Visual semantic segmentation aims at separating a visual sample into diverse blocks with
specific semantic attributes and identifying the category for each block, and it plays a crucial …

Previous works have shown that increasing the window size for Transformer-based image
super-resolution models (eg, SwinIR) can significantly improve the model performance but …

Salient object detection (SOD) and camouflaged object detection (COD) are related yet
distinct binary map** tasks. These tasks involve multiple modalities sharing …

Video segmentation—partitioning video frames into multiple segments or objects—plays a
critical role in a broad range of practical applications, from enhancing visual effects in movie …

The recently introduced Segment Anything Model (SAM) combines a clever architecture and
large quantities of training data to obtain remarkable image segmentation capabilities …

Transformer models have shown great success handling long-range interactions, making
them a promising tool for modeling video. However, they lack inductive biases and scale …

Appearance and motion are two important sources of information in video object
segmentation (VOS). Previous methods mainly focus on using simplex solutions, lowering …

We present the first comprehensive video polyp segmentation (VPS) study in the deep
learning era. Over the years, developments in VPS are not moving forward with ease due to …

Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as
independent information and design separate networks for feature extraction from each …

How to identify and segment camouflaged objects from the background is challenging.
Inspired by the multi-head self-attention in Transformers, we present a simple masked …