Cargando…
Global Context Attention for Robust Visual Tracking
Although there have been recent advances in Siamese-network-based visual tracking methods where they show high performance metrics on numerous large-scale visual tracking benchmarks, persistent challenges regarding the distractor objects with similar appearances to the target object still remain. To...
Autor principal: | |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007428/ https://www.ncbi.nlm.nih.gov/pubmed/36904897 http://dx.doi.org/10.3390/s23052695 |
_version_ | 1784905518788116480 |
---|---|
author | Choi, Janghoon |
author_facet | Choi, Janghoon |
author_sort | Choi, Janghoon |
collection | PubMed |
description | Although there have been recent advances in Siamese-network-based visual tracking methods where they show high performance metrics on numerous large-scale visual tracking benchmarks, persistent challenges regarding the distractor objects with similar appearances to the target object still remain. To address these aforementioned issues, we propose a novel global context attention module for visual tracking, where the proposed module can extract and summarize the holistic global scene information to modulate the target embedding for improved discriminability and robustness. Our global context attention module receives a global feature correlation map to elicit the contextual information from a given scene and generates the channel and spatial attention weights to modulate the target embedding to focus on the relevant feature channels and spatial parts of the target object. Our proposed tracking algorithm is tested on large-scale visual tracking datasets, where we show improved performance compared to the baseline tracking algorithm while achieving competitive performance with real-time speed. Additional ablation experiments also validate the effectiveness of the proposed module, where our tracking algorithm shows improvements in various challenging attributes of visual tracking. |
format | Online Article Text |
id | pubmed-10007428 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100074282023-03-12 Global Context Attention for Robust Visual Tracking Choi, Janghoon Sensors (Basel) Article Although there have been recent advances in Siamese-network-based visual tracking methods where they show high performance metrics on numerous large-scale visual tracking benchmarks, persistent challenges regarding the distractor objects with similar appearances to the target object still remain. To address these aforementioned issues, we propose a novel global context attention module for visual tracking, where the proposed module can extract and summarize the holistic global scene information to modulate the target embedding for improved discriminability and robustness. Our global context attention module receives a global feature correlation map to elicit the contextual information from a given scene and generates the channel and spatial attention weights to modulate the target embedding to focus on the relevant feature channels and spatial parts of the target object. Our proposed tracking algorithm is tested on large-scale visual tracking datasets, where we show improved performance compared to the baseline tracking algorithm while achieving competitive performance with real-time speed. Additional ablation experiments also validate the effectiveness of the proposed module, where our tracking algorithm shows improvements in various challenging attributes of visual tracking. MDPI 2023-03-01 /pmc/articles/PMC10007428/ /pubmed/36904897 http://dx.doi.org/10.3390/s23052695 Text en © 2023 by the author. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Choi, Janghoon Global Context Attention for Robust Visual Tracking |
title | Global Context Attention for Robust Visual Tracking |
title_full | Global Context Attention for Robust Visual Tracking |
title_fullStr | Global Context Attention for Robust Visual Tracking |
title_full_unstemmed | Global Context Attention for Robust Visual Tracking |
title_short | Global Context Attention for Robust Visual Tracking |
title_sort | global context attention for robust visual tracking |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007428/ https://www.ncbi.nlm.nih.gov/pubmed/36904897 http://dx.doi.org/10.3390/s23052695 |
work_keys_str_mv | AT choijanghoon globalcontextattentionforrobustvisualtracking |