LATrack: Limited Attention for Visual Object Tracking
The use of temporal information is becoming increasingly important in mainstream visual object trackers. Mainstream trackers typically interact trajectory information with image features. However, existing methods of interaction cannot effectively utilize trajectory information, and the significance...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10820357/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550772431486976 |
|---|---|
| author | Jian Shi Zheng Chang Yang Yu Junze Shi Haibo Luo |
| author_facet | Jian Shi Zheng Chang Yang Yu Junze Shi Haibo Luo |
| author_sort | Jian Shi |
| collection | DOAJ |
| description | The use of temporal information is becoming increasingly important in mainstream visual object trackers. Mainstream trackers typically interact trajectory information with image features. However, existing methods of interaction cannot effectively utilize trajectory information, and the significance of the interaction remains unclear. To address these issues, we propose a Limited Attention module (LA module). The LA module more effectively utilizes image features by masking certain image features based on historical trajectory information or prediction information. Based on the LA module, we propose Limited Attention Track (LATrack), which can make more effective use of trajectory information. LATrack can continuously approach the target object by utilizing the predicted coordinates of the historical trajectory, thereby obtaining the object’s position in the current frame. Our model excels in handling challenges such as motion blur, distraction from similar objects, and occlusion. LATrack demonstrates excellent performance across multiple datasets, notably achieving 76.7% AO and 53.8% AUC on the GOT-10k and <inline-formula> <tex-math notation="LaTeX">$\mathrm {LaSOT_{ext}}$ </tex-math></inline-formula> datasets, respectively. |
| format | Article |
| id | doaj-art-6f1e2b94b91d4c2e89e8249a6e19f9d7 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6f1e2b94b91d4c2e89e8249a6e19f9d72025-01-10T00:01:15ZengIEEEIEEE Access2169-35362025-01-01134034404710.1109/ACCESS.2024.352501610820357LATrack: Limited Attention for Visual Object TrackingJian Shi0https://orcid.org/0009-0000-3858-8864Zheng Chang1https://orcid.org/0000-0001-7705-0194Yang Yu2Junze Shi3https://orcid.org/0009-0006-5028-2749Haibo Luo4https://orcid.org/0000-0001-6425-6433Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang, ChinaChinese Academy of Sciences, Shenyang Institute of Automation, Shenyang, ChinaKey Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang, ChinaKey Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang, ChinaKey Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang, ChinaThe use of temporal information is becoming increasingly important in mainstream visual object trackers. Mainstream trackers typically interact trajectory information with image features. However, existing methods of interaction cannot effectively utilize trajectory information, and the significance of the interaction remains unclear. To address these issues, we propose a Limited Attention module (LA module). The LA module more effectively utilizes image features by masking certain image features based on historical trajectory information or prediction information. Based on the LA module, we propose Limited Attention Track (LATrack), which can make more effective use of trajectory information. LATrack can continuously approach the target object by utilizing the predicted coordinates of the historical trajectory, thereby obtaining the object’s position in the current frame. Our model excels in handling challenges such as motion blur, distraction from similar objects, and occlusion. LATrack demonstrates excellent performance across multiple datasets, notably achieving 76.7% AO and 53.8% AUC on the GOT-10k and <inline-formula> <tex-math notation="LaTeX">$\mathrm {LaSOT_{ext}}$ </tex-math></inline-formula> datasets, respectively.https://ieeexplore.ieee.org/document/10820357/Limited attentiontemporal promptvision transformervisual object tracking |
| spellingShingle | Jian Shi Zheng Chang Yang Yu Junze Shi Haibo Luo LATrack: Limited Attention for Visual Object Tracking IEEE Access Limited attention temporal prompt vision transformer visual object tracking |
| title | LATrack: Limited Attention for Visual Object Tracking |
| title_full | LATrack: Limited Attention for Visual Object Tracking |
| title_fullStr | LATrack: Limited Attention for Visual Object Tracking |
| title_full_unstemmed | LATrack: Limited Attention for Visual Object Tracking |
| title_short | LATrack: Limited Attention for Visual Object Tracking |
| title_sort | latrack limited attention for visual object tracking |
| topic | Limited attention temporal prompt vision transformer visual object tracking |
| url | https://ieeexplore.ieee.org/document/10820357/ |
| work_keys_str_mv | AT jianshi latracklimitedattentionforvisualobjecttracking AT zhengchang latracklimitedattentionforvisualobjecttracking AT yangyu latracklimitedattentionforvisualobjecttracking AT junzeshi latracklimitedattentionforvisualobjecttracking AT haiboluo latracklimitedattentionforvisualobjecttracking |