Saved in:
Bibliographic Details
Main Authors: Brilli, Dionysia Danai, Mallis, Dimitrios, Pitsikalis, Vassilis, Maragos, Petros
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911286027091968
author Brilli, Dionysia Danai
Mallis, Dimitrios
Pitsikalis, Vassilis
Maragos, Petros
author_facet Brilli, Dionysia Danai
Mallis, Dimitrios
Pitsikalis, Vassilis
Maragos, Petros
contents We propose GHR-VQA, Graph-guided Hierarchical Relational Reasoning for Video Question Answering (Video QA), a novel human-centric framework that incorporates scene graphs to capture intricate human-object interactions within video sequences. Unlike traditional pixel-based methods, each frame is represented as a scene graph and human nodes across frames are linked to a global root, forming the video-level graph and enabling cross-frame reasoning centered on human actors. The video-level graphs are then processed by Graph Neural Networks (GNNs), transforming them into rich, context-aware embeddings for efficient processing. Finally, these embeddings are integrated with question features in a hierarchical network operating across different abstraction levels, enhancing both local and global understanding of video content. This explicit human-rooted structure enhances interpretability by decomposing actions into human-object interactions and enables a more profound understanding of spatiotemporal dynamics. We validate our approach on the Action Genome Question Answering (AGQA) dataset, achieving significant performance improvements, including a 7.3% improvement in object-relation reasoning over the state of the art.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20201
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering
Brilli, Dionysia Danai
Mallis, Dimitrios
Pitsikalis, Vassilis
Maragos, Petros
Computer Vision and Pattern Recognition
We propose GHR-VQA, Graph-guided Hierarchical Relational Reasoning for Video Question Answering (Video QA), a novel human-centric framework that incorporates scene graphs to capture intricate human-object interactions within video sequences. Unlike traditional pixel-based methods, each frame is represented as a scene graph and human nodes across frames are linked to a global root, forming the video-level graph and enabling cross-frame reasoning centered on human actors. The video-level graphs are then processed by Graph Neural Networks (GNNs), transforming them into rich, context-aware embeddings for efficient processing. Finally, these embeddings are integrated with question features in a hierarchical network operating across different abstraction levels, enhancing both local and global understanding of video content. This explicit human-rooted structure enhances interpretability by decomposing actions into human-object interactions and enables a more profound understanding of spatiotemporal dynamics. We validate our approach on the Action Genome Question Answering (AGQA) dataset, achieving significant performance improvements, including a 7.3% improvement in object-relation reasoning over the state of the art.
title GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20201