Unlike Conventional Zero-Shot Learning (CZSL) which only focuses on the recognition of
unseen classes by using a classifier trained on seen classes and semantic embeddings …

Object detection is a fundamental task in computer vision that involves accurately locating
and classifying objects within images or video frames. In remote sensing, this task is …

We propose MoBox, a low-cost solution for semi-supervised video object segmentation that
requires only bounding boxes as manual annotations for training. Built upon a mature semi …

The Visual Language Model, known for its robust cross-modal capabilities, has been
extensively applied in various computer vision tasks. In this paper, we explore the use of …

Wireless Technology Recognition (WTR) distinguishes different wireless technologies by
analyzing characteristic features extracted from radio signals. While deep learning (DL) …

Existing semi-supervised medical image segmentation methods based on the teacher-
student model often employ unweighted pixel-level consistency loss, neglecting the varying …

Diffusion models show great potential in solving inverse problems, including MRI
reconstruction. With its unique characteristics, medical imaging demands both efficiency and …

Fine-grained action recognition typically faces challenges with lower inter-class variances
and higher intra-class variances. Supervised contrastive learning is inherently suitable for …

This paper proposes an end-to-end video saliency prediction network model, termed TM2SP-
Net (Transformer-based Multi-level Spatiotemporal Feature Pyramid Network). Leveraging …

Existing pyramid-based upsamplers (eg. SemanticFPN), although efficient, usually produce
less accurate results compared to dilation-based models when using the same backbone …