Related papers: Structure-Semantic Decoupled Modulation of Global …

Graph representation learning has emerged as a cornerstone for tasks like node classification and link prediction, yet prevailing self-supervised learning (SSL) methods face challenges such as computational inefficiency, reliance on…

Self-supervised representation learning techniques utilize large datasets without semantic annotations to learn meaningful, universal features that can be conveniently transferred to solve a wide variety of downstream supervised tasks. In…

Simultaneous Localization and Mapping (SLAM) is one of the most essential techniques in many real-world robotic applications. The assumption of static environments is common in most SLAM algorithms, which however, is not the case for most…

The impacts of climate change are felt by most critical systems, such as infrastructure, ecological systems, and power-plants. However, contemporary Earth System Models (ESM) are run at spatial resolutions too coarse for assessing effects…

Hyperspectral single image super-resolution (SISR) is a challenging task due to the difficulty of restoring fine spatial details while preserving spectral fidelity across a wide range of wavelengths, which limits the performance of…

Cross-modal metric learning is a prominent research topic that bridges the semantic heterogeneity between vision and language. Existing methods frequently utilize simple cosine or complex distance metrics to transform the pairwise features…

Deploying depth estimation networks in the real world requires high-level robustness against various adverse conditions to ensure safe and reliable autonomy. For this purpose, many autonomous vehicles employ multi-modal sensor systems,…

Geometric Deep Learning has recently made striking progress with the advent of continuous Deep Implicit Fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid,…

Neural Surface Reconstruction has become a standard methodology for indoor 3D reconstruction, with Signed Distance Functions (SDFs) proving particularly effective for representing scene geometry. A variety of applications require a detailed…

Existing deep learning methods for remote sensing image fusion often suffer from poor generalization when applied to unseen datasets due to the limited availability of real training data and the domain gap between different satellite…

Large language models (LLMs) are advanced AI systems applied across various domains, including NLP, information retrieval, and recommendation systems. Despite their adaptability and efficiency, LLMs have not been extensively explored for…

Cross-resolution land cover mapping aims to produce high-resolution semantic predictions from coarse or low-resolution supervision, yet the severe resolution mismatch makes effective learning highly challenging. Existing weakly supervised…

Recently the dense Simultaneous Localization and Mapping (SLAM) based on neural implicit representation has shown impressive progress in hole filling and high-fidelity mapping. Nevertheless, existing methods either heavily rely on known…

Spatial audio understanding is essential for accurately perceiving and interpreting acoustic environments. However, existing audio-language models exhibit limitations in processing spatial audio and perceiving spatial acoustic scenes. To…

Vision Transformers face a fundamental limitation: standard self-attention jointly processes spatial and channel dimensions, leading to entangled representations that prevent independent modeling of structural and semantic dependencies.…

Sound can convey significant information for spatial reasoning in our daily lives. To endow deep networks with such ability, we address the challenge of dense indoor prediction with sound in both 2D and 3D via cross-modal knowledge…

Publicly available satellite imagery, such as Sentinel- 2, often lacks the spatial resolution required for accurate analysis of remote sensing tasks including urban planning and disaster response. Current super-resolution techniques are…

Semantic segmentation of remote sensing imagery is a fundamental task in computer vision, supporting a wide range of applications such as land use classification, urban planning, and environmental monitoring. However, this task is often…

Stereo superpixel segmentation aims at grouping the discretizing pixels into perceptual regions through left and right views more collaboratively and efficiently. Existing superpixel segmentation algorithms mostly utilize color and spatial…

Domain Generalization Semantic Segmentation (DGSS) in spectral remote sensing is severely challenged by spectral shifts across diverse acquisition conditions, which cause significant performance degradation for models deployed in unseen…