Enregistré dans:
Détails bibliographiques
Auteurs principaux: Rodin, Ivan, Wu, Tz-Ying, Min, Kyle, Sridhar, Sharath Nittur, Furnari, Antonino, Tripathi, Subarna, Farinella, Giovanni Maria
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.05787
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908478291836928
author Rodin, Ivan
Wu, Tz-Ying
Min, Kyle
Sridhar, Sharath Nittur
Furnari, Antonino
Tripathi, Subarna
Farinella, Giovanni Maria
author_facet Rodin, Ivan
Wu, Tz-Ying
Min, Kyle
Sridhar, Sharath Nittur
Furnari, Antonino
Tripathi, Subarna
Farinella, Giovanni Maria
contents We introduce EASG-Bench, a question-answering benchmark for egocentric videos where the question-answering pairs are created from spatio-temporally grounded dynamic scene graphs capturing intricate relationships among actors, actions, and objects. We propose a systematic evaluation framework and evaluate several language-only and video large language models (video-LLMs) on this benchmark. We observe a performance gap in language-only and video-LLMs, especially on questions focusing on temporal ordering, thus identifying a research gap in the area of long-context video understanding. To promote the reproducibility of our findings and facilitate further research, the benchmark and accompanying code are available at the following GitHub page: https://github.com/fpv-iplab/EASG-bench.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05787
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs
Rodin, Ivan
Wu, Tz-Ying
Min, Kyle
Sridhar, Sharath Nittur
Furnari, Antonino
Tripathi, Subarna
Farinella, Giovanni Maria
Computer Vision and Pattern Recognition
We introduce EASG-Bench, a question-answering benchmark for egocentric videos where the question-answering pairs are created from spatio-temporally grounded dynamic scene graphs capturing intricate relationships among actors, actions, and objects. We propose a systematic evaluation framework and evaluate several language-only and video large language models (video-LLMs) on this benchmark. We observe a performance gap in language-only and video-LLMs, especially on questions focusing on temporal ordering, thus identifying a research gap in the area of long-context video understanding. To promote the reproducibility of our findings and facilitate further research, the benchmark and accompanying code are available at the following GitHub page: https://github.com/fpv-iplab/EASG-bench.
title EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.05787