Related papers: One-shot Information Extraction from Document Imag…

The availability of metadata for scientific documents is pivotal in propelling scientific knowledge forward and for adhering to the FAIR principles (i.e. Findability, Accessibility, Interoperability, and Reusability) of research findings.…

To solve the problem of redundant information and overlapping relations of the entity and relation extraction model, we propose a joint extraction model. This model can directly extract multiple pairs of related entities without generating…

We study the problem of generating abstractive summaries for opinionated text. We propose an attention-based neural network model that is able to absorb information from multiple text units to construct informative, concise, and fluent…

Information extraction (IE) aims to produce structured information from an input text, e.g., Named Entity Recognition and Relation Extraction. Various attempts have been proposed for IE via feature engineering or deep learning. However,…

Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses…

How can we better extract entities and relations from text? Using multimodal extraction with images and text obtains more signals for entities and relations, and aligns them through graphs or hierarchical fusion, aiding in extraction.…

Many studies have concentrated on constructing supervised models utilizing paired datasets for image denoising, which proves to be expensive and time-consuming. Current self-supervised and unsupervised approaches typically rely on…

In this dissertation we report results of our research on dense distributed representations of text data. We propose two novel neural models for learning such representations. The first model learns representations at the document level,…

Diffusion models and flow-matching models have enabled generating diverse and realistic images by learning to transfer noise to data. However, sampling from these models involves iterative denoising over many neural network passes, making…

Document-level relation extraction aims to discover relations between entities across a whole document. How to build the dependency of entities from different sentences in a document remains to be a great challenge. Current approaches…

Indoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on…

We propose a structured approach to the problem of retrieval of images by content and present a description logic that has been devised for the semantic indexing and retrieval of images containing complex objects. As other approaches do, we…

Fast and invariant feature extraction is crucial in certain computer vision applications where the computation time is constrained in both training and testing phases of the classifier. In this paper, we propose a nature-inspired…

Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training. To address the above problem, we consider an efficient…

Information extraction (IE) from documents is an intensive area of research with a large set of industrial applications. Current state-of-the-art methods focus on scanned documents with approaches combining computer vision, natural language…

Object recognition has become a crucial part of machine learning and computer vision recently. The current approach to object recognition involves Deep Learning and uses Convolutional Neural Networks to learn the pixel patterns of the…

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational…

Deep neural networks are becoming increasingly powerful and large and always require more labelled data to be trained. However, since annotating data is time-consuming, it is now necessary to develop systems that show good performance while…

The project, under industrial funding, presented in this publication aims at the semantic analysis of a normative document describing requirements applicable to electrical appliances. The objective of the project is to build a semantic…

Visual question answering (VQA) has emerged as a flexible approach for extracting specific pieces of information from document images. However, existing work typically queries each field in isolation, overlooking potential dependencies…