Related papers: MatViX: Multimodal Information Extraction from Vis…

We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades. For the vision component, we incorporate a…

We present MaterialFigBench, a benchmark dataset designed to evaluate the ability of multimodal large language models (LLMs) to solve university-level materials science problems that require accurate interpretation of figures. Unlike…

The rapid advancement of unsupervised representation learning and large-scale pre-trained vision-language models has significantly improved cross-modal retrieval tasks. However, existing multi-modal information retrieval (MMIR) studies lack…

The visual world around us constantly evolves, from real-time news and social media trends to global infrastructure changes visible through satellite imagery and augmented reality enhancements. However, Multimodal Large Language Models…

Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis. Despite this, existing benchmarks typically focus only on extracting text and simple layout information, neglecting the complex…

With the advancement of multimedia technologies, news documents and user-generated content are often represented as multiple modalities, making Multimedia Event Extraction (MEE) an increasingly important challenge. However, recent MEE…

Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from…

The increasing use of machine learning models has amplified the demand for high-quality, large-scale multimodal datasets. However, the availability of such datasets, especially those combining acoustic, visual and textual data, remains…

Multimedia collections are more than ever growing in size and diversity. Effective multimedia retrieval systems are thus critical to access these datasets from the end-user perspective and in a scalable way. We are interested in…

Key Information Extraction (KIE) from visually-rich documents (VrDs) is a critical task, for which recent Large Language Models (LLMs) and Multi-Modal Large Language Models (MLLMs) have demonstrated strong potential. However, their reliance…

Table Extraction (TE) consists in extracting tables from PDF documents, in a structured format which can be automatically processed. While numerous TE tools exist, the variety of methods and techniques makes it difficult for users to choose…

After pre-training on extensive image-text pairs, Contrastive Language-Image Pre-training (CLIP) demonstrates promising performance on a wide variety of benchmarks. However, a substantial volume of multimodal interleaved documents remains…

Web information extraction (WIE) is the task of automatically extracting data from web pages, offering high utility for various applications. The evaluation of WIE systems has traditionally relied on benchmarks built from HTML snapshots…

Document retrieval is an important task for search and Retrieval-Augmented Generation (RAG) applications. Large Language Models (LLMs) have contributed to improving the accuracy of text-based document retrieval. However, documents with…

Attribute Value Extraction (AVE) is important for structuring product information in e-commerce. However, existing AVE datasets are primarily limited to text-to-text or image-to-text settings, lacking support for product videos, diverse…

Information extraction (IE) from unstructured documents remains a critical challenge in data processing pipelines. Traditional optical character recognition (OCR) methods and conventional parsing engines demonstrate limited effectiveness…

Applying machine learning tools to digitized image archives has a potential to revolutionize quantitative research of visual studies in humanities and social sciences. The ability to process a hundredfold greater number of photos than has…

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment…

Content-based medical image retrieval is an important diagnostic tool that improves the explainability of computer-aided diagnosis systems and provides decision making support to healthcare professionals. Medical imaging data, such as…

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods…