Related papers: RTFDNet: Fusion-Decoupling for Robust RGB-T Segmen…
Visual place classification from a first-person-view monocular RGB image is a fundamental problem in long-term robot navigation. A difficulty arises from the fact that RGB image classifiers are often vulnerable to spatial and appearance…
Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and…
Mapping and localization are essential capabilities of robotic systems. Although the majority of mapping systems focus on static environments, the deployment in real-world situations requires them to handle dynamic objects. In this paper,…
Semantic segmentation of ultra-high-resolution (UHR) remote sensing imagery is critical for applications like environmental monitoring and urban planning but faces computational and optimization challenges. Conventional methods either lose…
Audio-visual speech separation has gained significant traction in recent years due to its potential applications in various fields such as speech recognition, diarization, scene analysis and assistive technologies. Designing a lightweight…
Understanding indoor scenes is crucial for urban studies. Considering the dynamic nature of indoor environments, effective semantic segmentation requires both real-time operation and high accuracy.To address this, we propose AsymFormer, a…
The encoder-decoder networks are commonly used in medical image segmentation due to their remarkable performance in hierarchical feature fusion. However, the expanding path for feature decoding and spatial recovery does not consider the…
Remote sensing image change detection (RSCD) is crucial for monitoring dynamic surface changes, with applications ranging from environmental monitoring to disaster assessment. While traditional CNN-based methods have improved detection…
Deep learning-based techniques for the analysis of multimodal remote sensing data have become popular due to their ability to effectively integrate complementary spatial, spectral, and structural information from different sensors.…
Haze obscures remote sensing images, hindering valuable information extraction. To this end, we propose RSHazeNet, an encoder-minimal and decoder-minimal framework for efficient remote sensing image dehazing. Specifically, regarding the…
We propose a new deep learning architecture for the tasks of semantic segmentation and depth prediction from RGB-D images. We revise the state of art based on the RGB and depth feature fusion, where both modalities are assumed to be…
Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data…
RGB-D salient object detection (SOD) aims to detect the prominent regions by jointly modeling RGB and depth information. Most RGB-D SOD methods apply the same type of backbones and fusion modules to identically learn the multimodality and…
Real-time semantic segmentation has received considerable attention due to growing demands in many practical applications, such as autonomous vehicles, robotics, etc. Existing real-time segmentation approaches often utilize feature fusion…
Perception is crucial for robots that act in real-world environments, as autonomous systems need to see and understand the world around them to act properly. Panoptic segmentation provides an interpretation of the scene by computing a…
Multispectral imaging plays a critical role in a range of intelligent transportation applications, including advanced driver assistance systems (ADAS), traffic monitoring, and night vision. However, accurate visible and thermal (RGB-T)…
In view of the problems that existing salient object detection (SOD) methods are prone to losing details, blurring edges, and insufficient fusion of single-modal information in complex scenes, this paper proposes a dynamic uncertainty…
In multimodal graph learning, graph structures that integrate information from multiple sources, such as vision and text, can more comprehensively model complex entity relationships. However, the continuous growth of their data scale poses…
Point clouds and images could provide complementary information when representing 3D objects. Fusing the two kinds of data usually helps to improve the detection results. However, it is challenging to fuse the two data modalities, due to…
RGB-T tracking leverages the complementary strengths of RGB and thermal infrared (TIR) modalities to address challenging scenarios such as low illumination and adverse weather. However, existing methods often fail to effectively integrate…