About Me

FullSizeRenderHui Ding, PhD
huidin@amazon.com

Google Scholar / LinkedIn

I am a Senior Applied Scientist at Amazon AGI Foundations. Before that I worked at 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.

 

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

Screen Shot 2023-02-16 at 2.27.00 PM
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)

[paper][project page]

 

pcl

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]

 

vis_web
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]

 

vis_web
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)
[paper][code][model][slides]

 

 

big_pic_for_aaai
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]

 

 

crop_ck

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