Accurate polyp delineation in colonoscopy is crucial for assisting in
di...
A key challenge with procedure planning in instructional videos lies in ...
Transformer-based methods have exhibited remarkable potential in single ...
Recently, large vision model, Segment Anything Model (SAM), has
revoluti...
Tuberculosis (TB) is a major global health threat, causing millions of d...
For safety, AI systems in health undergo thorough evaluations before
dep...
AI models have shown promise in many medical imaging tasks. However, our...
Nighttime image dehazing is a challenging task due to the presence of
mu...
A lightweight underwater image enhancement network is of great significa...
Cardiovascular diseases (CVDs) are responsible for a large proportion of...
Recently, indiscernible scene understanding has attracted a lot of atten...
Self-supervised learning is attracting large attention in point cloud
un...
Varicolored haze caused by chromatic casts poses haze removal and depth
...
Underwater images typically experience mixed degradations of brightness ...
Sentiment transfer aims at revising the input text to satisfy a given
se...
Large language models (LLMs) have demonstrated impressive capabilities i...
Ensemble learning serves as a straightforward way to improve the perform...
Artificial Intelligence (AI) is having a tremendous impact across most a...
Large sparse linear algebraic systems can be found in a variety of scien...
Recently, image restoration transformers have achieved comparable perfor...
Single image desnowing is a common yet challenging task. The complex sno...
Event extraction is an important work of medical text processing. Accord...
Current efficient LiDAR-based detection frameworks are lacking in exploi...
The essence of video semantic segmentation (VSS) is how to leverage temp...
External eye photos were recently shown to reveal signs of diabetic reti...
Image restoration of snow scenes in severe weather is a difficult task. ...
In winter scenes, the degradation of images taken under snow can be pret...
Recent progress in Medical Artificial Intelligence (AI) has delivered sy...
Removing adverse weather conditions like rain, fog, and snow from images...
Lung cancer has the highest mortality rate of deadly cancers in the worl...
The contextual information plays a core role in semantic segmentation. A...
Speech enhancement (SE) methods mainly focus on recovering clean speech ...
Underwater Image Rendering aims to generate a true-to-life underwater im...
Deep learning-based methods have made significant achievements for image...
Boundaries are among the primary visual cues used by human and computer
...
Recognizing facts is the most fundamental step in making judgments, henc...
This paper described the PCG-AIID system for L3DAS22 challenge in Task 1...
Complex spectrum and magnitude are considered as two major features of s...
Existing salient object detection (SOD) methods mainly rely on CNN-based...
Due to the fact that fully supervised semantic segmentation methods requ...
This paper jointly resolves two problems in vision transformer: i) the
c...
We tackle the low-efficiency flaw of vision transformer caused by the hi...
Significant progress on the crowd counting problem has been achieved by
...
Tuberculosis (TB) is a top-10 cause of death worldwide. Though the WHO
r...
We develop and rigorously evaluate a deep learning based system that can...
Recent advances regarding question answering and reading comprehension h...
The high computational cost of neural networks has prevented recent succ...
Recent progress on salient object detection (SOD) mainly benefits from
m...
Diabetes-related retinal conditions can be detected by examining the
pos...
Deriving interpretable prognostic features from deep-learning-based
prog...