Related papers: SciPostLayoutTree: A Dataset for Structural Analys…
Establishing visual correspondences under large intra-class variations, which is often referred to as semantic correspondence or semantic matching, remains a challenging problem in computer vision. Despite its significance, however, most of…
Steel surface defect analysis is critical for industrial quality control, yet existing benchmarks rely primarily on label-only annotations, limiting fine-grained semantic understanding and systematic evaluation of vision-language models. To…
With the widespread application of multimodal large language models in scientific intelligence, there is an urgent need for more challenging evaluation benchmarks to assess their ability to understand complex scientific data. Scientific…
Networks are a fundamental model of complex systems throughout the sciences, and network datasets are typically analyzed through lower-order connectivity patterns described at the level of individual nodes and edges. However, higher-order…
Tables are common and important in scientific documents, yet most text-based document search systems do not capture structures and semantics specific to tables. How to bridge different types of mismatch between keywords queries and…
Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at…
Shape is commonly used to distinguish between categories in multi-class scatterplots. However, existing guidelines for choosing effective shape palettes rely largely on intuition and do not consider how these needs may change as the number…
Systematic scientometric reviews, empowered by scientometric and visual analytic techniques, offer opportunities to improve the timeliness, accessibility, and reproducibility of conventional systematic reviews. While increasingly accessible…
Supporting equitable instruction is an important issue for teachers attending diverse STEM classrooms. Visual learning analytics along with effective student survey measures can support providing on time feedback to teachers in making…
Tractography from high-dimensional diffusion magnetic resonance imaging (dMRI) data allows brain's structural connectivity analysis. Recent dMRI studies aim to compare connectivity patterns across subject groups and disease populations to…
Time series clustering promises to uncover hidden structural patterns in data with applications across healthcare, finance, industrial systems, and other critical domains. However, without validated ground truth information, researchers…
Approaches form the foundation for conducting scientific research. Querying approaches from a vast body of scientific papers is extremely time-consuming, and without a well-organized management framework, researchers may face significant…
The correlation between children's personal and family characteristics (e.g., demographics and socioeconomic status) and their physical and mental health status has been extensively studied across various research domains, such as public…
Selecting the appropriate visual presentation of the data such that it preserves the semantics of the underlying data and at the same time provides an intuitive summary of the data is an important, often the final step of data analytics.…
Billions of X-ray images are taken worldwide each year. Machine learning, and deep learning in particular, has shown potential to help radiologists triage and diagnose images. However, deep learning requires large datasets with reliable…
The determination of the reading sequence of text is fundamental to document understanding. This problem is easily solved in pages where the text is organized into a sequence of lines and vertical alignment runs the height of the page…
Network data has become widespread, larger, and more complex over the years. Traditional network data is dyadic, capturing the relations among pairs of entities. With the need to model interactions among more than two entities, significant…
In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector.…
Ancestry and genealogy tree are proven tools to determine the lineage of any person and establish dependencies among individuals. Genealogy tree can be exploited further to gain information about the researcher and his scholastic lineage…
Effectively showing the relationships between objects in a dataset is one of the main tasks in information visualization. Typically there is a well-defined notion of distance between pairs of objects, and traditional approaches such as…