In this section
@inproceedings{Choi:2018:10.1109/CVPR.2018.00057,
author = {Choi, J and Chang, HJ and Fischer, T and Yun, S and Lee, K and Jeong, J and Demiris, Y and Choi, JY},
doi = {10.1109/CVPR.2018.00057},
pages = {479--488},
publisher = {Institute of Electrical and Electronics Engineers},
title = {Context-aware deep feature compression for high-speed visual tracking},
url = {http://dx.doi.org/10.1109/CVPR.2018.00057},
year = {2018}
}
TY - CPAPER
AB - We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert auto-encoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.
AU - Choi,J
AU - Chang,HJ
AU - Fischer,T
AU - Yun,S
AU - Lee,K
AU - Jeong,J
AU - Demiris,Y
AU - Choi,JY
DO - 10.1109/CVPR.2018.00057
EP - 488
PB - Institute of Electrical and Electronics Engineers
PY - 2018///
SN - 1063-6919
SP - 479
TI - Context-aware deep feature compression for high-speed visual tracking
UR - http://dx.doi.org/10.1109/CVPR.2018.00057
UR - http://hdl.handle.net/10044/1/58334
ER -
