Attention-Aware Compositional Network for Person Re-identification

@article{Xu2018AttentionAwareCN,
  title={Attention-Aware Compositional Network for Person Re-identification},
  author={J. Xu and R. Zhao and Feng Zhu and Huaming Wang and Wanli Ouyang},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={2119-2128}
}
  • J. Xu, R. Zhao, +2 authors Wanli Ouyang
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • Person re-identification (ReID) is to identify pedestrians observed from different camera views based on visual appearance. [...] Key Method AACN consists of two main components: Pose-guided Part Attention (PPA) and Attention-aware Feature Composition (AFC). PPA is learned and applied to mask out undesirable background features in pedestrian feature maps. Furthermore, pose-guided visibility scores are estimated for body parts to deal with part occlusion in the proposed AFC module. Extensive experiments with…Expand Abstract
    Mask-Guided Region Attention Network for Person Re-Identification
    A part-based attention network for person re-identification
    Improve Person Re-Identification With Part Awareness Learning
    A Hybrid of Hard and Soft Attention for Person Re-Identification
    Deep Attention Aware Feature Learning for Person Re-Identification
    • 1
    • PDF
    Cross-Camera Person Re-Identification With Body-Guided Attention Network

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 63 REFERENCES
    Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification
    • 410
    • PDF
    Pose-Invariant Embedding for Deep Person Re-Identification
    • 266
    • Highly Influential
    • PDF
    Deeply-Learned Part-Aligned Representations for Person Re-identification
    • 409
    • PDF
    DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
    • 1,405
    • Highly Influential
    • PDF
    Pedestrian Alignment Network for Large-scale Person Re-Identification
    • 247
    • PDF
    End-to-End Comparative Attention Networks for Person Re-Identification
    • 352
    • PDF
    Constrained Deep Metric Learning for Person Re-identification
    • 38
    • PDF
    Transferring a semantic representation for person re-identification and search
    • 168
    • PDF
    Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion
    • 470
    • Highly Influential
    • PDF