相关论文: A Benchmark for Multi-Lingual Vision-Language Lear…

Accurate interpretation of land-cover changes in multi-temporal satellite imagery is critical for real-world scenarios. However, existing methods typically provide only one-shot change masks or static captions, limiting their ability to…

We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded…

Large vision-language models (LVLMs) are increasingly being applied to multi-view image inputs captured from diverse viewpoints. However, despite this growing use, current LVLMs often confuse or mismatch visual information originating from…

Recent advances in large language models (LLMs) and vision-language models (LVLMs) have shown promise across many tasks, yet their scientific reasoning capabilities remain untested, particularly in multimodal settings. We present…

Recently, Referring Remote Sensing Image Segmentation (RRSIS) has aroused wide attention. To handle drastic scale variation of remote targets, existing methods only use the full image as input and nest the saliency-preferring techniques of…

Vision-langugage models (VLMs) have shown strong performance in computer vision (CV), yet their performance on remote sensing (RS) data remains limited due to the lack of large-scale, multi-sensor RS image-text datasets with diverse textual…

Referring Image Segmentation (RIS) is a fundamental vision-language task that outputs object masks based on text descriptions. Many works have achieved considerable progress for RIS, including different fusion method designs. In this work,…

Curation methods for massive vision-language datasets trade off between dataset size and quality. However, even the highest quality of available curated captions are far too short to capture the rich visual detail in an image. To show the…

The rapid progress of Multimodal Large Language Models (MLLMs) has unlocked the potential for enhanced 3D scene understanding and spatial reasoning. A recent line of work explores learning spatial reasoning directly from multi-view images,…

In this paper, we present a high-performance and light-weight deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the aerial scene of a remote sensing image. To this end, we first valuate various…

Large Language Models (LLMs) have undergone rapid progress, largely attributed to reinforcement learning on complex reasoning tasks. In contrast, while spatial intelligence is fundamental for Vision-Language Models (VLMs) in real-world…

Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments. Augmenting these systems with visual signals has the potential to improve robustness to noise. However, audio-visual…

The goal of referring remote sensing image segmentation (RRSIS) is to extract specific pixel-level regions within an aerial image via a natural language expression. Recent advancements, particularly Transformer-based fusion designs, have…

Recent advances in Vision-Language Models (VLMs) have achieved impressive progress in multimodal mathematical reasoning. Yet, how much visual information truly contributes to reasoning remains unclear. Existing benchmarks report strong…

Vision-Language Models (VLMs) face significant challenges when dealing with the diverse resolutions and aspect ratios of real-world images, as most existing models rely on fixed, low-resolution inputs. While recent studies have explored…

Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on general images, acquiring high-quality referring expressions…

In this paper, we present an approach, namely Lexical Semantic Image Completion (LSIC), that may have potential applications in art, design, and heritage conservation, among several others. Existing image completion procedure is highly…

Radar sensors provide reliable perception across adverse weather, lighting, and long-range conditions, yet existing machine learning approaches remain fragmented and task-specific, with each downstream task employing distinct architectures…

Visual Question Answering (VQA) in remote sensing (RS) is pivotal for interpreting Earth observation data. However, existing RS VQA datasets are constrained by limitations in annotation richness, question diversity, and the assessment of…

We investigate the ability of Vision Language Models (VLMs) to perform visual perspective taking using a new set of visual tasks inspired by established human tests. Our approach leverages carefully controlled scenes in which a single…