persion reid 论文列表

Feb 17, 2018 · 2 min read · reid

Key:

(1). Pose-driven, body part alignment, combine whole feature and body part feature, focus on alignment of part model,

(2). Combine image label and human attributes classes, do classification with attributes and identity learning

(3). Based on triplet loss, improve metric learning for an end to end learning

(4). Post-process, re-ranking

  1. AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

  2. Hydraplus-net: Attentive deep features for pedestrian analysis.

  3. Darkrank: Accelerating deep metric learning via cross sample similarities transfer.

  4. Glad: Global-local-alignment descriptor for pedestrian retrieval.

    1. PDC: Pose-driven Deep Convolutional Model for Person Re-identification (ICCV2017)
    2. Spindle: Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion (CVPR 2017)
    3. MSML: Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
    4. DLPA: Deeply-Learned Part-Aligned Representation for Person Re-Identification (ICCV 2017)
    5. DTL: Deep Transfer Learning for Person Re-identification
    6. Unlabeled: Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro (ICCV 2017)
    7. In: In Defense of the Triplet Loss for Person Re-identification
    8. A: A Discriminatively Learned CNN Embedding for Person Re-identification
    9. DGD: Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
    10. Quadruplet: Beyond triplet loss: a deep quadruplet network for person re-identification

  5. AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

  6. Glad: Global-local-alignment descriptor for pedestrian retrieval.

  7. Darkrank: Accelerating deep metric learning via cross sample similarities transfer.

  8. Deep mutual learning

  9. In Defense of the Triplet Loss fr Person Re-identification + Re-Ranking

  10. Hydraplus-net: Attentive deep features for pedestrian analysis.

    1. MSML: Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
    2. In: In Defense of the Triplet Loss for Person Re-identification
    3. APR: Improving Person Re-dentification by Attribute and Identity Learning
    4. PDC: Pose-driven Deep Convolutional Model for Person Re-identification
    5. Unlabeled: Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
    6. DTL: Deep Transfer Learning for Person Re-identification
    7. DLPA: Deeply-Learned Part-Aligned Representation for Person Re-Identification
    8. PIE: Pose Invariant Embedding for Deep Person Re-identification
    9. Re-rank: Re-ranking person re-identification with k-reciprocal encoding
    10. Spindle: Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion