Related papers: Beyond Artificial Misalignment: Detecting and Grou…

Remote sensing change captioning is an emerging and popular research task that aims to describe, in natural language, the content of interest that has changed between two remote sensing images captured at different times. Existing methods…

Automatic human matting is highly desired for many real applications. We investigate recent human matting methods and show that common bad cases happen when semantic human segmentation fails. This indicates that semantic understanding is…

We introduce a multicrossmodal LLM-agent framework motivated by the growing volume and diversity of materials-science data ranging from high-resolution microscopy and dynamic simulation videos to tabular experiment logs and sprawling…

Deep learning models benefit from increasing data diversity and volume, motivating synthetic data augmentation to improve existing datasets. However, existing evaluation metrics for synthetic data typically calculate latent feature…

The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities, has made it easier for all to produce harmful, toxic, faked or forged content. In response, various proposals have…

DeepFakes, which refer to AI-generated media content, have become an increasing concern due to their use as a means for disinformation. Detecting DeepFakes is currently solved with programmed machine learning algorithms. In this work, we…

While Open Set Semantic Mapping and 3D Semantic Scene Graphs (3DSSGs) are established paradigms in robotic perception, deploying them effectively to support high-level reasoning in large-scale, real-world environments remains a significant…

Radiology report generation (RRG) aims to automatically produce diagnostic reports from medical images, with the potential to enhance clinical workflows and reduce radiologists' workload. While recent approaches leveraging multimodal large…

In recent years, particularly since the early 2020s, Large Language Models (LLMs) have emerged as the most powerful AI tools in addressing a diverse range of challenges, from natural language processing to complex problem-solving in various…

Multi-modal large language models (MLLMs) have achieved remarkable success in fine-grained visual understanding across a range of tasks. However, they often encounter significant challenges due to inadequate alignment for fine-grained…

After natural disasters, accurate evaluations of damage to housing are important for insurance claims response and planning of resources. In this work, we introduce a novel multimodal retrieval-augmented generation (MM-RAG) framework. On…

The existing image manipulation localization (IML) models mainly relies on visual cues, but ignores the semantic logical relationships between content features. In fact, the content semantics conveyed by real images often conform to human…

Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer…

With the advancement of drone technology, the volume of video data increases rapidly, creating an urgent need for efficient semantic retrieval. We are the first to systematically propose and study the drone video-text retrieval (DVTR) task.…

Video foundation models generate visually realistic and temporally coherent content, but their reliability as world simulators depends on whether they capture physical, logical, and spatial constraints. Existing metrics such as Frechet…

Traditional Retrieval-Augmented Generation (RAG) methods are limited by their reliance on a fixed number of retrieved documents, often resulting in incomplete or noisy information that undermines task performance. Although recent adaptive…

The rapid advancement of generative AI has enabled the mass production of photorealistic synthetic images, blurring the boundary between authentic and fabricated visual content. This challenge is particularly evident in deepfake scenarios…

Visual grounding is essential for precise perception and reasoning in multimodal large language models (MLLMs), especially in medical imaging domains. While existing medical visual grounding benchmarks primarily focus on single-image…

Multimodal Large Language Models (MLLMs) have demonstrated impressive progress in single-image grounding and general multi-image understanding. Recently, some methods begin to address multi-image grounding. However, they are constrained by…

Nowadays, the widespread dissemination of misinformation across numerous social media platforms has led to severe negative effects on society. To address this challenge, the automatic detection of misinformation, particularly under…