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 -