Stevan Rudinac

International Journal of Information Management Data Insights

Learning for Heterogeneous Information Networks

for Review Volume Prediction

for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Models

MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding

MMArt is introduced, a large-scale dataset of 74,234 WikiArt paintings, each annotated with four independently annotated perspectives plus a harmonized unified caption, produced by specialized vision-language models or human annotation and validated through complementary quality evaluations.

for City Exploration

This paper proposes Scenemash, a system that generates multimodal summaries of multiple alternative routes between locations in a city by jointly analysing distributions of a large number of semantic concepts detected in the visual content and latent topics extracted from associated text.

Showdown 2024: Relevance Feedback Meets Conversational Search

This work extends the existing Exquisitor URF system with conversational search, and the user interface has been completely redesigned to prepare for future integration with conversational search and better support novice users.