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

TL;DR

VideoChain is a new transformer-based framework that generates multi-hop questions across video segments, advancing reasoning evaluation in video question generation beyond single-segment, zero-hop questions.

Contribution

It introduces a modular architecture with video embeddings for multi-hop video question generation and constructs a large-scale dataset for training and evaluation.

Findings

Strong performance on standard metrics

Effective reasoning across multiple video segments

Scalable dataset construction

Abstract

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.