ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning
Cited 488 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Sangdoo Yun, Jongwon Choi, Youngjoon Yoo, Kimin Yun, Jin Young Choi
Issue Date
2017-07
Citation
Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pp.1349-1358
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/CVPR.2017.148
Abstract
This paper proposes a novel tracker which is controlled by sequentially pursuing actions learned by deep reinforcement learning. In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale. The deep network to control actions is pre-trained using various training sequences and fine-tuned during tracking for online adaptation to target and background changes. The pre-training is done by utilizing deep reinforcement learning as well as supervised learning. The use of reinforcement learning enables even partially labeled data to be successfully utilized for semi-supervised learning. Through evaluation of the OTB dataset, the proposed tracker is validated to achieve a competitive performance that is three times faster than state-of-the-art, deep network-based trackers. The fast version of the proposed method, which operates in real-time on GPU, outperforms the state-of-the-art real-time trackers.
KSP Keywords
Competitive performance, Decision network, Deep reinforcement learning, Network-based, Partially labeled data, Pre-Training, Real-time, Reinforcement learning(RL), Semi-Supervised Learning(SSL), Target and background, Visual tracking