mlsanityData to 7 Oct 2026

Why Does a Visual Question Have Different Answers?

arXiv 1908.04342 ↗First posted 12 Aug 2019cs.CV cs.HC cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

Visual question answering is the task of returning the answer to a question about an image. A challenge is that different people often provide different answers to the same visual question. To our knowledge, this is the first work that aims to understand why. We propose a taxonomy of nine plausible reasons, and create two labelled datasets consisting of ~45,000 visual questions indicating which reasons led to answer differences. We then propose a novel problem of predicting directly from a visual question which reasons will cause answer differences as well as a novel algorithm for this purpose. Experiments demonstrate the advantage of our approach over several related baselines on two diverse datasets. We publicly share the datasets and code at https://vizwiz.org.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 5; 2023: 10; 2024: 8; 2025: 4; 2026: 1.

34 papers.

Sort:

By area:

  1. 2022Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectlycited by 86
  2. 2023Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructionscited by 76
  3. 2021AmbiFC: Fact-Checking Ambiguous Claims with Evidencecited by 38
  4. 2023Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreementcited by 22
  5. 2023Zero and Few-shot Semantic Parsing with Ambiguous Inputscited by 16
  6. 2021Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillationcited by 14
  7. 2023VQA Therapy: Exploring Answer Differences by Visually Grounding Answerscited by 14
  8. 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Modelscited by 14
  9. 2023Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questionscited by 14
  10. 2022Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQAcited by 13
  11. 2024Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Modelscited by 12
  12. 2021Visual Question Answering: which investigated applications?cited by 11
22 more
  1. 2022VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairmentscited by 11
  2. 2025Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questionscited by 11
  3. 2021'Just because you are right, doesn't mean I am wrong': Overcoming a Bottleneck in the Development and Evaluation of Open-Ended Visual Question Answering (VQA) Taskscited by 10
  4. 2024Right this way: Can VLMs Guide Us to See More to Answer Questions?cited by 10
  5. 2023Dealing with Semantic Underspecification in Multimodal NLPcited by 9
  6. 2024Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Cameracited by 9
  7. 2023Quality-agnostic Image Captioning to Safely Assist People with Vision Impairmentcited by 8
  8. 2024RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMscited by 8
  9. 2021Unanswerable Questions about Images and Textscited by 7
  10. 2023Evaluating AI systems under uncertain ground truth: a case study in dermatologycited by 7
  11. 2024Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Cameracited by 7
  12. 2025Acknowledging Focus Ambiguity in Visual Questionscited by 7
  13. 2023Empowering Visually Impaired Individuals: A Novel Use of Apple Live Photos and Android Motion Photoscited by 6
  14. 2022What's Different between Visual Question Answering for Machine "Understanding" Versus for Accessibility?cited by 5
  15. 2024BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairmentscited by 5
  16. 2025"It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Modelscited by 3
  17. 2021Evaluating and Improving Interactions with Hazy Oraclescited by 1
  18. 2024Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictionscited by 1
  19. 2024SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Datasetcited by 1
  20. 2022EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answeringcited by 0
  21. 2025Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Informationcited by 0
  22. 2026CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQAcited by 0