Enhancing interactive image retrieval with query rewriting using large language models and vision language models

H Zhu, JH Huang, S Rudinac, E Kanoulas - Proceedings of the 2024 …, 2024 - dl.acm.org
Image search stands as a pivotal task in multimedia and computer vision, finding
applications across diverse domains, ranging from internet search to medical diagnostics …

Ada-HGNN: Adaptive Sampling for Scalable Hypergraph Neural Networks

S Wang, DW Zhang, JH Huang, S Rudinac… - arxiv preprint arxiv …, 2024 - arxiv.org
Hypergraphs serve as an effective model for depicting complex connections in various real-
world scenarios, from social to biological networks. The development of Hypergraph Neural …

Image2text2image: A novel framework for label-free evaluation of image-to-text generation with text-to-image diffusion models

JH Huang, H Zhu, Y Shen, S Rudinac… - … on Multimedia Modeling, 2025 - Springer
Evaluating the quality of automatically generated image descriptions is a complex task that
requires metrics capturing various dimensions, such as grammaticality, coverage, accuracy …

Exploration of graph classes and concepts for superhypergraphs and n-th power mathematical structures

T Fujita - engrxiv.org
Graphs are fundamental concepts used in modeling across various fields such as computer
science and engineering. A hypergraph extends this idea by allowing edges, known as …

[PDF][PDF] Discovery of Some Concepts for SuperHyperGraphs and nth-Power Mathematical structures

T Fujita - researchgate.net
This paper explores superhypergraphs, an extension of hypergraphs incorporating
superedges and supervertices. Andb we introduce the Generalized n-th Powerset, a …