提出统一框架，融合RGB与事件视频信息，提升跨摄像头行人检索性能。
Paths: Prompt-aware Spatio-temporal Transformer with Hierarchical Multi-modal Fusion for RGB-Event Video Person Re-Identification
- 设计记忆增强主干网络，保持模态特异性身份原型。
- 引入提示感知时空变换器，联合建模空间与时间特征。
- 分层多模态融合策略，兼顾全局与局部判别性信息，适合多模态行人识别任务。
RGB-事件视频行人重识别（RE-VReID）旨在通过互补的RGB视频和事件流，在非重叠摄像头间检索特定行人。现有方法常将空间与时间建模解耦，限制了交互；且全局级多模态融合难以充分挖掘细粒度判别线索。为此，我们提出Paths，一个统一的框架，包含时空建模与分层多模态融合机制。首先设计记忆增强主干网络（MAB），维护模态特异性身份原型，实现稳定的模态内表征学习。其次提出提示感知时空变换器（PST），在统一的Transformer中联合建模空间与时间线索。最后引入分层多模态融合（HMF），在全局与局部层面融合RGB与事件特征。在EvReID、MARS和iLIDS-VID三个公开数据集上的大量实验验证了方法的有效性。代码已开源：https://github.com/Reflection0427/Paths。
原文摘要 · Abstract (English)
RGB-Event Video Person Re-Identification (RE-VReID) aims to retrieve specific person across non-overlapping cameras with complementary RGB videos and event streams. However, existing methods often decouple spatial and temporal modeling, which limits their interaction. In addition, global-level RGB-Event fusion fails to fully exploit fine-grained discriminative cues. To address these issues, we propose Paths, a unified framework with spatio-temporal modeling and hierarchical multi-modal fusion for RE-VReID. Specifically, we first design a Memory-Augmented Backbone (MAB) to maintain modality-specific identity prototypes for stable intra-modal representation learning. Then, we propose a Prompt-aware Spatio-temporal Transformer (PST) to jointly model spatial and temporal cues within a unified Transformer. Finally, we introduce a Hierarchical Multi-modal Fusion (HMF) to integrate RGB and event features at global and local levels. With these modules, our framework can learn robust and discriminative representations for RE-VReID. Extensive experiments on three public RE-VReID benchmarks including EvReID, MARS and iLIDS-VID, demonstrate the effectiveness of our proposed method. The code is available at https://github.com/Reflection0427/Paths.
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。