Hybrid contrastive learning for unsupervised person re-identification
Unsupervised person re-identification (Re-ID) aims to learn discriminative features without
human-annotated labels. Recently, contrastive learning has provided a new prospect for …
human-annotated labels. Recently, contrastive learning has provided a new prospect for …
Logical relation inference and multiview information interaction for domain adaptation person re-identification
Domain adaptation person re-identification (Re-ID) is a challenging task, which aims to
transfer the knowledge learned from the labeled source domain to the unlabeled target …
transfer the knowledge learned from the labeled source domain to the unlabeled target …
Diversity feature constraint based on heterogeneous data for unsupervised person re-identification
Person re-identification (ReID) based on heterogeneous data aims to search for the same
pedestrian from different modalities. The existing unsupervised heterogeneous ReID …
pedestrian from different modalities. The existing unsupervised heterogeneous ReID …
Mask-aware pseudo label denoising for unsupervised vehicle re-identification
As a significant part of Intelligent Transportation System (ITS), vehicle Re-Identification (Re-
ID) aims to retrieve all target vehicle images captured from non-overlapping cameras …
ID) aims to retrieve all target vehicle images captured from non-overlapping cameras …
Cross-Scatter Sparse Dictionary Pair Learning for Cross-Domain Classification
In cross-domain recognition tasks, the divergent distributions of data acquired from various
domains degrade the effectiveness of knowledge transfer. Additionally, in practice, cross …
domains degrade the effectiveness of knowledge transfer. Additionally, in practice, cross …
Weakly supervised contrastive learning for unsupervised vehicle reidentification
Reidentification (Re-id) of vehicles in a multicamera system is an essential process for traffic
control automation. Previously, there have been efforts to reidentify vehicles based on shots …
control automation. Previously, there have been efforts to reidentify vehicles based on shots …
Inter-cluster and intra-cluster joint optimization for unsupervised cross-domain person re-identification
J Sun, Y Li, H Chen, X Zhu, Y Peng, Y Peng - Knowledge-Based Systems, 2022 - Elsevier
The purpose of unsupervised cross-domain (UCD) person re-identification (re-ID) is to adapt
the well pre-trained model on the labeled source domain to the unlabeled target domain …
the well pre-trained model on the labeled source domain to the unlabeled target domain …
Discriminative Identity-Feature Exploring and Differential Aware Learning for Unsupervised Person Re-Identification
Unsupervised person re-identification (Re-ID) aims to learn discriminative representations
for person retrieval from unlabeled data. Currently, state-of-the-art techniques accomplish …
for person retrieval from unlabeled data. Currently, state-of-the-art techniques accomplish …
Structured serialization semantic transfer network for unsupervised cross-domain recognition and retrieval
D Song, Y Yang, W Li, X Li, M Liu, AA Liu - Information Processing & …, 2024 - Elsevier
Unsupervised domain adaptation aims to apply a model trained from labeled datasets to
unlabeled datasets, which still exist challenges to minimize the degree of inter-domain …
unlabeled datasets, which still exist challenges to minimize the degree of inter-domain …
Domain-class correlation decomposition for generalizable person re-identification
Domain generalization in person re-identification is a highly important meaningful and
practical task in which a model trained with data from several source domains is expected to …
practical task in which a model trained with data from several source domains is expected to …