Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4946745 | Neural Networks | 2017 | 17 Pages |
Abstract
Imitating the behaviors of an arbitrary visual tracking algorithm enables many higher level tasks such as tracker identification and efficient tracker-fusion. It is also useful for discovering the features essential in a black-box tracker or learning from several trackers to form a super-tracker. In this study, we propose a non-linear feature fusion framework, “MIMIC” that imitates many popular trackers by mixing a pool of heterogeneous features. The MIMIC framework consists of two subtasks, feature selection and feature weight tuning. These subtasks, however, tended to suffer from an overfitting problem when the number of videos available for training is limited. To address this issue, we incorporated Dropout algorithm into the training, which grants the trained MIMIC tracker a high degree of generalization. Extensive experiments testified the effectiveness of the proposed framework so that its applications would be promoted into different related tasks in visual tracking.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Kourosh Meshgi, Shin-ichi Maeda, Shigeyuki Oba, Shin Ishii,