Related papers: Automatic Recognition of Learning Resource Categor…

Object recognition and detection are well-studied problems with a developed set of almost standard solutions. Identity documents recognition, classification, detection, and localization are the tasks required in a number of applications,…

Indexing learning documents using the Learning Object Metadata (LOM) is often carried out manually by archivists. Filling out the LOM fields is a long and difficult task, requiring a complete reading and a full knowledge on the topic dealt…

A heterogeneous information network (HIN) has as vertices objects of different types and as edges the relations between objects, which are also of various types. We study the problem of classifying objects in HINs. Most existing methods…

The quality of machine learning models depends heavily on their training data. Selecting high-quality, diverse training sets for large language models (LLMs) is a difficult task, due to the lack of cheap and reliable quality metrics. While…

Safety-critical applications such as autonomous driving require robust 3D environment perception algorithms capable of handling diverse and ambiguous surroundings. The predictive performance of classification models is heavily influenced by…

Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language…

Hierarchical text classification is a challenging subtask of multi-label classification due to its complex label hierarchy. Existing methods encode text and label hierarchy separately and mix their representations for classification, where…

Handwritten Text Recognition (HTR) is a task of central importance in the field of document image understanding. State-of-the-art methods for HTR require the use of extensive annotated sets for training, making them impractical for…

Within the past few decades we have witnessed digital revolution, which moved scholarly communication to electronic media and also resulted in a substantial increase in its volume. Nowadays keeping track with the latest scientific…

In this paper, we explore the intersection of technology and cultural preservation by developing a self-supervised learning framework for the classification of musical symbols in historical manuscripts. Optical Music Recognition (OMR) plays…

Machine unlearning aims to efficiently remove the influence of specific training data from a model without full retraining. While much progress has been made in unlearning for LLMs, document classification models remain relatively…

Online learning systems have multiple data repositories in the form of transcripts, books and questions. To enable ease of access, such systems organize the content according to a well defined taxonomy of hierarchical nature…

Within the field of image and video recognition, the traditional approach is a dataset split into fixed training and test partitions. However, the labelling of the training set is time-consuming, especially as datasets grow in size and…

Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to…

Multi-label Recognition (MLR) involves assigning multiple labels to each data instance in an image, offering advantages over single-label classification in complex scenarios. However, it faces the challenge of annotating all relevant…

This paper describes the design and implementation of a new machine learning model for online learning systems. We aim at improving the intelligent level of the systems by enabling an automated math word problem solver which can support a…

Non-textual components such as charts, diagrams and tables provide key information in many scientific documents, but the lack of large labeled datasets has impeded the development of data-driven methods for scientific figure extraction. In…

We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning methods assume that all tasks share the same attribute space,…

Heterogeneous graphs (HGs) are composed of multiple types of nodes and edges, making it more effective in capturing the complex relational structures inherent in the real world. However, in real-world scenarios, labeled data is often…

Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irregular layouts. These documents are widely observed across domains and account for a…