L
Li Xuejun
Researcher at Nanjing University of Information Science and Technology
Publications - 4
Citations - 53
Li Xuejun is an academic researcher from Nanjing University of Information Science and Technology. The author has contributed to research in topics: Segmentation & Active appearance model. The author has an hindex of 3, co-authored 4 publications receiving 49 citations.
Papers
More filters
Journal ArticleDOI
Visual tracking using spatio-temporally nonlocally regularized correlation filter
TL;DR: This paper explores the nonlocal information to accurately represent and segment the target, yielding an object likelihood map to regularize a correlation filter (CF) for visual tracking, which performs favorably against some state-of-art methods.
Patent
Unsupervised video segmentation method integrated with temporal-spatial multi-feature representation
TL;DR: Wang et al. as discussed by the authors proposed an unsupervised video segmentation method integrated with temporal-spatial multi-feature representation, where features of a target are extracted and identified according to themotion information and saliency and color features of the target, and the target is segmented stably and accurately through a Gaussian mixture model.
Posted Content
Unsupervised Video Segmentation via Spatio-Temporally Nonlocal Appearance Learning
TL;DR: This paper proposes a simple yet effective approach to mine the long-term sptatio-temporally nonlocal appearance information for unsupervised video segmentation, and develops a spatio-temporal graphical model comprised of the superpixel label consistency potentials.
Patent
Unsupervised video segmentation method based on non-local space-time characteristic learning
TL;DR: In this paper, an unsupervised video segmentation method based on non-local space-time characteristic learning is proposed, which consists of acquiring a video sequence which needs to be segmented, using a superpixel to segment and process the video sequence; using a light stream to carry out previous and next frame information matching; according to adjacent frame information, acquiring a range of a motion target and taking as model initialization input; using global information to optimize a matching result; and establishing a graph model and using a graph segmentation algorithm to solve a segmentation result, and through