Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/221353
Title: Discriminative Reverse Sparse Tracking via Weighted Multitask Learning
Authors: Yehui Yang;Wenrui Hu;Wensheng Zhang;Tianzhu Zhang;Yuan Xie
Year: 2017
Publisher: IEEE
Abstract: Multitask learning has shown great potentiality for visual tracking under a particle filter framework. However, the recent multitask trackers, which exploit the similarity between all candidates by imposing group sparsity on the candidate representations, have a limitation in robustness due to the diverse sampling of candidates. To deal with this issue, we propose a discriminative reverse sparse tracker via weighted multitask learning. Our positive and negative templates are retained from the target observations and the background, respectively. Here, the templates are reversely represented via the candidates, and the representation of each positive template is viewed as a single task. Compared with existing multitask trackers, the proposed algorithm has the following advantages. First, we regularize the target representations with the &x2113;<sub>2,1</sub>-norm to exploit the similarity shared by the positive templates, which is reasonable because of the target appearance consistency in the tracking process. Second, the valuable prior relationship between the candidates and the templates is introduced into the representation model by a weighted multitask learning scheme. Third, both target information and background information are integrated to generate discriminative scores for enhancing the proposed tracker. The experimental results on challenging sequences show that the proposed algorithm is effective and performs favorably against 12 state-of-the-art trackers.
URI: http://localhost/handle/Hannan/221353
volume: 27
issue: 5
More Information: 1031,
1042
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7368895.pdf2.1 MBAdobe PDF
Title: Discriminative Reverse Sparse Tracking via Weighted Multitask Learning
Authors: Yehui Yang;Wenrui Hu;Wensheng Zhang;Tianzhu Zhang;Yuan Xie
Year: 2017
Publisher: IEEE
Abstract: Multitask learning has shown great potentiality for visual tracking under a particle filter framework. However, the recent multitask trackers, which exploit the similarity between all candidates by imposing group sparsity on the candidate representations, have a limitation in robustness due to the diverse sampling of candidates. To deal with this issue, we propose a discriminative reverse sparse tracker via weighted multitask learning. Our positive and negative templates are retained from the target observations and the background, respectively. Here, the templates are reversely represented via the candidates, and the representation of each positive template is viewed as a single task. Compared with existing multitask trackers, the proposed algorithm has the following advantages. First, we regularize the target representations with the &x2113;<sub>2,1</sub>-norm to exploit the similarity shared by the positive templates, which is reasonable because of the target appearance consistency in the tracking process. Second, the valuable prior relationship between the candidates and the templates is introduced into the representation model by a weighted multitask learning scheme. Third, both target information and background information are integrated to generate discriminative scores for enhancing the proposed tracker. The experimental results on challenging sequences show that the proposed algorithm is effective and performs favorably against 12 state-of-the-art trackers.
URI: http://localhost/handle/Hannan/221353
volume: 27
issue: 5
More Information: 1031,
1042
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7368895.pdf2.1 MBAdobe PDF
Title: Discriminative Reverse Sparse Tracking via Weighted Multitask Learning
Authors: Yehui Yang;Wenrui Hu;Wensheng Zhang;Tianzhu Zhang;Yuan Xie
Year: 2017
Publisher: IEEE
Abstract: Multitask learning has shown great potentiality for visual tracking under a particle filter framework. However, the recent multitask trackers, which exploit the similarity between all candidates by imposing group sparsity on the candidate representations, have a limitation in robustness due to the diverse sampling of candidates. To deal with this issue, we propose a discriminative reverse sparse tracker via weighted multitask learning. Our positive and negative templates are retained from the target observations and the background, respectively. Here, the templates are reversely represented via the candidates, and the representation of each positive template is viewed as a single task. Compared with existing multitask trackers, the proposed algorithm has the following advantages. First, we regularize the target representations with the &x2113;<sub>2,1</sub>-norm to exploit the similarity shared by the positive templates, which is reasonable because of the target appearance consistency in the tracking process. Second, the valuable prior relationship between the candidates and the templates is introduced into the representation model by a weighted multitask learning scheme. Third, both target information and background information are integrated to generate discriminative scores for enhancing the proposed tracker. The experimental results on challenging sequences show that the proposed algorithm is effective and performs favorably against 12 state-of-the-art trackers.
URI: http://localhost/handle/Hannan/221353
volume: 27
issue: 5
More Information: 1031,
1042
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7368895.pdf2.1 MBAdobe PDF