Qingming Huang
Chinese Academy of Sciences
675 Papers
3.6K Citations
Qingming Huang is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Computer science & Feature (computer vision). The author has an hindex of 62, co-authored 603 publications. Previous affiliations of Qingming Huang include Association for Computing Machinery & Intel.
Chat about Author
Papers
Set-label modeling and deep metric learning on person re-identification
TL;DR: A novel method named Set-Label Model (SLM) is proposed to improve the performance of person re-identification under the multi-shot setting and a deep non-linear metric learning (DeepML) approach is developed based on Neighborhood Component Analysis and Deep Belief Network.
Structure-Aware Local Sparse Coding for Visual Tracking
TL;DR: A structure-aware local sparse coding algorithm is proposed, which encodes a target candidate using templates with both global and local sparsity constraints, and an effective template update scheme is designed to alleviate the issues with tracking drifts.
Naming faces in broadcast news video by image google
Chunxi Liu,Shuqiang Jiang,Qingming Huang +2 more
- 26 Oct 2008
TL;DR: A novel approach to name the faces by exploring extra knowledge obtained from image google is presented, which assumes that the faces of those important persons will turn out many times in the web images and could be retrieved from imageGoogle easily.
Online Asymmetric Metric Learning With Multi-Layer Similarity Aggregation for Cross-Modal Retrieval
TL;DR: A new asymmetric image–text similarity formulation which aggregates the layer-wise visual–textual similarities parameterized by different bilinear parameter matrices to learn the metric that can well reflect the cross-modal semantic relation.
A new method to calculate the camera focusing area and player position on playfield in soccer video
Yang Liu,Qingming Huang,Qixiang Ye,Wen Gao +3 more
- 01 Jul 2005
TL;DR: An algorithm to cope with the former problem, i.e. to compute players' position on court and the homographies between image and playfield, and the result is encouraging.