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 ...
Spectral graph convolutional neural networks (GCNNs) have been producing...
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...
This paper presents our solution for the 2nd COVID-19 Competition, occur...
Visual-only self-supervised learning has achieved significant improvemen...
Recognizing and localizing events in videos is a fundamental task for vi...
When watching videos, the occurrence of a visual event is often accompan...
In this paper, we establish a novel bottom-up cue named Convex Hull Over...