X
Xiaokang Yang
Researcher at Shanghai Jiao Tong University
Publications - 548
Citations - 23068
Xiaokang Yang is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Image quality & Computer science. The author has an hindex of 68, co-authored 518 publications receiving 17663 citations. Previous affiliations of Xiaokang Yang include City University of Hong Kong & Institute for Infocomm Research Singapore.
Papers
More filters
Proceedings ArticleDOI
Hierarchical Convolutional Features for Visual Tracking
TL;DR: This paper adaptively learn correlation filters on each convolutional layer to encode the target appearance and hierarchically infer the maximum response of each layer to locate targets.
Proceedings ArticleDOI
Cross-scene crowd counting via deep convolutional neural networks
TL;DR: A deep convolutional neural network is proposed for crowd counting, and it is trained alternatively with two related learning objectives, crowd density and crowd count, to obtain better local optimum for both objectives.
Proceedings ArticleDOI
Long-term correlation tracking
TL;DR: This paper decomposes the task of tracking into translation and scale estimation of objects and shows that the correlation between temporal context considerably improves the accuracy and reliability for translation estimation, and it is effective to learn discriminative correlation filters from the most confident frames to estimate the scale change.
Journal ArticleDOI
Using free energy principle for blind image quality assessment
TL;DR: A new no-reference (NR) image quality assessment (IQA) metric is proposed using the recently revealed free-energy-based brain theory and classical human visual system (HVS)-inspired features to predict an image that the HVS perceives from a distorted image based on the free energy theory.
Journal ArticleDOI
Deep Multimodal Distance Metric Learning Using Click Constraints for Image Ranking
TL;DR: This paper develops a novel deep multimodal distance metric learning (Deep-MDML) method, which adopts a new ranking model to use multi-modal features, including click features and visual features in DML.