Enregistré dans:
Détails bibliographiques
Auteurs principaux: Taluzzi, Agnese, Gesualdi, Davide, Santambrogio, Riccardo, Plizzari, Chiara, Palermo, Francesca, Mentasti, Simone, Matteucci, Matteo
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.08553
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909645143015424
author Taluzzi, Agnese
Gesualdi, Davide
Santambrogio, Riccardo
Plizzari, Chiara
Palermo, Francesca
Mentasti, Simone
Matteucci, Matteo
author_facet Taluzzi, Agnese
Gesualdi, Davide
Santambrogio, Riccardo
Plizzari, Chiara
Palermo, Francesca
Mentasti, Simone
Matteucci, Matteo
contents This report presents SceneNet and KnowledgeNet, our approaches developed for the HD-EPIC VQA Challenge 2025. SceneNet leverages scene graphs generated with a multi-modal large language model (MLLM) to capture fine-grained object interactions, spatial relationships, and temporally grounded events. In parallel, KnowledgeNet incorporates ConceptNet's external commonsense knowledge to introduce high-level semantic connections between entities, enabling reasoning beyond directly observable visual evidence. Each method demonstrates distinct strengths across the seven categories of the HD-EPIC benchmark, and their combination within our framework results in an overall accuracy of 44.21% on the challenge, highlighting its effectiveness for complex egocentric VQA tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08553
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge
Taluzzi, Agnese
Gesualdi, Davide
Santambrogio, Riccardo
Plizzari, Chiara
Palermo, Francesca
Mentasti, Simone
Matteucci, Matteo
Computer Vision and Pattern Recognition
This report presents SceneNet and KnowledgeNet, our approaches developed for the HD-EPIC VQA Challenge 2025. SceneNet leverages scene graphs generated with a multi-modal large language model (MLLM) to capture fine-grained object interactions, spatial relationships, and temporally grounded events. In parallel, KnowledgeNet incorporates ConceptNet's external commonsense knowledge to introduce high-level semantic connections between entities, enabling reasoning beyond directly observable visual evidence. Each method demonstrates distinct strengths across the seven categories of the HD-EPIC benchmark, and their combination within our framework results in an overall accuracy of 44.21% on the challenge, highlighting its effectiveness for complex egocentric VQA tasks.
title From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.08553