In recent years, person re-identification (ReID) has received much attention since it is a
fundamental task in intelligent surveillance systems and has widespread application …

Intelligent multi-camera video surveillance is a multidisciplinary field related to computer
vision, pattern recognition, signal processing, communication, embedded computing and …

Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging
visual learning tasks, which can be cast as a feature distribution matching problem. With the …

As an instance-level recognition problem, person re-identification (ReID) relies on
discriminative features, which not only capture different spatial scales but also encapsulate …

Attention has become more attractive in person re-identification (ReID) as it is capable of
biasing the allocation of available resources towards the most informative parts of an input …

Person re-identification (re-ID) has become increasingly popular in the community due to its
application and research significance. It aims at spotting a person of interest in other …

Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired
training data and learning discriminative identity-sensitive and view-invariant features in the …

Although supervised person re-identification (Re-ID) methods have shown impressive
performance, they suffer from a poor generalization capability on unseen domains …

Existing person re-identification benchmarks and methods mainly focus on matching
cropped pedestrian images between queries and candidates. However, it is different from …

Video-based person re-identification matches video clips of people across non-overlapping
cameras. Most existing methods tackle this problem by encoding each video frame in its …