RGB-D Tracking via Hierarchical Modality Aggregation and Distribution Network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908336650190848 |
|---|---|
| author | Xu, Boyue Xu, Yi Hou, Ruichao Bei, Jia Ren, Tongwei Wu, Gangshan |
| author_facet | Xu, Boyue Xu, Yi Hou, Ruichao Bei, Jia Ren, Tongwei Wu, Gangshan |
| contents | The integration of dual-modal features has been pivotal in advancing RGB-Depth (RGB-D) tracking. However, current trackers are less efficient and focus solely on single-level features, resulting in weaker robustness in fusion and slower speeds that fail to meet the demands of real-world applications. In this paper, we introduce a novel network, denoted as HMAD (Hierarchical Modality Aggregation and Distribution), which addresses these challenges. HMAD leverages the distinct feature representation strengths of RGB and depth modalities, giving prominence to a hierarchical approach for feature distribution and fusion, thereby enhancing the robustness of RGB-D tracking. Experimental results on various RGB-D datasets demonstrate that HMAD achieves state-of-the-art performance. Moreover, real-world experiments further validate HMAD's capacity to effectively handle a spectrum of tracking challenges in real-time scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17595 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RGB-D Tracking via Hierarchical Modality Aggregation and Distribution Network Xu, Boyue Xu, Yi Hou, Ruichao Bei, Jia Ren, Tongwei Wu, Gangshan Computer Vision and Pattern Recognition The integration of dual-modal features has been pivotal in advancing RGB-Depth (RGB-D) tracking. However, current trackers are less efficient and focus solely on single-level features, resulting in weaker robustness in fusion and slower speeds that fail to meet the demands of real-world applications. In this paper, we introduce a novel network, denoted as HMAD (Hierarchical Modality Aggregation and Distribution), which addresses these challenges. HMAD leverages the distinct feature representation strengths of RGB and depth modalities, giving prominence to a hierarchical approach for feature distribution and fusion, thereby enhancing the robustness of RGB-D tracking. Experimental results on various RGB-D datasets demonstrate that HMAD achieves state-of-the-art performance. Moreover, real-world experiments further validate HMAD's capacity to effectively handle a spectrum of tracking challenges in real-time scenarios. |
| title | RGB-D Tracking via Hierarchical Modality Aggregation and Distribution Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.17595 |