用跨注意力重排序提升步态识别准确率，尤其改善高排名表现。
CarGait: Cross-Attention based Re-ranking for Gait recognition
- 通过跨注意力分析步态片段间细粒度关联，重排候选列表。
- 在三个数据集上实现Rank-1和Rank-5精度普遍提升，最高增益达3.2%。
- 可无缝接入现有单阶段模型，适合需要高精度的步态识别场景。
步态识别是基于行走姿态识别个体的计算机视觉任务，通常通过排序候选集并测量前K名中的准确率来评估性能。现有模型多为单阶段，使用全局特征表示搜索最近邻，虽在前K名中表现良好，但在出现困难负样本时，最高排名（如Rank-1）性能较差。本文提出CarGait，一种基于跨注意力的重排序方法，通过步态条带间的交叉注意力机制，挖掘细粒度关联，重新排序前K候选列表。该方法可适配现有单阶段模型以提升最终结果。我们在Gait3D、GREW、OU-MVLP三个常用数据集及七种不同步态模型上进行了广泛实验，验证了CarGait在Rank-1、Rank-5上的持续提升，优于现有重排序方法，并建立强基准。
原文摘要 · Abstract (English)
Gait recognition is a computer vision task that identifies individuals based on their walking patterns. Gait recognition performance is commonly evaluated by ranking a gallery of candidates and measuring the accuracy at the top Rank-$K$. Existing models are typically single-staged, i.e. searching for the probe's nearest neighbors in a gallery using a single global feature representation. Although these models typically excel at retrieving the correct identity within the top-$K$ predictions, they struggle when hard negatives appear in the top short-list, leading to relatively low performance at the highest ranks (e.g., Rank-1). In this paper, we introduce CarGait, a Cross-Attention Re-ranking method for gait recognition, that involves re-ordering the top-$K$ list leveraging the fine-grained correlations between pairs of gait sequences through cross-attention between gait strips. This re-ranking scheme can be adapted to existing single-stage models to enhance their final results. We demonstrate the capabilities of CarGait by extensive experiments on three common gait datasets, Gait3D, GREW, and OU-MVLP, and seven different gait models, showing consistent improvements in Rank-1,5 accuracy, superior results over existing re-ranking methods, and strong baselines.
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。