Wei Zhang, Qinxuan Luo, Boqiang Xu, Qi Li, Zhenan Sun. CAPS: A Contextual Aligned End-to-end Anchor-free Framework for Efficient Person SearchJ. Machine Intelligence Research, 2026, 23(6): 1367-1381. DOI: 10.1007/s11633-025-1603-z
Citation: Wei Zhang, Qinxuan Luo, Boqiang Xu, Qi Li, Zhenan Sun. CAPS: A Contextual Aligned End-to-end Anchor-free Framework for Efficient Person SearchJ. Machine Intelligence Research, 2026, 23(6): 1367-1381. DOI: 10.1007/s11633-025-1603-z

CAPS: A Contextual Aligned End-to-end Anchor-free Framework for Efficient Person Search

  • Person search presents unique challenges by requiring simultaneous pedestrian detection and identification within unified frameworks. While anchor-free models have emerged to address computational inefficiencies from dense object anchors, their simplified architectures often suffer from object conflicts and region misalignment issues. To resolve these limitations, we introduce CAPS, a novel contextually aligned end-to-end anchor-free person search framework that explores more contextual cues in scene feature for identification. Our architecture preserves spatial-contextual information through dedicated identity branches that explicitly align features along channel and spatial dimensions. We further introduce region-aligned knowledge distillation to ensure spatial robustness, transferring the teacher model′s discriminative capabilities via multi-level adapters. This strategy decouples intensive training supervision from efficient deployment inference, achieving an optimal balance between performance and speed. Extensive experiments demonstrate state-of-the-art performance of CAPS on CUHK-SYSU and PRW benchmarks and validate our approach′s simultaneous optimization of accuracy, computational efficiency, and architectural simplicity.
  • loading

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return