Quoc-Huy Tran
Scholar

Quoc-Huy Tran

Google Scholar ID: 8JbK0V8AAAAJ
Retrocausal, Inc.
Video UnderstandingAction Recognition3D PerceptionAutonomous Driving
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,717
 
H-index
18
 
i10-index
26
 
Publications
20
 
Co-authors
31
list available
Contact
No contact links provided.
Publications
7 items
Unsupervised Skeleton-Based Action Segmentation via Hierarchical Spatiotemporal Vector Quantization
2026
Cited
0
A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics
2026
Cited
0
Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport
2025
Cited
0
Joint Self-Supervised Video Alignment and Action Segmentation
2025
Cited
0
Video LLMs for Temporal Reasoning in Long Videos
arXiv.org · 2024
Cited
0
Permutation-Aware Activity Segmentation via Unsupervised Frame-to-Segment Alignment
IEEE Workshop/Winter Conference on Applications of Computer Vision · 2023
Cited
19
Learning by Aligning 2D Skeleton Sequences and Multi-modality Fusion
European Conference on Computer Vision · 2023
Cited
5
Resume (English only)
Co-authors
31 total
Zeeshan Zia
Zeeshan Zia
Retrocausal, Inc.
Manmohan Chandraker
Manmohan Chandraker
Professor, University of California, San Diego
Sanjay Haresh
Sanjay Haresh
Qualcomm AI Research
Pan Ji
Pan Ji
Ph.D., ex Tencent XR Vision Labs
Co-author 5
Co-author 5
Sateesh Kumar
Sateesh Kumar
PhD student at The University of Texas at Austin.
Co-author 7
Co-author 7
David Suter
David Suter
Prof. Edith Cowan University