Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Gate connected Convolutional Neural Network for Object Tracking

Abstract: 

Convolutional neural networks (CNNs) have been employed in visual tracking due to their rich levels of feature representation. While the learning capability of a CNN increases with its depth, unfortunately spatial information is diluted in deeper layers which hinders its important ability to localise targets. To successfully manage this trade-off, we propose a novel residual network based gating CNN architecture for object tracking. Our deep model connects the front and bottom convolutional features with a gate layer. This new network learns discriminative features while reducing the spatial information lost. This architecture is pre-trained to learn generic tracking characteristics. In online tracking, an efficient domain adaptation mechanism is used to accurately learn the target appearance with limited samples. Extensive evaluation performed on a publicly available benchmark dataset demonstrates our proposed tracker outperforms state-of-the-art approaches.

up
0 users have voted:

Paper Details

Authors:
T.Kokul, C.Fookes, S.Sridharan, A.Ramanan, U.A.J.Pinidiyaarachchi
Submitted On:
11 September 2017 - 6:09pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Clinton Fookes
Paper Code:
2285
Document Year:
2017
Cite

Document Files

poster_ICIP.pdf

(6 downloads)

Keywords

Additional Categories

Subscribe

[1] T.Kokul, C.Fookes, S.Sridharan, A.Ramanan, U.A.J.Pinidiyaarachchi, "Gate connected Convolutional Neural Network for Object Tracking", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1919. Accessed: Sep. 19, 2017.
@article{1919-17,
url = {http://sigport.org/1919},
author = {T.Kokul; C.Fookes; S.Sridharan; A.Ramanan; U.A.J.Pinidiyaarachchi },
publisher = {IEEE SigPort},
title = {Gate connected Convolutional Neural Network for Object Tracking},
year = {2017} }
TY - EJOUR
T1 - Gate connected Convolutional Neural Network for Object Tracking
AU - T.Kokul; C.Fookes; S.Sridharan; A.Ramanan; U.A.J.Pinidiyaarachchi
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1919
ER -
T.Kokul, C.Fookes, S.Sridharan, A.Ramanan, U.A.J.Pinidiyaarachchi. (2017). Gate connected Convolutional Neural Network for Object Tracking. IEEE SigPort. http://sigport.org/1919
T.Kokul, C.Fookes, S.Sridharan, A.Ramanan, U.A.J.Pinidiyaarachchi, 2017. Gate connected Convolutional Neural Network for Object Tracking. Available at: http://sigport.org/1919.
T.Kokul, C.Fookes, S.Sridharan, A.Ramanan, U.A.J.Pinidiyaarachchi. (2017). "Gate connected Convolutional Neural Network for Object Tracking." Web.
1. T.Kokul, C.Fookes, S.Sridharan, A.Ramanan, U.A.J.Pinidiyaarachchi. Gate connected Convolutional Neural Network for Object Tracking [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1919