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 …

Multi-modal semantic segmentation significantly enhances AI agents' perception and scene
understanding, especially under adverse conditions like low-light or overexposed …

Recent progress in the text-driven 3D stylization of a single object has been considerably
promoted by CLIP-based methods. However the stylization of multi-object 3D scenes is still …

Wide-range multiscale object detection for multispectral scene perception from a drone
perspective is challenging. Previous RGB-T perception methods directly use backbone …

Understanding indoor scenes is crucial for urban studies. Considering the dynamic nature of
indoor environments effective semantic segmentation requires both real-time operation and …

Multimodal (eg, RGB-Depth/RGB-Thermal) fusion has shown great potential for improving
semantic segmentation in complex scenes (eg, indoor/low-light conditions). Existing …

This paper presents a simple but performant semi-supervised semantic segmentation
approach called CorrMatch. Previous approaches mostly employ complicated training …

While witnessed with rapid development, remote sensing object detection remains
challenging for detecting high aspect ratio objects. This paper shows that large strip …

RGB-D Salient Object Detection (SOD) aims to segment the most prominent areas and
objects in a given pair of RGB and depth images. Most current models adopt a dual-stream …

Incorporating heterogeneous representations from different architectures has facilitated
various vision tasks, eg, some hybrid networks combine transformers and convolutions …