相关论文: Towards Robust Visual Information Extraction in Re…

Estimating the 3D poses of hands and objects from a single RGB image is a fundamental yet challenging problem, with broad applications in augmented reality and human-computer interaction. Existing methods largely rely on visual cues alone,…

Detecting bias in multimodal news requires models that reason over text--image pairs, not just classify text. In response, we present ViLBias, a VQA-style benchmark and framework for detecting and reasoning about bias in multimodal news.…

Objective: To design and evaluate a general framework for interactive record linkage using a convenient algorithm combined with tractable Human Intelligent Tasks (HITs; i.e. micro tasks requiring human judgment) that can support…

Bias in generative Text-to-Image (T2I) models is a known issue, yet systematically analyzing such models' outputs to uncover it remains challenging. We introduce the Visual Bias Explorer (ViBEx) to interactively explore the output space of…

Problems at the intersection of vision and language are of significant importance both as challenging research questions and for the rich set of applications they enable. However, inherent structure in our world and bias in our language…

Open Information Extraction (OIE) is the task of the unsupervised creation of structured information from text. OIE is often used as a starting point for a number of downstream tasks including knowledge base construction, relation…

Real-world applications are stretching context windows to hundreds of thousand of tokens while Large Language Models (LLMs) swell from billions to trillions of parameters. This dual expansion send compute and memory costs skyrocketing,…

Open Information Extraction (OIE) aims to extract objective structured knowledge from natural texts, which has attracted growing attention to build dedicated models with human experience. As the large language models (LLMs) have exhibited…

The interest in Artificial Intelligence (AI) and its applications has seen unprecedented growth in the last few years. The success can be partly attributed to the advancements of deep neural networks made in the sub-fields of AI such as…

Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in significant discrimination if not handled properly as CV systems highly depend on the data they are fed with and can…

Impressive results on real-world image super-resolution (Real-ISR) have been achieved by employing pre-trained stable diffusion (SD) models. However, one critical issue of such methods lies in their poor reconstruction of image fine…

Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largely based on the concept of visual token reduction. This approach, however, creates an information bottleneck that impairs performance,…

The visual layout of a webpage can provide valuable clues for certain types of Information Extraction (IE) tasks. In traditional rule based IE frameworks, these layout cues are mapped to rules that operate on the HTML source of the…

Knowledge-based visual question answering (VQA) requires answering questions with external knowledge in addition to the content of images. One dataset that is mostly used in evaluating knowledge-based VQA is OK-VQA, but it lacks a gold…

Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to…

Legal practitioners often face a vast amount of documents. Lawyers, for instance, search for appropriate precedents favorable to their clients, while the number of legal precedents is ever-growing. Although legal search engines can assist…

Visual understanding requires interpreting both natural scenes and the textual information that appears within them, motivating tasks such as Visual Question Answering (VQA). However, current VQA benchmarks overlook scenarios with visually…

Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vision encoders set a strong inductive bias in abstracting…

Universal Information Extraction (UIE) is an area of interest due to the challenges posed by varying targets, heterogeneous structures, and demand-specific schemas. However, previous works have only achieved limited success by unifying a…

Despite progress in vision-based inspection algorithms, real-world industrial challenges -- specifically in data availability, quality, and complex production requirements -- often remain under-addressed. We introduce the VISION Datasets, a…