Deep learning-based edge detectors heavily rely on pixel-wise labels whi...
Automatic action quality assessment (AQA) has attracted more interests d...
This paper describes the BLCU-ICALL system used in the SemEval-2022 Task...
Convolutional neural networks have made significant progresses in edge
d...
As a fundamental building block in computer vision, edges can be categor...
This paper addresses semi-supervised semantic segmentation by exploiting...
It is crucial to distinguish mislabeled samples for dealing with noisy
l...
Most existing Grammatical Error Correction (GEC) methods based on
sequen...
Most existing dehazing algorithms often use hand-crafted features or
Con...
The goal of our work is to discover dominant objects without using any
a...
Fine-grained image classification remains challenging due to the large
i...
Hazy images are common in real scenarios and many dehazing methods have ...
Just like many other topics in computer vision, image classification has...
This paper considers the task of thorax disease classification on chest ...