Polymer simulation with both accuracy and efficiency is a challenging ta...
Computer-assisted automatic analysis of diabetic retinopathy (DR) is of ...
In this paper, we consider the problem of open-vocabulary semantic
segme...
This paper presents our solution for the 2nd COVID-19 Severity Detection...
This paper presents our solution for the 2nd COVID-19 Competition, occur...
Automatic diabetic retinopathy (DR) grading based on fundus photography ...
Decision-focused learning (DFL) was recently proposed for stochastic
opt...
The ultra-wide optical coherence tomography angiography (OCTA) has becom...
Weakly-supervised audio-visual violence detection aims to distinguish
sn...
Vision-Language Pre-training (VLP) with large-scale image-text pairs has...
Although audio-visual representation has been proved to be applicable in...
This paper presents our solution for the 2nd COVID-19 Competition, occur...
It has been found that temporal action proposal generation, which aims t...
Visual-only self-supervised learning has achieved significant improvemen...
User sessions empower many search and recommendation tasks on a daily ba...
Multi-label learning in the presence of missing labels (MLML) is a
chall...
Recognizing and localizing events in videos is a fundamental task for vi...
Audio-visual event localization aims to localize an event that is both
a...
We study the problem of event extraction from text data, which requires ...
We study the problem of using (partial) constituency parse trees as synt...
Infrared and visible image fusion, as a hot topic in image processing an...
When watching videos, the occurrence of a visual event is often accompan...
Density regression has been widely employed in crowd counting. However, ...
Fairness has become a central issue for our research community as
classi...
Network embedding aims to learn the low-dimensional representations of
v...