Y
Yap-Peng Tan
Researcher at Nanyang Technological University
Publications - 296
Citations - 9430
Yap-Peng Tan is an academic researcher from Nanyang Technological University. The author has contributed to research in topics: Facial recognition system & Feature extraction. The author has an hindex of 47, co-authored 290 publications receiving 8521 citations. Previous affiliations of Yap-Peng Tan include Fudan University & Intel.
Papers
More filters
Proceedings ArticleDOI
Joint Representative Selection and Feature Learning: A Semi-Supervised Approach
TL;DR: A joint optimization framework is proposed which alternately optimizes representative selection in the target data and (2) discriminative feature learning from both the source and the target for better representative selection.
Proceedings ArticleDOI
Performance Factors for Evaluating Color Filter Array Demosaicking Algorithms
TL;DR: A series of experiments have been conducted to examine and demonstrate the effects of three experimental settings-CFA arrangement, image size, and image luminance-on demosaicking performance.
Proceedings ArticleDOI
Estimating relative objective quality among images compressed from the same original
Gao Yang,Ci Wang,Yap-Peng Tan +2 more
TL;DR: This paper proposes to cross-check each image against the quantization constraints of another version and obtain a conservative estimation of the difference in mean squared error (ΔMSE), indicating the relative objective quality between these images.
Proceedings ArticleDOI
Efficient Video Clip Retrieval Using Index Structure
TL;DR: A new video clip retrieval algorithm is proposed in this paper to achieve high query efficiency by using restricted sliding window to construct candidate video clips and a new similarity measure which takes the temporal order among the video representations into account to improve the accuracy of query.
Journal ArticleDOI
Robust color object tracking with application to people monitoring
Ji Tao,Yap-Peng Tan,Wenmiao Lu +2 more
TL;DR: An automated and complete camera-based monitoring system that makes use of low-level color features to perform detection, tracking and recognition of multiple people in video sequence and incorporates a shadow removal scheme to suppress shadow effects and hence improve the quality of color histogram is presented.