Re-Identification With Consistent Attentive Siamese Networks

@article{Zheng2019ReIdentificationWC,
  title={Re-Identification With Consistent Attentive Siamese Networks},
  author={M. Zheng and Srikrishna Karanam and Z. Wu and R. Radke},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={5728-5737}
}
  • M. Zheng, Srikrishna Karanam, +1 author R. Radke
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • We propose a new deep architecture for person re-identification (re-id. [...] Key Method Our key innovations compared to existing, competing methods include (a) a flexible framework design that produces attention with only identity labels as supervision, (b) explicit mechanisms to enforce attention consistency among images of the same person, and (c) a new Siamese framework that integrates attention and attention consistency, producing principled supervisory signals as well as the first mechanism that can…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Uniformity Attentive Learning-Based Siamese Network for Person Re-Identification
    Cross-Correlated Attention Networks for Person Re-Identification
    Pose Guided Gated Fusion for Person Re-identification
    2
    Mixed High-Order Attention Network for Person Re-Identification
    33
    Attention: A Big Surprise for Cross-Domain Person Re-Identification
    3
    IAUnet: Global Context-Aware Feature Learning for Person Re-Identification
    SaADB: A Self-attention Guided ADB Network for Person Re-identification

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 62 REFERENCES
    Harmonious Attention Network for Person Re-identification
    471
    Resource Aware Person Re-identification Across Multiple Resolutions
    114
    Deeply-Learned Part-Aligned Representations for Person Re-identification
    390
    Mask-Guided Contrastive Attention Model for Person Re-identification
    195
    Attention-Aware Compositional Network for Person Re-identification
    165
    Tell Me Where to Look: Guided Attention Inference Network
    129