With the rapid development of deep learning techniques, deep convolutional neural
networks (DCNNs) have become more important for object detection. Compared with …

Concealed scene understanding (CSU) is a hot computer vision topic aiming to perceive
objects exhibiting camouflage. The current boom in terms of techniques and applications …

Global epidemic crises, such as the coronavirus (COVID-19), usually expose small and
medium enterprises (SMEs) to various kinds of challenges and may put their lives at risk …

As an essential problem in computer vision, salient object detection (SOD) has attracted an
increasing amount of research attention over the years. Recent advances in SOD are …

In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D
saliency detection by learning from the data labeling process. Existing RGB-D saliency …

Being able to learn dense semantic representations of images without supervision is an
important problem in computer vision. However, despite its significance, this problem …

The last decade has witnessed a growing interest in video salient object detection (VSOD).
However, the research community long-term lacked a well-established VSOD dataset …

Abstract Deep Supervised Salient Object Detection (SSOD) excessively relies on large-
scale annotated pixel-level labels which consume intensive labour acquiring high quality …

Compared with laborious pixel-wise dense labeling, it is much easier to label data by
scribbles, which only costs 1 2 seconds to label one image. However, using scribble labels …

Convolutional neural network (CNN)-based encoder-decoder models have profoundly
inspired recent works in the field of salient object detection (SOD). With the rapid …