EvRainDrop：基于超图的高效帧和事件流聚合
EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation
AI总结：
EvRainDrop通过超图引导的方法完成事件流，实现多模态特征的有效融合与学习。
摘要：
事件相机产生异步事件流，这些流在空间上稀疏但在时间上密集。主流的事件表示学习算法通常使用事件帧、体素或张量作为输入。尽管这些方法已取得显著进展，但它们难以解决由空间稀疏性引起的采样不足问题。在本文中，我们提出了一种新颖的超图引导的空间-时间事件流完成机制，通过超图连接不同时间和空间位置的事件标记，并利用上下文信息消息传递来完成这些稀疏事件。所提出的方法可以在该完成框架内灵活地将RGB标记作为超图中的节点，实现多模态超图信息完成。随后，我们通过自注意力机制在不同时间步上聚合超图节点信息，实现多模态特征的有效学习和融合。在单标签和多标签事件分类任务上的大量实验充分验证了我们提出框架的有效性。本文的源代码将在https://github.com/Event-AHU/EvRainDrop上发布。
英文摘要：
Event cameras produce asynchronous event streams that are spatially sparse yet temporally dense. Mainstream event representation learning algorithms typically use event frames, voxels, or tensors as input. Although these approaches have achieved notable progress, they struggle to address the undersampling problem caused by spatial sparsity. In this paper, we propose a novel hypergraph-guided spatio-temporal event stream completion mechanism, which connects event tokens across different times and spatial locations via hypergraphs and leverages contextual information message passing to complete these sparse events. The proposed method can flexibly incorporate RGB tokens as nodes in the hypergraph within this completion framework, enabling multi-modal hypergraph-based information completion. Subsequently, we aggregate hypergraph node information across different time steps through self-attention, enabling effective learning and fusion of multi-modal features. Extensive experiments on both single- and multi-label event classification tasks fully validated the effectiveness of our proposed framework. The source code of this paper will be released on https://github.com/Event-AHU/EvRainDrop.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
