mlsanityData to 7 Oct 2026

Visual Question Generation as Dual Task of Visual Question Answering

arXiv 1709.07192 ↗First posted 21 Sep 2017cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

Recently visual question answering (VQA) and visual question generation (VQG) are two trending topics in the computer vision, which have been explored separately. In this work, we propose an end-to-end unified framework, the Invertible Question Answering Network (iQAN), to leverage the complementary relations between questions and answers in images by jointly training the model on VQA and VQG tasks. Corresponding parameter sharing scheme and regular terms are proposed as constraints to explicitly leverage Q,A's dependencies to guide the training process. After training, iQAN can take either question or answer as input, then output the counterpart. Evaluated on the large-scale visual question answering datasets CLEVR and VQA2, our iQAN improves the VQA accuracy over the baselines. We also show the dual learning framework of iQAN can be generalized to other VQA architectures and consistently improve the results over both the VQA and VQG tasks.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 11; 2023: 8; 2024: 9; 2025: 3; 2026: 3.

41 papers.

Sort:

By area:

  1. 2021The GEM Benchmark: Natural Language Generation, its Evaluation and Metricscited by 239
  2. 2023ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptionscited by 86
  3. 2023VIGC: Visual Instruction Generation and Correctioncited by 80
  4. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 74
  5. 2022All You May Need for VQA are Image Captionscited by 65
  6. 2022Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigationcited by 50
  7. 2021Neural-Symbolic Solver for Math Word Problems with Auxiliary Taskscited by 38
  8. 2022Learning to Answer Visual Questions from Web Videoscited by 30
  9. 2023Chatting Makes Perfect: Chat-based Image Retrievalcited by 25
  10. 2023HRVQA: A Visual Question Answering Benchmark for High-Resolution Aerial Imagescited by 21
  11. 2024LOVA3: Learning to Visual Question Answering, Asking and Assessmentcited by 21
  12. 2022Improving Biomedical Information Retrieval with Neural Retrieverscited by 20
29 more
  1. 2023Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!cited by 19
  2. 2021Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answeringcited by 14
  3. 2021Guiding Visual Question Generationcited by 14
  4. 2022Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQAcited by 13
  5. 2022K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisitioncited by 9
  6. 2021Cross-Modal Generative Augmentation for Visual Question Answeringcited by 7
  7. 2021End-to-End Video Question-Answer Generation with Generator-Pretester Networkcited by 6
  8. 2022Closed-book Question Generation via Contrastive Learningcited by 6
  9. 2022Look, Read and Ask: Learning to Ask Questions by Reading Text in Imagescited by 5
  10. 2024A Survey on Neural Question Generation: Methods, Applications, and Prospectscited by 5
  11. 2026Temporal Consistency-Aware Text-to-Motion Generationcited by 5
  12. 2021Hybrid Reasoning Network for Video-based Commonsense Captioningcited by 4
  13. 2024ConVQG: Contrastive Visual Question Generation with Multimodal Guidancecited by 4
  14. 2024Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokenscited by 4
  15. 2023Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captionercited by 3
  16. 2022Learning by Asking Questions for Knowledge-based Novel Object Recognitioncited by 2
  17. 2024Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generationcited by 2
  18. 2024Synthesizing Conversations from Unlabeled Documents using Automatic Response Segmentationcited by 2
  19. 2024ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videoscited by 2
  20. 2026Questions beyond Pixels: Integrating Commonsense Knowledge in Visual Question Generation for Remote Sensingcited by 2
  21. 2024Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-referencecited by 1
  22. 2026Knowledge-aware Visual Question Generation for Remote Sensing Imagescited by 1
  23. 2022Few-Shot Visual Question Generation: A Novel Task and Benchmark Datasetscited by 0
  24. 2022Adversarial and Safely Scaled Question Generationcited by 0
  25. 2023Weakly Supervised Visual Question Answer Generationcited by 0
  26. 2023From text to multimodal: a survey of adversarial example generation in question answering systemscited by 0
  27. 2025Can LLMs Ask Good Questions?cited by 0
  28. 2025VQA support to Arabic Language Learning Educational Toolcited by 0
  29. 2025Prototype-Aware Multimodal Alignment for Open-Vocabulary Visual Groundingcited by 0