@article{ART003055350},
author={Janghoon Choi},
title={Utilizing Context of Object Regions for Robust Visual Tracking},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2024},
volume={29},
number={2},
pages={79-86},
doi={10.9708/jksci.2024.29.02.079}
TY - JOUR
AU - Janghoon Choi
TI - Utilizing Context of Object Regions for Robust Visual Tracking
JO - Journal of The Korea Society of Computer and Information
PY - 2024
VL - 29
IS - 2
PB - The Korean Society Of Computer And Information
SP - 79
EP - 86
SN - 1598-849X
AB - In this paper, a novel visual tracking method which can utilize the context of object regions is presented. Conventional methods have the inherent problem of treating all candidate regions independently, where the tracker could not successfully discriminate regions with similar appearances.
This was due to lack of contextual modeling in a given scene, where all candidate object regions should be taken into consideration when choosing a single region. The goal of the proposed method is to encourage feature exchange between candidate regions to improve the discriminability between similar regions. It improves upon conventional methods that only consider a single region, and is implemented by employing the MLP-Mixer model for enhanced feature exchange between regions. By implementing channel-wise, inter-region interaction operation between candidate features, contextual information of regions can be embedded into the individual feature representations. To evaluate the performance of the proposed tracker, the large-scale LaSOT dataset is used, and the experimental results show a competitive AUC performance of 0.560 while running at a real-time speed of 65 fps.
KW - Visual tracking;Object tracking;Video understanding;Context modeling;Mixer network
DO - 10.9708/jksci.2024.29.02.079
ER -
Janghoon Choi. (2024). Utilizing Context of Object Regions for Robust Visual Tracking. Journal of The Korea Society of Computer and Information, 29(2), 79-86.
Janghoon Choi. 2024, "Utilizing Context of Object Regions for Robust Visual Tracking", Journal of The Korea Society of Computer and Information, vol.29, no.2 pp.79-86. Available from: doi:10.9708/jksci.2024.29.02.079
Janghoon Choi "Utilizing Context of Object Regions for Robust Visual Tracking" Journal of The Korea Society of Computer and Information 29.2 pp.79-86 (2024) : 79.
Janghoon Choi. Utilizing Context of Object Regions for Robust Visual Tracking. 2024; 29(2), 79-86. Available from: doi:10.9708/jksci.2024.29.02.079
Janghoon Choi. "Utilizing Context of Object Regions for Robust Visual Tracking" Journal of The Korea Society of Computer and Information 29, no.2 (2024) : 79-86.doi: 10.9708/jksci.2024.29.02.079
Janghoon Choi. Utilizing Context of Object Regions for Robust Visual Tracking. Journal of The Korea Society of Computer and Information, 29(2), 79-86. doi: 10.9708/jksci.2024.29.02.079
Janghoon Choi. Utilizing Context of Object Regions for Robust Visual Tracking. Journal of The Korea Society of Computer and Information. 2024; 29(2) 79-86. doi: 10.9708/jksci.2024.29.02.079
Janghoon Choi. Utilizing Context of Object Regions for Robust Visual Tracking. 2024; 29(2), 79-86. Available from: doi:10.9708/jksci.2024.29.02.079
Janghoon Choi. "Utilizing Context of Object Regions for Robust Visual Tracking" Journal of The Korea Society of Computer and Information 29, no.2 (2024) : 79-86.doi: 10.9708/jksci.2024.29.02.079
