Guodong Ding (Ph.D) 丁国栋 [CV] dinggd [at] comp.nus.edu [dot] sg Senior Research Fellow, School of Computing (SoC), National University of Singapore (NUS), AS6-04-11, 11 Computing Dr, Singapore, 117416

Research Interest

My current research interest is mainly understanding human actions in long range video sequences, i.e., Temporal Action Segmentation. I am also interested in learning with weaker forms of data supervisions such as, weakly-supervised and semi-supervised learning.

Updates

• [Oct., 23] One survey paper accpeted to TPAMI.

• [Dec., 22] One journal paper accpetd to TMM.

• [Oct., 22] We hosted an ATLAS tutorial in conjunction with ECCV22 on October 24!

• [Jul., 22] One conference paper accepted to ECCV2022.

• [Jun., 21] One journal paper accepted to SPL.

• [Oct., 20] I relocated to Singapore.

• [Dec., 19] I have successfully passed my PhD thesis defense.

• [Jul., 19] One conference paper accepted to BMVC2019.

• [May, 19] One journal paper accepted to TMM.

• [Feb., 19] One journal paper accepted to PRL.

Employment

• Research Fellow (Oct., 20 - Present), in School of Computing (SoC), National University of Singapore, Singapore.

• Engineering Intern (June, 19 - Sept., 19), in China QCT MM R&D, Qualcomm Shanghai, China.

Research Experiences

• Visiting Scholar (Feb., 17 - Oct., 17), in Australian National University, Australia.

• Research Assistant (Nov., 15 - Feb., 17), in the Hong Kong Polytechnic University, Hong Kong, China.

Education

• Ph.D. (Sept. 2013 - Jan. 2020), in Computer Science and Technology (081200),
  Nanjing University of Science and Technology, Nanjing
  Advisor: Prof. Zhenmin Tang and Prof. Guangyi Bai,
  博士论文: 面向不同监督条件下的行人再识别深度学习方法关键问题研究 [pdf],
  Dissertation: Research on Deep Learning based Person Re-identification Methods under Different Supervisions

• B.Eng. (Sept. 2009- June. 2013), in Computer Science and Technology (080605),
  Nanjing University of Science and Technology, Nanjing
  Advisor: Prof. Zhenmin Tang,
  本科论文: 基于内容的商品图像检索,
  Thesis: Content based Commodity Image Retrieval

Publications

Preprints & working papers

• G. Ding, F. Sener, S. Ma and A. Yao, Every Mistake Counts in Assembly, Arxiv paper 2023. [pdf]|[project page]|[annots]

• G. Ding*, S. Khan, Z. Tang, J. Zhang and F. Porikli, Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification, Arxiv paper 2019. [pdf]|[code]|[project page]

Journal articles

• G. Ding, F. Sener and A. Yao, Temporal Action Segmentation: An Analysis of Modern Techniques, IEEE Transactions on Pattern Analysis and Machine Intelligence 2023. [pdf]|[project page]|[resources]

• G. Ding and A. Yao, Temporal Action Segmentation with High-level Complex Activity Labels, IEEE Transcations on Multimedia 2022. [pdf]|[project page]

• Q. Yin, G. Wang, G. Ding, Q. Li, S. Gong and Z. Tang, Rapid Person Re-Identification via Sub-space Consistency Regularization, Neural Processing Letters 2022. [pdf]|[project page]

• Q. Yin, G. Wang, G. Ding, S. Gong and Z. Tang, Multi-View Label Prediction for Unsupervsied Person Re-identification, IEEE Singal Processing Letters 2021. [pdf]|[project page]

• G. Ding*, S. Zhang, S. Khan, Z. Tang, J. Zhang and F. Porikli, Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification, IEEE Transcations on Multimedia 2019. [pdf]|[project page]

• G. Ding*, S. Khan, Z. Tang, and F. Porikli, Feature Mask Network for Person Re-identification, Pattern Recognition Letters 2019. [pdf]|[project page]

Conference papers

• G. Ding and A. Yao, Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation, European Conference on Computer Vision 2022. [pdf]|[project page]

• G. Ding*, S. Khan, and Z. Tang, Dispersion based Clustering for Unsupervised Person Re-identification, British Machine Vision Conference 2019. [pdf]|[poster]|[project page]

• G. Ding*, S. Zhang, S. Khan, and Z. Tang, Center based Pseudo-labeling for Semi-supervised Person Re-identification, International Conference of Multimedia and Expo Workshops 2018. [pdf]|[slides]

(*: corresponding author)

Reviewer

Journal:

TPAMI, TMM, TIP, TOSN, TII

Conference:

CVPR, ECCV, ICCV, AAAI, BMVC, ICME
Co-organizer of ATLAS Tutorial on understanding actions in long untrimmed videos in conjunction with ECCV2022.

Collaborators

Prof. Angela Yao, School of Computing, National University of Singapore
Prof. Salman Khan, MBZUAI
Prof. Jian Zhang, University of Technology Sydney
Prof. Fatih Porikli, Australian National University and FutureWei, USA
Prof. Shanshan Zhang, Nanjing University of Science and Technology