Generative adversarial networks (GANs) present a way to learn deep representations
without extensively annotated training data. These networks achieve learning through …

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

Most state-of-the-art action localization systems process each action proposal individually,
without explicitly exploiting their relations during learning. However, the relations between …

RGB-Infrared person re-identification (RGB-IR ReID) is a challenging cross-modality
retrieval problem, which aims at matching the person-of-interest over visible and infrared …

Cross-modality person re-identification (cm-ReID) is a challenging but key technology for
intelligent video analysis. Existing works mainly focus on learning modality-shared …

In this paper, we propose a novel Feature Decomposition and Reconstruction Learning
(FDRL) method for effective facial expression recognition. We view the expression …

Temporal action proposal generation plays an important role in video action understanding,
which requires localizing high-quality action content precisely. However, generating …

In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset"
LUPerson" and make the first attempt of performing unsupervised pre-training for improving …