Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-
overlapping cameras. With the advancement of deep neural networks and increasing …

Estimation of the human pose from a monocular camera has been an emerging research
topic in the computer vision community with many applications. Recently, benefiting from the …

One essential problem in skeleton-based action recognition is how to extract discriminative
features over all skeleton joints. However, the complexity of the recent State-Of-The-Art …

Occluded person re-identification (ReID) is a person retrieval task which aims at matching
occluded person images with holistic ones. For addressing occluded ReID, part-based …

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

Person re-identification (re-id) remains challenging due to significant intra-class variations
across different cameras. Recently, there has been a growing interest in using generative …

Attention mechanisms have been found effective for person re-identification (Re-ID).
However, the learned" attentive" features are often not naturally uncorrelated or" diverse" …

Although a significant progress has been witnessed in supervised person re-identification
(re-id), it remains challenging to generalize re-id models to new domains due to the huge …

Existing fully-supervised person re-identification (ReID) methods usually suffer from poor
generalization capability caused by domain gaps. The key to solving this problem lies in …

For person re-identification (re-id), attention mechanisms have become attractive as they
aim at strengthening discriminative features and suppressing irrelevant ones, which …