RoI Pooling Based Fast Multi-Domain Convolutional Neural Networks for Visual Tracking

DOI

10.2991/aiie-16.2016.46How to use a DOI?

Keywords

component; visual tracking; Fast MDNet; CNN; RoI

Abstract

This paper proposes a fast multi-domain convolutional neural networks method (Fast MDNet) for visual tracking. Fast MDNet builds on fast region-based convolutional neural networks (Fast R-CNN) and MDNet to efficiently track arbitrary objects using deep convolutional networks. We introduce a RoI pooling layer which shares full-image convolutional features, thus significantly speed up MDNet. Compared to previous works, Fast MDNet's online tracking rate is 15x faster than MDNet, and it performs favorably against the state-of-the-art methods on large benchmark datasets.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yuanyuan Qin
AU  - Shiying He
AU  - Yong Zhao
AU  - Yuanzhi Gong
PY  - 2016/11
DA  - 2016/11
TI  - RoI Pooling Based Fast Multi-Domain Convolutional Neural Networks for Visual Tracking
BT  - Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)
PB  - Atlantis Press
SP  - 198
EP  - 202
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-16.2016.46
DO  - 10.2991/aiie-16.2016.46
ID  - Qin2016/11
ER  -