This paper aims to address the problem of pre-training for person re-identification (Re-ID)
with noisy labels. To setup the pre-training task, we apply a simple online multi-object …

Recent studies show that, both explicit deep feature matching as well as large-scale and
diverse training data can significantly improve the generalization of person re-identification …

Construction sites are highly hazardous due to the dynamic interaction between workers
and moving equipment, with high fatality rates caused by collision and falling from height …

This paper proposes a novel transformer-based framework to generate accurate class-
specific object localization maps for weakly supervised semantic segmentation (WSSS) …

Supervised person re-identification (re-id) methods require expensive manual labeling
costs. Although unsupervised re-id methods can reduce the requirement of the labeled …

Person re-identification (re-ID) in the scenario with large spatial and temporal spans has not
been fully explored. This fact partially occurs because existing benchmark datasets were …

Person re-identification (ReID) plays a crucial role in video surveillance with the aim to
search a specific person across disjoint cameras, and it has progressed notably in recent …

Self-supervised learning (especially contrastive learning) has attracted great interest due to
its huge potential in learning discriminative representations in an unsupervised manner …