Henghui Ding

Biography

Henghui Ding is currently a Presidential Postdoctoral Fellow (PPF, Principal Investigator) at Nanyang Technological University (NTU) in Singapore. Prior to that, he was a Postdoctoral Researcher at Computer Vision Lab of ETH Zürich in Switzerland and a Research Scientist at ByteDance AI Lab in Singapore. He received the Ph.D. degree (winner of Best Thesis Award) from NTU in 2020, and the B.E. degree from Xi'an Jiaotong University (XJTU), Xi'an China, in 2016. His research interests broadly includes machine learning and computer vision. Specifically, he focuses on scene understanding (e.g., image/video segmentation, detection), multi-modal learning (e.g., vision-language), low-shot learning, and human–computer interaction. He serves as a Senior Program Committee (SPC) member of AAAI'22 and IJCAI'23, and an Associate Editor of IET Computer Vision.

News

Selected Publications [Google Scholar]

	MOSE: A New Dataset for Video Object Segmentation in Complex Scenes Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Philip H.S. Torr, Song Bai MOSE Dataset Report, 2023. A benchmark dataset of coMplex video Object SEgmentation: 🔥Project Page🔥
	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation Henghui Ding, Chang Liu, Suchen Wang, Xudong Jiang IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.
	Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation Henghui Ding, Hui Zhang, Xudong Jiang Pattern Recognition (PR), 2023.
	Instance-Specific Feature Propagation for Referring Segmentation Chang Liu, Xudong Jiang, Henghui Ding IEEE Transactions on Multimedia (TMM), 2022. ( Corresponding Authorship)
	Spatial Feature Mapping for 6DoF Object Pose Estimation Jianhan Mei, Xudong Jiang, Henghui Ding Pattern Recongnition (PR), 2022. ( Corresponding Authorship)
	Distilling Knowledge from Object Classification to Aesthetics Assessment Jingwen Hou*, Henghui Ding*, Weisi Lin, Weide Liu, Yuming Fang IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022. (* Equal contribution)
	Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives Xinke Li*, Henghui Ding*, Zekun Tong, Yuwei Wu, Yeow Meng Chee IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (* Equal contribution)
	Coarse-to-Fine Feature Mining for Video Semantic Segmentation Guolei Sun, Yun Liu, Henghui Ding, Thomas Probst, Luc Van Gool IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
	Deep Interactive Image Matting with Feature Propagation Henghui Ding, Hui Zhang, Chang Liu, Xudong Jiang IEEE Transactions on Image Processing (TIP), 2022.
	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)
	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.
	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.
	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)
	Towards Enhancing Fine-grained Details for Image Matting Chang Liu, Henghui Ding, Xudong Jiang IEEE 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

• Associate Editor, IET Computer Vision, 2022-Present.
• Senior Program Committee (SPC): AAAI'22, IJCAI'23.
• Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, WACV, BMVC, ICRA, ICIP, etc.
• Journal Reviewer: TPAMI, IJCV, 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