paper-with-me

홈 › Papers

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

2025-11-11 · Arpan Phukan, Anupam Pandey, Deepjyoti Bodo, Asif Ekbal arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.08348

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SimilarityQuestion Generation

Similar Papers 제목 키워드 기반

Temporal Pyramid Transformer with Multimodal Interaction for Video Question Answering

2021-09-10 · Min Peng, Chongyang Wang, Yuan Gao, Yu Shi 외

Video question answering (VideoQA) is challenging given its multimodal combination of visual understanding and natural language understanding. While existing approaches seldom leverage the appearance-motion information i…

multimodal interactionNatural Language UnderstandingQuestion AnsweringVideo Question Answering

Just Ask: Learning to Answer Questions from Millions of Narrated Videos

2020-12-01 · ICCV 2021 10 · Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev 외

Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propos…

Question AnsweringQuestion GenerationQuestion-GenerationVideo Question Answering+3

Learning to Answer Visual Questions from Web Videos

2022-05-10 · Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev 외

Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propos…

Dataset GenerationQuestion AnsweringQuestion GenerationQuestion-Generation+4

Mounting Video Metadata on Transformer-based Language Model for Open-ended Video Question Answering

2021-08-11 · Donggeon Lee, SeongHo Choi, Youwon Jang, Byoung-Tak Zhang

Video question answering has recently received a lot of attention from multimodal video researchers. Most video question answering datasets are usually in the form of multiple-choice. But, the model for the multiple-choi…

Language ModelingLanguage ModellingMultiple-choiceOpen-Ended Question Answering+2

Contrastive Video Question Answering via Video Graph Transformer

2023-02-27 · Junbin Xiao, Pan Zhou, Angela Yao, Yicong Li 외

We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer …

Contrastive LearningQuestion AnsweringVideo Question Answering