logo
banner

Journals & Publications

Journals Publications Papers

Papers

Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking
Feb 08, 2017Author:
PrintText Size A A

Title: Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking
Authors: Hu, WM; Gao, J; Xing, JL; Zhang, C; Maybank, S
Author Full Names: Hu, Weiming; Gao, Jin; Xing, Junliang; Zhang, Chao; Maybank, Stephen
Source: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 39 (1):172-188; 10.1109/TPAMI.2016.2539944 JAN 2017
Language: English
Abstract: An appearance model adaptable to changes in object appearance is critical in visual object tracking. In this paper, we treat an image patch as a two-order tensor which preserves the original image structure. We design two graphs for characterizing the intrinsic local geometrical structure of the tensor samples of the object and the background. Graph embedding is used to reduce the dimensions of the tensors while preserving the structure of the graphs. Then, a discriminant embedding space is constructed. We prove two propositions for finding the transformation matrices which are used to map the original tensor samples to the tensor-based graph embedding space. In order to encode more discriminant information in the embedding space, we propose a transfer-learning-based semi-supervised strategy to iteratively adjust the embedding space into which discriminative information obtained from earlier times is transferred. We apply the proposed semi-supervised tensor-based graph embedding learning algorithm to visual tracking. The new tracking algorithm captures an object's appearance characteristics during tracking and uses a particle filter to estimate the optimal object state. Experimental results on the CVPR 2013 benchmark dataset demonstrate the effectiveness of the proposed tracking algorithm.
ISSN: 0162-8828
eISSN: 1939-3539
IDS Number: EF6DP
Unique ID: WOS:000390421300015
*Click Here to View Full Record