针对跨视角视频行人重识别难题，提出轻量级高效框架提升鲁棒性。
Seeing Across Time and Views: Multi-Temporal Cross-View Learning for Robust Video Person Re-Identification
- 通过七个模块化组件协同优化视角、尺度与时间一致性
- 在AG-VPReID上达到顶尖性能，189帧/秒保持实时效率
- 适合多源监控场景下的跨视角身份追踪应用
基于视频的跨视角行人重识别（ReID）在异构视角场景（如空地监控）中仍面临挑战，主要源于极端视角变化、尺度差异及时间不一致。为此，本文提出参数高效的MTF-CVReID框架，在ViT-B/16基础上引入七种互补模块：(1) 跨流特征归一化（CSFN）校正摄像头与视角偏差；(2) 多分辨率特征调和（MRFH）稳定不同高度下的尺度变化；(3) 无偏身份记忆模块（IAMM）强化持久身份特征；(4) 时序动态建模（TDM）实现运动感知的短期时序编码；(5) 跨视角特征对齐（IVFA）实现视角不变表示；(6) 分层时序模式学习（HTPL）捕捉多尺度时序规律；(7) 多视角身份一致性学习（MVICL）采用对比学习强化跨视角身份一致性。尽管仅增加约200万参数和0.7 GFLOPs，MTF-CVReID仍保持189 FPS实时效率，并在所有高度层级的AG-VPReID基准上实现最先进性能，且在G2A-VReID与MARS数据集上展现强跨数据集泛化能力。结果表明，精心设计的适配模块可显著提升跨视角鲁棒性与时序一致性，同时不牺牲计算效率。代码已开源。
原文摘要 · Abstract (English)
Video-based person re-identification (ReID) in cross-view domains (for example, aerial-ground surveillance) remains an open problem because of extreme viewpoint shifts, scale disparities, and temporal inconsistencies. To address these challenges, we propose MTF-CVReID, a parameter-efficient framework that introduces seven complementary modules over a ViT-B/16 backbone. Specifically, we include: (1) Cross-Stream Feature Normalization (CSFN) to correct camera and view biases; (2) Multi-Resolution Feature Harmonization (MRFH) for scale stabilization across altitudes; (3) Identity-Aware Memory Module (IAMM) to reinforce persistent identity traits; (4) Temporal Dynamics Modeling (TDM) for motion-aware short-term temporal encoding; (5) Inter-View Feature Alignment (IVFA) for perspective-invariant representation alignment; (6) Hierarchical Temporal Pattern Learning (HTPL) to capture multi-scale temporal regularities; and (7) Multi-View Identity Consistency Learning (MVICL) that enforces cross-view identity coherence using a contrastive learning paradigm. Despite adding only about 2 million parameters and 0.7 GFLOPs over the baseline, MTF-CVReID maintains real-time efficiency (189 FPS) and achieves state-of-the-art performance on the AG-VPReID benchmark across all altitude levels, with strong cross-dataset generalization to G2A-VReID and MARS datasets. These results show that carefully designed adapter-based modules can substantially enhance cross-view robustness and temporal consistency without compromising computational efficiency. The source code is available at https://github.com/MdRashidunnabi/MTF-CVReID
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。