Exploiting All Mamba Fusion for Efficient RGB-D Tracking
Ge Ying, Dawei Zhang, Chengzhuan Yang, Wei Liu, Sang-Woon Jeon, Hua Wang, Changqin Huang, Zhonglong Zheng
Abstract
Despite the progress made through deep learning, existing Visual Object Tracking (VOT) frameworks struggle with real-world challenges. Recent approaches incorporate additional modalities like Depth, Thermal Infrared, and Language to enhance the robustness of VOT, particularly with the improvement of the depth sensor precision, facilitating RGB-D tracking. However, current RGB-D trackers often copy RGB tracking paradigms, leading to inefficiency due to two-stream architectures that fail to exploit heterogeneous features, and reliance on simplistic or large-parameter fusion methods. To address these challenges, we propose AMTrack, a one-stream RGB-D tracker leveraging Mamba
BibTeX
@inproceedings{aaai2026_exploitingallmam,
title = {Exploiting All Mamba Fusion for Efficient RGB-D Tracking},
author = {Ge Ying and Dawei Zhang and Chengzhuan Yang and Wei Liu and Sang-Woon Jeon and Hua Wang and Changqin Huang and Zhonglong Zheng},
booktitle = {AAAI 2026},
year = {2026}
}