提出分层多模态融合网络，提升RGB-D跟踪的鲁棒性与实时性。
RGB-D Tracking via Hierarchical Modality Aggregation and Distribution Network
- 采用分层机制融合RGB与深度特征，增强模态间互补性。
- 在多个数据集上达到领先性能，实测可满足实时跟踪需求。
- 适合需要高精度、低延迟视觉跟踪的应用场景。
双模态特征融合对推进RGB-Depth（RGB-D）跟踪至关重要。然而，现有跟踪器效率较低，仅关注单层次特征，导致融合鲁棒性弱且速度慢，难以满足实际应用需求。本文提出一种新型网络HMAD（Hierarchical Modality Aggregation and Distribution），充分利用RGB与深度模态的特征表达优势，采用分层特征分布与融合策略，显著提升RGB-D跟踪的鲁棒性。在多个RGB-D数据集上的实验结果表明，HMAD实现当前最优性能；真实场景实验进一步验证其在实时场景中有效应对多样化跟踪挑战的能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。