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
Parsing robustness in High Efficiency Video Coding - analysis and improvement
Bin Li,Xu Jizheng,Houqiang Li +2 more
TL;DR: Experimental results show that the proposed methods can solve the parsing problem in HEVC with a marginal influence on the coding performance and provide significant improvements for the decoded video when there are errors.
Posted Content
Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
Longhui Wei,Lingxi Xie,Jianzhong He,Jianlong Chang,Xiaopeng Zhang,Wengang Zhou,Houqiang Li,Qi Tian +7 more
TL;DR: A new algorithm named Supervised Contrastive Adjustment in Neighborhood (SCAN) is presented that maximally prevents the semantic guidance from damaging the appearance feature embedding and reveals that semantic labels are useful in assisting self-supervised methods, opening a new direction for the community.
Posted Content
Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
TL;DR: Wang et al. as discussed by the authors designed a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
Journal ArticleDOI
Distributed Lossless Coding Techniques for Hyperspectral Images
TL;DR: Experimental results on the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data demonstrate that the proposed scheme is able to achieve competitive compression performance comparing with the-state-of-the-art 3D schemes, including existing distributed source coding (DSC) schemes.
Posted Content
In Defense of the Classification Loss for Person Re-Identification
TL;DR: Zhang et al. as discussed by the authors proposed a person re-id framework with channel grouping and multi-branch strategy, which divides global features into multiple channel groups and learns the discriminative channel group features by multibranch classification layers.