HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking.

RGB cameras capture rich texture with high spatial resolution, whereas event cameras offer superior temporal resolution and high dynamic range (HDR). Exploiting their complementarity can significantly improve object tracking in challenging scenarios, including high-speed motion, HDR conditions, and dynamic background interference. However, effective multimodal integration is impeded by pronounced spatio-temporal asymmetries induced by their distinct imaging mechanisms. To address this issue, we propose hierarchical asymmetric distillation (HAD), a multimodal distillation framework that explicitly models and alleviates such asymmetries. HAD employs a hierarchical alignment strategy to reduce information loss during cross-modal transfer while maintaining the efficiency and compactness of the student network. Extensive experiments demonstrate that HAD consistently outperforms state-of-the-art methods, and comprehensive ablations verify the effectiveness of each component. The code will be released at https://github.com/Taxalfer/HAD.