Abstract: Semantic segmentation ... of the input image. It adaptively generates two masks to separate high- and low-frequency components, therefore providing optimal details and contextual ...

Abstract: Referring Video Object Segmentation (RVOS) aims at segmenting out the described object in a video clip according to given expression. The task requires methods to effectively fuse ...

However, due to the inherent unique optical characteristics and high noise in underwater imagery, existing underwater instance segmentation models struggle to accurately capture the global and local ...

IteRPrimE is a novel framework for zero-shot referring image segmentation that leverages an Iterative Grad-CAM Refinement Strategy (IGRS) and a Primary Word Emphasis Module (PWEM) to improve ...

Laboratory of Mathematics and Complex Systems (Ministry of Education of China), School of Mathematical Sciences, Beijing Normal University, Beijing, P. R. China ...

We proposed a new 3D bi-directional framework to learn deep 3D features for medical image semantic segmentation. • We designed a novel attention mechanism specifically suitable for network training ...

Each tracker was configured using the default parameters from their official repositories. Multi-object tracking solutions today depend heavily on the computational capabilities of the underlying ...