Semi-supervised learning (SSL) seeks to enhance task performance by training on both
labeled and unlabeled data. Mainstream SSL image classification methods mostly optimize …

In recent years, remote sensing scene classification has obtained much attention owing to its
widespread applications. Nevertheless, the existing deep learning-based scene …

The application of large field-of-view (FoV) cameras equipped with fish-eye lenses brings
notable advantages to various real-world computer vision applications, including …

Semi-supervised learning suffers from the imbalance of labeled and unlabeled training data
in the video surveillance scenario. In this paper, we propose a new semi-supervised …

The 2D human pose estimation is a basic visual problem. However, supervised learning of a
model requires massive labeled images, which is expensive and labor-intensive. In this …