Scholar
Jinlong Li
Google Scholar ID: hpEAymEAAAAJ
SZU, Meituan, Unitn
Citations & Impact
Citations
1,818
H-index
7
i10-index
6
Publications
11
Co-authors
13
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published papers:
- - CUA-O3D and FisherTune accepted by CVPR 2025
- - LESS accepted by NeurIPS 2024
- - RKP accepted by ACM MM 2024
- - 3DSS-VLG accepted by ECCV 2024
- - One paper accepted by Neurocomputing 2023
- - ESOL accepted by NeurIPS 2022
- - PPL accepted by TMM 2022
- Preprints:
- - Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation
- - Feature Compression for Vision-Language Models: Query-Driven Encoding in Bandwidth-Constrained Environments
- - When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding
- - Enhancing Robustness of Vision-Language Models through Orthogonality Learning and self-Regularization
Research Experience
- Worked as a computer vision scientist at MeiTuan, collaborating closely with Dr. Lin Ma and Dr. Zequn Jie, focusing on 2D/3D/4D Label-Efficient Detection and Segmentation.
Education
- Obtained dual B.Sc (main Applied Physics) and M.Sc (Computer Science) degrees from Shenzhen University. Currently pursuing a PhD at the Multimedia and Human Understanding Group (MHUG) at the University of Trento, supervised by Prof. Nicu Sebe.
Background
- Research interests include Computer Vision and Deep Learning, particularly in Label-Efficient Learning, Multi-Modal Perception and Reasoning, Spatial Foundation Models, and Generative Models. Currently a PhD student at the Multimedia and Human Understanding Group (MHUG), supervised by Prof. Nicu Sebe.
Miscellany
- Personal motto: Pushing a long-termist, strike the tough yet right things.
