Popular semi-supervised medical image segmentation networks often suffer from error
supervision from unlabeled data since they usually use consistency learning under different …

Efficient and effective real-world image super-resolution (Real-ISR) is a challenging task
due to the unknown complex degradation of real-world images and the limited computation …

As an essential component of the new energy vehicle battery, current collectors affect the
performance of battery and are crucial to the safety of passengers. The significant …

In image denoising networks, feature scaling is widely used to enlarge the receptive field
size and reduce computational costs. This practice, however, also leads to the loss of high …

Although the impressive performance in visual grounding, the prevailing approaches usually
exploit the visual backbone in a passive way, ie, the visual backbone extracts features with …

Spatial transcriptomics unveils the complex dynamics of cell regulation and transcriptomes,
but it is typically cost-prohibitive. Predicting spatial gene expression from histological images …

RGBT Salient Object Detection (SOD) focuses on common salient regions of a pair of visible
and thermal infrared images. Existing methods perform on the well-aligned RGBT image …

Traffic sign detection is a crucial task in computer vision, finding wide-ranging applications in
intelligent transportation systems, autonomous driving, and traffic safety. However, due to …

Object detection in images captured by unmanned aerial vehicles (UAVs) holds great
potential in various domains, including civilian applications, urban planning, and disaster …

The use of drones to observe ships is an effective means of maritime surveillance. However,
the object scale from drone-captured images changes dramatically, presenting a significant …