MMGait：迈向多模态步态识别
MMGait: Towards Multi-Modal Gait Recognition
为视觉研究者提供了一个覆盖 RGB、深度、红外、激光雷达与 4D 雷达五种传感器、共十二种模态的步态识别基准，可用于研究跨模态检索与模态互补性；其 OmniGait 基线通过共享嵌入空间统一单模态、跨模态与多模态三种范式，可作为多模态表征对齐的可复用思路。
原文依据 we present MMGait, a comprehensive multi-modal gait benchmark integrating data from five heterogeneous sensors
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论步态识别已成为一种强大的生物特征识别技术，可在无需用户配合的情况下远距离识别个体。现有方法大多主要依赖 RGB 衍生模态，在需要多模态协同与跨模态检索的真实场景中存在不足。为应对这些挑战，我们提出 MMGait，一个综合性的多模态步态基准，整合了来自五种异构传感器的数据，包括 RGB 相机、深度相机、红外相机、激光雷达扫描仪和 4D 雷达系统。MMGait 包含十二种模态、来自 725 名受试者的 334,060 条序列，支持在几何、光度与运动域上进行系统性探索。基于 MMGait，我们对单模态、跨模态与多模态范式开展了广泛评测，以分析模态的鲁棒性与互补性。此外，我们引入了一项新任务——全模态步态识别（Omni Multi-Modal Gait Recognition），旨在将上述三种步态识别范式统一到单一模型中。我们还提出了一个简单而强大的基线 OmniGait，它在多种模态之间学习共享嵌入空间，并取得了有前景的识别性能。MMGait 基准、代码库与预训练检查点已在 https://github.com/BNU-IVC/MMGait 公开。
英文原文摘要 1317 字符
Gait recognition has emerged as a powerful biometric technique for identifying individuals at a distance without requiring user cooperation. Most existing methods focus primarily on RGB-derived modalities, which fall short in real-world scenarios requiring multi-modal collaboration and cross-modal retrieval. To overcome these challenges, we present MMGait, a comprehensive multi-modal gait benchmark integrating data from five heterogeneous sensors, including an RGB camera, a depth camera, an infrared camera, a LiDAR scanner, and a 4D Radar system. MMGait contains twelve modalities and 334,060 sequences from 725 subjects, enabling systematic exploration across geometric, photometric, and motion domains. Based on MMGait, we conduct extensive evaluations on single-modal, cross-modal, and multi-modal paradigms to analyze modality robustness and complementarity. Furthermore, we introduce a new task, Omni Multi-Modal Gait Recognition, which aims to unify the above three gait recognition paradigms within a single model. We also propose a simple yet powerful baseline, OmniGait, which learns a shared embedding space across diverse modalities and achieves promising recognition performance. The MMGait benchmark, codebase, and pretrained checkpoints are publicly available at https://github.com/BNU-IVC/MMGait.