Adaptive Perception for Unified Visual Multi-modal Object Tracking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909486110736384 |
|---|---|
| author | Hu, Xiantao Zhong, Bineng Liang, Qihua Mo, Zhiyi Shi, Liangtao Tai, Ying Yang, Jian |
| author_facet | Hu, Xiantao Zhong, Bineng Liang, Qihua Mo, Zhiyi Shi, Liangtao Tai, Ying Yang, Jian |
| contents | Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods to dynamically utilize complementary information from each modality in complex scenarios, making it challenging to fully perceive the advantages of multi-modal. As a result, a unified parameter model often underperforms in various multi-modal tracking tasks. To address this issue, we propose APTrack, a novel unified tracker designed for multi-modal adaptive perception. Unlike previous methods, APTrack explores a unified representation through an equal modeling strategy. This strategy allows the model to dynamically adapt to various modalities and tasks without requiring additional fine-tuning between different tasks. Moreover, our tracker integrates an adaptive modality interaction (AMI) module that efficiently bridges cross-modality interactions by generating learnable tokens. Experiments conducted on five diverse multi-modal datasets (RGBT234, LasHeR, VisEvent, DepthTrack, and VOT-RGBD2022) demonstrate that APTrack not only surpasses existing state-of-the-art unified multi-modal trackers but also outperforms trackers designed for specific multi-modal tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06583 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive Perception for Unified Visual Multi-modal Object Tracking Hu, Xiantao Zhong, Bineng Liang, Qihua Mo, Zhiyi Shi, Liangtao Tai, Ying Yang, Jian Computer Vision and Pattern Recognition Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods to dynamically utilize complementary information from each modality in complex scenarios, making it challenging to fully perceive the advantages of multi-modal. As a result, a unified parameter model often underperforms in various multi-modal tracking tasks. To address this issue, we propose APTrack, a novel unified tracker designed for multi-modal adaptive perception. Unlike previous methods, APTrack explores a unified representation through an equal modeling strategy. This strategy allows the model to dynamically adapt to various modalities and tasks without requiring additional fine-tuning between different tasks. Moreover, our tracker integrates an adaptive modality interaction (AMI) module that efficiently bridges cross-modality interactions by generating learnable tokens. Experiments conducted on five diverse multi-modal datasets (RGBT234, LasHeR, VisEvent, DepthTrack, and VOT-RGBD2022) demonstrate that APTrack not only surpasses existing state-of-the-art unified multi-modal trackers but also outperforms trackers designed for specific multi-modal tasks. |
| title | Adaptive Perception for Unified Visual Multi-modal Object Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.06583 |