H
Houqiang Li
Researcher at University of Science and Technology of China
Publications - 612
Citations - 17591
Houqiang Li is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Motion compensation. The author has an hindex of 57, co-authored 520 publications receiving 12325 citations. Previous affiliations of Houqiang Li include China University of Science and Technology & Nanjing Medical University.
Papers
More filters
Proceedings ArticleDOI
Occupancy-Map-Based Rate Distortion Optimization for Video-Based Point Cloud Compression
TL;DR: In this paper, the authors proposed to consider only the rate instead of the rate distortion cost for the unoccupied pixels during the distortion optimization process, which can achieve an average of 11:9% and 15:4% bitrate savings for the geometry and attribute, respectively.
Proceedings ArticleDOI
Mixed Gaussian-impulse video noise removal via temporal-spatial decomposition
TL;DR: A two-stage algorithm is developed to solve the mixed Gaussian-impulse noise removal task as a temporal-spatial decomposition problem, which amounts to a convex program.
Journal ArticleDOI
Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization
Qi Zhou,Houqiang Li,Jie Wang +2 more
TL;DR: An upper bound of the uncertainty is derived based on which an uncertainty-aware policy optimization algorithm that optimizes the policy conservatively to encourage performance improvement with high probability can significantly alleviate the overfitting of policy to inaccurate models.
Posted Content
Distortion Bounds for Source Broadcast Problems
Lei Yu,Houqiang Li,Weiping Li +2 more
TL;DR: An inner bound and several outer bounds on the admissible distortion region are derived, which respectively generalize and unify several existing bounds in the joint source-channel coding problem.
Journal ArticleDOI
MINet: Meta-Learning Instance Identifiers for Video Object Detection
TL;DR: In this article, a meta-learnt instance identifier network (MINet) is proposed to learn instance identifiers for instance association in a meta learning paradigm, which requires no auxiliary inputs or post-processing.