Henghui Ding's Homepage

Biography

Henghui Ding is currently a Postdoctoral Researcher at Computer Vision Lab of ETH Zürich in Switzerland, working with Prof. Fisher Yu. He was a Research Scientist at ByteDance AI Lab in Singapore. He received the Ph.D. degree (winner of Best Thesis Award) from Nanyang Technological University (NTU), Singapore, advised by Prof. Xudong Jiang, and Prof. Gang Wang. Prior to that, he received the B.E. degree from Xi'an Jiaotong University (XJTU), Xi'an, China. His research interests include computer vision, language, machine learning, with special emphasis on high-level image/video recognition and pixel-level scene understanding.
If you are interested in joining/visitng (or remotely collaborating with) our group at ETH, please do not hesitate to drop me an email with your resume. We will usually reply within a week if we have a suitable position.

henghui.ding@vision.ee.ethz.ch

Selected Publications [Google Scholar]

	Directed Graph Contrastive Learning Zekun Tong, Yuxuan Liang, Henghui Ding^†, Yongxing Dai, Xinke Li, Changhu Wang Advances in Neural Information Processing Systems (NeurIPS), 2021. († Corresponding Authorship)
	Adaptive Data Augmentation on Temporal Graphs Yiwei Wang^#, Yujun Cai, Yuxuan Liang, Henghui Ding, Changhu Wang, Siddharth Bhatia, Bryan Hooi Advances in Neural Information Processing Systems (NeurIPS), 2021. (# Henghui's Intern at ByteDance AI Lab)
	Vision-Language Transformer and Query Generation for Referring Segmentation Henghui Ding, Chang Liu, Suchen Wang, Xudong Jiang IEEE International Conference on Computer Vision (ICCV), 2021. (* Equal contribution)
	Interaction via Bi-directional Graph of Semantic Region Affinity for Scene Parsing Henghui Ding, Hui Zhang, Jun Liu, Jiaxin Li, Zijian Feng, Xudong Jiang IEEE International Conference on Computer Vision (ICCV), 2021.
	Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning Chi Zhang^#, Henghui Ding, Guosheng Lin, Ruibo Li, Changhu Wang, Chunhua Shen IEEE International Conference on Computer Vision (ICCV), 2021. (# Henghui's Intern at ByteDance AI Lab)
	Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation Hui Zhang, Henghui Ding^† IEEE International Conference on Computer Vision (ICCV), 2021. († Corresponding Authorship)
	Recovering the Unbiased Scene Graphs from the Biased Ones Meng-Jiun Chiou^#, Henghui Ding, Hanshu Yan, Changhu Wang, Roger Zimmermann, Jiashi Feng ACM International Conference on Multimedia, 2021. (# Henghui's Intern at ByteDance AI Lab)
	Towards Enhancing Fine-grained Details for Image Matting Chang Liu, Henghui Ding^†, Xudong Jiang IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021. († Corresponding Authorship)
	PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click Henghui Ding, Scott Cohen, Brian Price, Xudong Jiang European Conference on Computer Vision (ECCV), 2020. Spotlight presentation, Acceptance Rate 5.3%. Work done when intern at Adobe Research
	Semantic Segmentation with Context Encoding and Multi-Path Decoding Henghui Ding, Xudong Jiang, Bing Shuai, Ai Qun Liu, Gang Wang IEEE Transactions on Image Processing (TIP), 2020.
	Feature Boosting Network For 3D Pose Estimation Jun Liu, Henghui Ding, Amir Shahroudy, Ling-Yu Duan, Xudong Jiang, Gang Wang, Alex C. Kot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020.
	Toward Achieving Robust High-level and Low-level Scene Parsing Henghui Ding, Bing Shuai, Ting Liu, Gang Wang, Xudong Jiang IEEE Transactions on Image Processing (TIP), 2019. (* Equal contribution)
	Boundary-Aware Feature Propagation for Scene Segmentation Henghui Ding, Xudong Jiang, Ai Qun Liu, Nadia Magnenat Thalmann, Gang Wang IEEE International Conference on Computer Vision (ICCV), 2019.
	Semantic Correlation Promoted Shape-Variant Context for Segmentation Henghui Ding, Xudong Jiang, Bing Shuai, Ai Qun Liu, Gang Wang IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. Oral presentation, Acceptance Rate 5.6%.
	Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation Henghui Ding, Xudong Jiang, Bing Shuai, Ai Qun Liu, Gang Wang IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. Oral presentation, Acceptance Rate 2.1%.

Activities

Senior Program Committee: AAAI'22.
Conference Reviewer: NeurIPS'21&20, CVPR'22&21&20&19, ICCV'21&19, ICML'21, ICLR'22&21, AAAI'21&20, WACV'21, ECCV'20, BMVC'20, ICIP'19&17, etc.
Journal Reviewer: TPAMI, TIP, TMI, TNNLS, TMM, TCSVT, PR, Neurocomputing, SPL, etc.
Internship: Adobe Research, San José, USA.

Patents

US Patent App. 16/839,209, 2021, Integrated Interactive Image Segmentation.

Teaching

Semester 2, 2018-2019, E2010L/IM2004: Signals&Systems, NTU
Semester 2, 2018-2019, E2004: Digital Electronics, NTU
Semester 1, 2018-2019, EE4717: Web Application Design, NTU

Henghui Ding

Dr.

Biography

Selected Publications [Google Scholar]

Directed Graph Contrastive Learning

Adaptive Data Augmentation on Temporal Graphs

Vision-Language Transformer and Query Generation for Referring Segmentation

Interaction via Bi-directional Graph of Semantic Region Affinity for Scene Parsing

Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning

Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation

Recovering the Unbiased Scene Graphs from the Biased Ones

Towards Enhancing Fine-grained Details for Image Matting

PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click

Semantic Segmentation with Context Encoding and Multi-Path Decoding

Feature Boosting Network For 3D Pose Estimation

Toward Achieving Robust High-level and Low-level Scene Parsing

Boundary-Aware Feature Propagation for Scene Segmentation

Semantic Correlation Promoted Shape-Variant Context for Segmentation

Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation

Activities

Patents

Teaching