Scholar

Ding Guodong

Google Scholar ID: PqlGbTYAAAAJ

National University of Singapore

Video Understanding

Citations & Impact

All-time

Citations

446

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

19 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

1. Conference paper: Condensing Action Segmentation Datasets via Generative Network Inversion, CVPR 2025.
2. Conference paper: OnlineTAS: An Online Baseline for Temporal Action Segmentation, NeurIPS 2024.
3. Conference paper: Ordering Mistake Detection in Assembly Tasks, CVPR Workshop 2024.
4. Conference paper: Coherent Temporal Synthesis for Incremental Action Segmentation, CVPR 2024.
5. Conference paper: Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation, ECCV 2022.
6. Conference paper: Dispersion-based Clustering for Unsupervised Person Re-identification, BMVC 2019.
7. Conference paper: Center based Pseudo-labeling for Semi-supervised Person Re-identification, ICME Workshops 2018.
8. Journal article: Temporal Action Segmentation: An Analysis of Modern Techniques, TPAMI 2023.
9. Journal article: Temporal Action Segmentation with High-level Complex Activity Labels, IEEE Transactions on Multimedia 2022.

Research Experience

1. Senior Research Fellow (Oct., 23 - Present), School of Computing (SoC), National University of Singapore, Singapore.
2. Research Fellow (Oct., 20 - Oct., 23), School of Computing (SoC), National University of Singapore, Singapore.
3. Research Intern (June, 19 - Sept., 19), China QCT MM R&D, Qualcomm Shanghai, China.
4. Visiting Scholar (Feb., 17 - Oct., 17), Australian National University, Australia.
5. Research Assistant (Nov., 15 - Feb., 17), The Hong Kong Polytechnic University, Hong Kong, China.

Education

Background

Research Interest: Understanding human actions in long-range, multi-step video sequences, particularly temporal action segmentation. Recently, his work has expanded to explore efficient understanding of procedural videos in continual and online settings.

Miscellany