Related papers: Structure-Semantic Decoupled Modulation of Global …
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…
Exploring the semantic context in scene images is essential for indoor scene recognition. However, due to the diverse intra-class spatial layouts and the coexisting inter-class objects, modeling contextual relationships to adapt various…
While Multimodal Large Language Models (MLLMs) excel in semantic tasks, they frequently lack the "spatial sense" essential for sophisticated geometric reasoning. Current models typically suffer from exorbitant modality-alignment costs and…
Building 3D reconstruction from remote sensing images has a wide range of applications in smart cities, photogrammetry and other fields. Methods for automatic 3D urban building modeling typically employ multi-view images as input to…
Land cover maps generated from semantic segmentation of high-resolution remotely sensed images have drawn mucon in the photogrammetry and remote sensing research community. Currently, massive fine-resolution remotely sensed (FRRS) images…
Satellite-terrestrial communications are severely constrained by high path loss, limited spectrum resources, and time-varying channel conditions, rendering conventional bit-level transmission schemes inefficient and fragile, particularly in…
Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…
Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this…
Automated segmentation of Martian landslides, particularly in tectonically active regions such as Valles Marineris,is important for planetary geology, hazard assessment, and future robotic exploration. However, detecting landslides from…
Recent advances in natural-domain multi-modal large language models (MLLMs) have demonstrated effective spatial reasoning through visual and textual prompting. However, their direct transfer to remote sensing (RS) is hindered by…
Recent years have witnessed remarkable progress in multimodal learning within computational pathology. Existing models primarily rely on vision and language modalities; however, language alone lacks molecular specificity and offers limited…
Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…
Simultaneous Localization and Mapping (SLAM) has been crucial across various domains, including autonomous driving, mobile robotics, and mixed reality. Dense visual SLAM, leveraging RGB-D camera systems, offers advantages but faces…
Semantic segmentation of large-scale 3D point clouds is crucial for applications such as autonomous driving and urban digital twins. However, the sparse sampling pattern of LiDAR and the view-dependent geometric distortion in image…
Existing image foundation models are not optimized for spherical images having been trained primarily on perspective images. PanoSAMic integrates the pre-trained Segment Anything (SAM) encoder to make use of its extensive training and…
Semantic segmentation is a core computer vision problem, but the high costs of data annotation have hindered its wide application. Weakly-Supervised Semantic Segmentation (WSSS) offers a cost-efficient workaround to extensive labeling in…
City models and height maps of urban areas serve as a valuable data source for numerous applications, such as disaster management or city planning. While this information is not globally available, it can be substituted by digital surface…
Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from…
As the electromagnetic environment becomes increasingly complex, Global Navigation Satellite Systems (GNSS) face growing threats from sophisticated jamming interference. Although Deep Learning (DL) effectively identifies basic interference,…
Unified hyperspectral image (HSI) restoration aims to recover various degraded HSIs using a single model, offering great practical value. However, existing methods often depend on explicit degradation priors (e.g., degradation labels) as…