Abstract
Video-based Person Re-IDentification (VPReID) aims to retrieve the same person from videos captured by non-overlapping cameras. At extreme far distances, VPReID is highly challenging due to severe resolution degradation, drastic viewpoint variation and inevitable appearance noise. To address these issues, we propose a Scale-Adaptive framework with Shape Priors for VPReID, named SAS-VPReID. The framework is built upon three complementary modules. First, we deploy a Memory-Enhanced Visual Backbone (MEVB) to extract discriminative feature representations, which leverages the CLIP vision encoder and multi-proxy memory. Second, we propose a Multi-Granularity Temporal Modeling (MGTM) to construct sequences at multiple temporal granularities and adaptively emphasize motion cues across scales. Third, we incorporate Prior-Regularized Shape Dynamics (PRSD) to capture body structure dynamics. With these modules, our framework can obtain more discriminative feature representations. Experiments on the VReID-XFD benchmark demonstrate the effectiveness of each module and our final framework ranks the first on the VReID-XFD challenge leaderboard. The source code is available at this https URL.
Abstract (translated)
基于视频的人再识别（VPReID）的目标是从不同摄像头捕获的视频中检索同一个人。在极端远距离情况下，由于分辨率严重退化、视角变化剧烈以及不可避免的外观噪声，VPReID变得非常具有挑战性。为解决这些问题，我们提出了一种名为SAS-VPReID的尺度自适应框架，并引入形状先验。该框架基于三个互补模块构建： 1. 我们部署了一个增强型视觉骨干网（Memory-Enhanced Visual Backbone, MEVB），用于提取判别性的特征表示，它利用了CLIP视觉编码器和多代理记忆。 2. 提出了一个多粒度时间建模（Multi-Granularity Temporal Modeling, MGTM）模块，以在多个时间粒度上构建序列，并适应性地强调不同尺度上的运动线索。 3. 我们融入了一种先验正则化的形状动态模型（Prior-Regularized Shape Dynamics, PRSD），用于捕捉人体结构的变化。 通过这些模块的结合，我们的框架可以获得更具判别性的特征表示。在VReID-XFD基准测试上进行的实验展示了每个模块的有效性，并且我们最终的框架在VReID-XFD挑战排行榜中排名第一。源代码可在上述链接获取。
URL
https://arxiv.org/abs/2601.05535
