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
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
Hydraplus-net: Attentive deep features for pedestrian analysis.
Darkrank: Accelerating deep metric learning via cross sample similarities transfer.
Glad: Global-local-alignment descriptor for pedestrian retrieval.
PDC: Pose-driven Deep Convolutional Model for Person Re-identification (ICCV2017)
Spindle: Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion (CVPR 2017)
MSML: Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
DLPA: Deeply-Learned Part-Aligned Representation for Person Re-Identification (ICCV 2017)
DTL: Deep Transfer Learning for Person Re-identification
Unlabeled: Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro (ICCV 2017)
In: In Defense of the Triplet Loss for Person Re-identification
A: A Discriminatively Learned CNN Embedding for Person Re-identification
DGD: Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
Quadruplet: Beyond triplet loss: a deep quadruplet network for person re-identification
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
Glad: Global-local-alignment descriptor for pedestrian retrieval.
Darkrank: Accelerating deep metric learning via cross sample similarities transfer.
Deep mutual learning
In Defense of the Triplet Loss fr Person Re-identification + Re-Ranking
Hydraplus-net: Attentive deep features for pedestrian analysis.
MSML: Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
In: In Defense of the Triplet Loss for Person Re-identification
APR: Improving Person Re-identification by Attribute and Identity Learning
PDC: Pose-driven Deep Convolutional Model for Person Re-identification
Unlabeled: Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
DTL: Deep Transfer Learning for Person Re-identification
DLPA: Deeply-Learned Part-Aligned Representation for Person Re-Identification
PIE: Pose Invariant Embedding for Deep Person Re-identification
Re-rank: Re-ranking person re-identification with k-reciprocal encoding
Spindle: Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion