Ultrasound (US) imaging is indispensable in clinical practice. To diagno...
Google's Bard has emerged as a formidable competitor to OpenAI's ChatGPT...
We propose a novel approach for RGB-D salient instance segmentation usin...
In this paper, we consider the problem of referring camouflaged object
d...
Deep neural networks have been widely applied in dichotomous medical ima...
To date, the widely-adopted way to perform fixation collection in panopt...
The Segment Anything Model (SAM) is the first foundation model for gener...
Recently, indiscernible scene understanding has attracted a lot of atten...
Concealed scene understanding (CSU) is a hot computer vision topic aimin...
Segmenting anything is a ground-breaking step toward artificial general
...
The burgeoning field of camouflaged object detection (COD) seeks to iden...
Daily images may convey abstract meanings that require us to memorize an...
Depth cues are known to be useful for visual perception. However, direct...
How to identify and segment camouflaged objects from the background is
c...
We present a masked vision-language transformer (MVLT) for fashion-speci...
We present OSFormer, the first one-stage transformer framework for
camou...
In this paper, we present a novel end-to-end group collaborative learnin...
This paper introduces DGNet, a novel deep framework that exploits object...
In the deep learning era, we present the first comprehensive video polyp...
Spotting camouflaged objects that are visually assimilated into the
back...
We propose a new video camouflaged object detection (VCOD) framework tha...
We present a systematic study on a new task called dichotomous image
seg...
The goal of this paper is to conduct a comprehensive study on the facial...
Thanks to the rapid advances in deep learning techniques and the wide
av...
Existing RGB-D saliency detection models do not explicitly encourage RGB...
RGB-D saliency detection has attracted increasing attention, due to its
...
Most polyp segmentation methods use CNNs as their backbone, leading to t...
Appearance and motion are two important sources of information in video
...
Exploring to what humans pay attention in dynamic panoramic scenes is us...
Existing video polyp segmentation (VPS) models typically employ convolut...
This paper identifies and addresses a serious design bias of existing sa...
Camouflaged object segmentation (COS) aims to identify objects that are
...
The transformer networks, which originate from machine translation, are
...
Automatically detecting/segmenting object(s) that blend in with their
su...
We present a new vision-language (VL) pre-training model dubbed Kaleido-...
Camouflage is a key defence mechanism across species that is critical to...
We present the first systematic study on concealed object detection (COD...
Albeit current salient object detection (SOD) works have achieved fantas...
Although deep models have greatly improved the accuracy and robustness o...
Salient object detection (SOD) is a long-standing research topic in comp...
We propose the first stochastic framework to employ uncertainty for RGB-...
Existing RGB-D salient object detection (SOD) models usually treat RGB a...
Salient object detection (SOD), which simulates the human visual percept...
Most existing RGB-D salient object detection (SOD) methods focus on the
...
Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causi...
This paper proposes a novel joint learning and densely-cooperative fusio...
Recently, the novel coronavirus 2019 (COVID-19) has caused a pandemic di...
While it is trivial for humans to quickly assess the perceptual similari...
The use of RGB-D information for salient object detection has been explo...
Directly learning features from the point cloud has become an active res...