Diverse part discovery: Occluded person re-identification with part-aware transformer
Occluded person re-identification (Re-ID) is a challenging task as persons are frequently
occluded by various obstacles or other persons, especially in the crowd scenario. To …
occluded by various obstacles or other persons, especially in the crowd scenario. To …
CM-NAS: Cross-modality neural architecture search for visible-infrared person re-identification
Visible-Infrared person re-identification (VI-ReID) aims to match cross-modality pedestrian
images, breaking through the limitation of single-modality person ReID in dark environment …
images, breaking through the limitation of single-modality person ReID in dark environment …
Person re-identification based on metric learning: a survey
Person re-identification is a challenging research issue in computer vision and has a broad
application prospect in intelligent security. In recent years, with the emergence of large-scale …
application prospect in intelligent security. In recent years, with the emergence of large-scale …
Solving inefficiency of self-supervised representation learning
Self-supervised learning (especially contrastive learning) has attracted great interest due to
its huge potential in learning discriminative representations in an unsupervised manner …
its huge potential in learning discriminative representations in an unsupervised manner …
Deep features for person re-identification on metric learning
Person re-identification, a branch of image retrieval, is an increasingly important public
safety application. When monitoring larger areas, it is crucial to correctly match the same …
safety application. When monitoring larger areas, it is crucial to correctly match the same …
Pose-guided feature learning with knowledge distillation for occluded person re-identification
Occluded person re-identification (ReID) aims to match person images with occlusion. It is
fundamentally challenging because of the serious occlusion which aggravates the …
fundamentally challenging because of the serious occlusion which aggravates the …
Dual distribution alignment network for generalizable person re-identification
Abstract Domain generalization (DG) offers a preferable real-world setting for Person Re-
Identification (Re-ID), which trains a model using multiple source domain datasets and …
Identification (Re-ID), which trains a model using multiple source domain datasets and …
Unsupervised domain adaptation for person re-identification via heterogeneous graph alignment
M Zhang, K Liu, Y Li, S Guo, H Duan, Y Long… - Proceedings of the AAAI …, 2021 - ojs.aaai.org
Unsupervised person re-identification (re-ID) is becoming increasingly popular due to its
power in real-world systems such as public security and intelligent transportation systems …
power in real-world systems such as public security and intelligent transportation systems …
Asymmetric weighted logistic metric learning for hyperspectral target detection
Traditional target detection methods assume that the background spectrum is subject to the
Gaussian distribution, which may only perform well under certain conditions. In addition …
Gaussian distribution, which may only perform well under certain conditions. In addition …
Deep shape-aware person re-identification for overcoming moderate clothing changes
Although person re-identification (person re-id) has advanced substantially in recent years,
most methods are based on the assumption that the identities would not change clothes …
most methods are based on the assumption that the identities would not change clothes …