Multi-Scale Adaptive Cascaded Tracking for Vision-Language Integration
IEEE Signal Processing Letters · 2025 · 32 · 4119-4123
DOI: 10.1109/lsp.2025.3624079 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2025. Verfasst von Guomao Guo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Foundation of Yunnan Key Laboratory of Unmanned Autonomous Systems, Basic and Applied Basic Research Foundation of Guangdong Province.
Abstract (Originalsprache)
Unlike traditional single-modal visual tracking, vision-language tracking leverages textual descriptions to provide semantic understanding, aiding in handling challenges such as appearance variations, occlusions, and motion blur. However, the semantic gap between textual and visual information complicates cross-modal alignment and fusion. Moreover, fixed textual descriptions may fail to reflect real-time variations in dynamic video frames, thereby affecting tracking accuracy.To address these challenges, we propose MACT, the Multi-scale Adaptive Cascaded Tracker, which enhances vision-language integration through a series of key mechanisms. First, Multi-Scale Feature Alignment (MSFA) encodes image and text features at multiple scales and dynamically aligns them using cross-modal attention, strengthening information flow and interaction between modalities. Second, Adaptive Cascaded Fusion (ACF) adaptively learns the correspondence between text descriptions and video frames, extracting appropriate hierarchical interaction features to ensure that textual information effectively aids visual tracking. Finally, Scale Recovery(SR) integrates multi-scale deep feature representations back to the original scale before passing them to the tracking head for final predictions. Extensive experiments on TNL2K, LaSOT, and OTB99 demonstrate that our proposed MACT achieves state-of-the-art tracking performance.
Förderung
- National Natural Science Foundation of China
- Foundation of Yunnan Key Laboratory of Unmanned Autonomous Systems
- Basic and Applied Basic Research Foundation of Guangdong Province
Zitieren
APA
Guo, G., Geng, G., Tang, J., Liu, Q., & Yuan, D. (2025). Multi-Scale Adaptive Cascaded Tracking for Vision-Language Integration. IEEE Signal Processing Letters, 32, 4119-4123. https://doi.org/10.1109/lsp.2025.3624079
Vancouver
Guo G, Geng G, Tang J, Liu Q, Yuan D. Multi-Scale Adaptive Cascaded Tracking for Vision-Language Integration. IEEE Signal Processing Letters. 2025;32:4119-4123. doi:10.1109/lsp.2025.3624079
BibTeX
@article{Guo2025,
author = {Guo, Guomao and Geng, Gu and Tang, Jianing and Liu, Qiao and Yuan, Di},
title = {Multi-Scale Adaptive Cascaded Tracking for Vision-Language Integration},
journal = {IEEE Signal Processing Letters},
year = {2025},
volume = {32},
pages = {4119--4123},
doi = {10.1109/lsp.2025.3624079}
}
EUVIMED