VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Phukan, Arpan, Pandey, Anupam, Bodo, Deepjyoti, Ekbal, Asif
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915612052160512
author Phukan, Arpan
Pandey, Anupam
Bodo, Deepjyoti
Ekbal, Asif
author_facet Phukan, Arpan
Pandey, Anupam
Bodo, Deepjyoti
Ekbal, Asif
contents Multi-hop Question Generation (QG) effectively evaluates reasoning but remains confined to text; Video Question Generation (VideoQG) is limited to zero-hop questions over single segments. To address this, we introduce VideoChain, a novel Multi-hop Video Question Generation (MVQG) framework designed to generate questions that require reasoning across multiple, temporally separated video segments. VideoChain features a modular architecture built on a modified BART backbone enhanced with video embeddings, capturing textual and visual dependencies. Using the TVQA+ dataset, we automatically construct the large-scale MVQ-60 dataset by merging zero-hop QA pairs, ensuring scalability and diversity. Evaluations show VideoChain's strong performance across standard generation metrics: ROUGE-L (0.6454), ROUGE-1 (0.6854), BLEU-1 (0.6711), BERTScore-F1 (0.7967), and semantic similarity (0.8110). These results highlight the model's ability to generate coherent, contextually grounded, and reasoning-intensive questions.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08348
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation
Phukan, Arpan
Pandey, Anupam
Bodo, Deepjyoti
Ekbal, Asif
Computer Vision and Pattern Recognition
Multi-hop Question Generation (QG) effectively evaluates reasoning but remains confined to text; Video Question Generation (VideoQG) is limited to zero-hop questions over single segments. To address this, we introduce VideoChain, a novel Multi-hop Video Question Generation (MVQG) framework designed to generate questions that require reasoning across multiple, temporally separated video segments. VideoChain features a modular architecture built on a modified BART backbone enhanced with video embeddings, capturing textual and visual dependencies. Using the TVQA+ dataset, we automatically construct the large-scale MVQ-60 dataset by merging zero-hop QA pairs, ensuring scalability and diversity. Evaluations show VideoChain's strong performance across standard generation metrics: ROUGE-L (0.6454), ROUGE-1 (0.6854), BLEU-1 (0.6711), BERTScore-F1 (0.7967), and semantic similarity (0.8110). These results highlight the model's ability to generate coherent, contextually grounded, and reasoning-intensive questions.
title VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.08348