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
Journal ArticleDOI
SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding
TL;DR: In this article , the hand pose is regarded as a visual token, which is derived from an off-the-shelf detector and each visual token is embedded with gesture state and spatial-temporal position encoding.
Proceedings ArticleDOI
Video frame interpolation using 3-D total variation regularized completion
TL;DR: A novel 3-D total variation regularized completion model is proposed, which exploits both temporal and spatial smoothness among video frames, and demonstrates its superior performance compared to several classical methods.
Journal ArticleDOI
Deep Unrestricted Document Image Rectification
TL;DR: Li et al. as discussed by the authors presented DocTr++, a unified framework for document image rectification, without any restrictions on the input distorted images, which adopted a hierarchical encoder-decoder structure for multi-scale representation extraction and parsing.
Journal ArticleDOI
Exploiting weak mask representation with convolutional neural networks for accurate object tracking
TL;DR: A semantic segmentation model by online fine-tuning with augmented samples in the initial frame to uncover the target in the following frames is adapted, and a bounding box approximation method by considering temporal consistency is proposed.
Journal ArticleDOI
Similar Reference Image Quality Assessment: A New Database and A Trial with Local Feature Matching
TL;DR: This paper proposes an IQA framework based on local feature matching, which can help to identify the similar regions and structures in similar reference images and computed only from these similar regions to predict the final image quality score.