Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Part-based visual tracking with online latent structural learning|
Van Den Hengel, A.
|Citation:||Proceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, 23-28 June 2013, Portland, Oregon, USA: pp. 2363-2370|
|Publisher Place:||United States of America|
|Series/Report no.:||IEEE Conference on Computer Vision and Pattern Recognition|
|Conference Name:||IEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon)|
|Rui Yao, Qinfeng Shi, Chunhua Shen, Yanning Zhang, Anton van den Hengel|
|Abstract:||Despite many advances made in the area, deformable targets and partial occlusions continue to represent key problems in visual tracking. Structured learning has shown good results when applied to tracking whole targets, but applying this approach to a part-based target model is complicated by the need to model the relationships between parts, and to avoid lengthy initialisation processes. We thus propose a method which models the unknown parts using latent variables. In doing so we extend the online algorithm pegasos to the structured prediction case (i.e., predicting the location of the bounding boxes) with latent part variables. To better estimate the parts, and to avoid over-fitting caused by the extra model complexity/capacity introduced by the parts, we propose a two-stage training process, based on the primal rather than the dual form. We then show that the method outperforms the state-of-the-art (linear and non-linear kernel) trackers.|
|Keywords:||Online Latent Structural Learning; part-based tracking; visual tracking|
|Appears in Collections:||Computer Science publications|
Files in This Item:
|hdl_77413.pdf||Accepted version||2.22 MB||Adobe PDF||View/Open|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.