEE International Conference on Communications (ICC), pp. 5538-6642. Ph.D. Thesis [presentation]
Service
- Journal Reviewer: TPAMI, IJCV, TIP, TMM
- Conference Reviewer: CVPR, ICCV, ECCV