Loading [a11y]/accessibility-menu.js
Learning deep features for multiple object tracking by using a multi-task learning strategy | IEEE Conference Publication | IEEE Xplore

Learning deep features for multiple object tracking by using a multi-task learning strategy


Abstract:

Model-free object tracking is still challenging because of the limited prior knowledge and the unexpected variation of the target object. In this paper, we propose a feat...Show More

Abstract:

Model-free object tracking is still challenging because of the limited prior knowledge and the unexpected variation of the target object. In this paper, we propose a feature learning algorithm for model-free multiple object tracking. First, we pre-learn generic features invariant to diverse motion transformations from auxiliary video data by using a deep network of anto-encoder. Then, we adapt the pre-learned features according to multiple target objects respectively in a multi-task learning manner. We treat the feature adaptation for each target object as one single task. We simultaneously learn the common feature shared by all target objects and the individual feature of each object. Experimental results demonstrate that our feature learning algorithm can significantly improve multiple object tracking performance.
Date of Conference: 27-30 October 2014
Date Added to IEEE Xplore: 29 January 2015
Electronic ISBN:978-1-4799-5751-4

ISSN Information:

Conference Location: Paris, France

References

References is not available for this document.