Scholar
Quoc-Huy Tran
Google Scholar ID: 8JbK0V8AAAAJ
Retrocausal, Inc.
Video Understanding
Action Recognition
3D Perception
Autonomous Driving
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,717
H-index
18
i10-index
26
Publications
20
Co-authors
31
list available
Publications
8 items
Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization
2026
Cited
0
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
Co-authors
14 total
Zeeshan Zia
Retrocausal, Inc.
Manmohan Chandraker
Professor, University of California, San Diego
Sanjay Haresh
Qualcomm AI Research
Pan Ji
Ph.D., ex Tencent XR Vision Labs
Sateesh Kumar
PhD student at The University of Texas at Austin.
David Suter
Prof. Edith Cowan University
Tat-Jun Chin
SmartSat CRC Professorial Chair of Sentient Satellites, The University of Adelaide
Xiang Yu
Amazon
