mlsanityData to 14 Oct 2026

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

arXiv 2511.08348 ↗First posted 11 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 78 references that are in the map. First posted on arXiv 11 Nov 2025.

Builds on

49 of 78 references.

References · 49

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2015VQA: Visual Question Answeringcited by 2,506
  6. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  7. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 950
  8. 2019ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answeringcited by 561
  9. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 556
  10. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 528
  11. 2018TVQA: Localized, Compositional Video Question Answeringcited by 467
  12. 2017TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answeringcited by 378
37 more
  1. 2015Neural Module Networkscited by 376
  2. 2020HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-trainingcited by 362
  3. 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 314
  4. 2015MovieQA: Understanding Stories in Movies through Question-Answeringcited by 304
  5. 2023Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioningcited by 263
  6. 2020Just Ask: Learning to Answer Questions from Millions of Narrated Videoscited by 248
  7. 2016Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Groundingcited by 243
  8. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 237
  9. 2024STAR: A Benchmark for Situated Reasoning in Real-World Videoscited by 213
  10. 2018A Joint Sequence Fusion Model for Video Question Answering and Retrievalcited by 208
  11. 2016FVQA: Fact-based Visual Question Answeringcited by 181
  12. 2019TVQA+: Spatio-Temporal Grounding for Video Question Answeringcited by 154
  13. 2018TallyQA: Answering Complex Counting Questionscited by 153
  14. 2016TGIF: A New Dataset and Benchmark on Animated GIF Descriptioncited by 124
  15. 2021AGQA: A Benchmark for Compositional Spatio-Temporal Reasoningcited by 120
  16. 2022EgoTaskQA: Understanding Human Tasks in Egocentric Videoscited by 115
  17. 2024VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understandingcited by 115
  18. 2021SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Eventscited by 84
  19. 2024Vript: A Video Is Worth Thousands of Wordscited by 71
  20. 2020What is More Likely to Happen Next? Video-and-Language Future Event Predictioncited by 62
  21. 2016Generating Natural Questions About an Imagecited by 56
  22. 2019KnowIT VQA: Answering Knowledge-Based Questions about Videoscited by 53
  23. 2020DramaQA: Character-Centered Video Story Understanding with Hierarchical QAcited by 45
  24. 2019Recent Advances in Neural Question Generationcited by 42
  25. 2016A dataset and exploration of models for understanding video data through fill-in-the-blank question-answeringcited by 41
  26. 2020Semantic Graphs for Generating Deep Questionscited by 38
  27. 2020ClarQ: A large-scale and diverse dataset for Clarification Question Generationcited by 31
  28. 2017Creativity: Generating Diverse Questions using Variational Autoencoderscited by 24
  29. 2023Connecting Vision and Language with Video Localized Narrativescited by 24
  30. 2023Reading Between the Lanes: Text VideoQA on the Roadcited by 23
  31. 2017iVQA: Inverse Visual Question Answeringcited by 22
  32. 2019TutorialVQA: Question Answering Dataset for Tutorial Videoscited by 20
  33. 2016Automatic Generation of Grounded Visual Questionscited by 19
  34. 2024CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenescited by 13
  35. 2018Visual Curiosity: Learning to Ask Questions to Learn Visual Recognitioncited by 11
  36. 2022WildQA: In-the-Wild Video Question Answeringcited by 9
  37. 2024ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videoscited by 2

Built on by

Not cited yet.