mlsanityData to 7 Oct 2026

Acknowledging Focus Ambiguity in Visual Questions

arXiv 2501.02201 ↗First posted 4 Jan 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

No published work on visual question answering (VQA) accounts for ambiguity regarding where the content described in the question is located in the image. To fill this gap, we introduce VQ-FocusAmbiguity, the first VQA dataset that visually grounds each plausible image region a question could refer to when arriving at valid answers. We next analyze and compare our dataset to existing datasets to reveal its unique properties. Finally, we benchmark modern models for two novel tasks related to acknowledging focus ambiguity: recognizing whether a visual question has focus ambiguity and locating all plausible focus regions within the image. Results show that the dataset is challenging for modern models. To facilitate future progress on these tasks, we publicly share the dataset with an evaluation server at https://vizwiz.org/tasks-and-datasets/focus-ambiguity-in-visual-questions.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 42 of its 54 references that are in the map. First posted on arXiv 4 Jan 2025.

Builds on

42 of 54 references.

References · 42

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2023Segment Anythingcited by 8,158
  3. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  4. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  5. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  6. 2015VQA: Visual Question Answeringcited by 2,489
  7. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  8. 2019Towards VQA Models That Can Readcited by 1,696
  9. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,582
  10. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  11. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  12. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
30 more
  1. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  2. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 929
  3. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 852
  4. 2021Multimodal Few-Shot Learning with Frozen Language Modelscited by 657
  5. 2019Object Detection in 20 Years: A Surveycited by 528
  6. 2023GLaMM: Pixel Grounding Large Multimodal Modelcited by 447
  7. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  8. 2015Visual7W: Grounded Question Answering in Imagescited by 315
  9. 2023PACO: Parts and Attributes of Common Objectscited by 146
  10. 2020PhraseCut: Language-based Image Segmentation in the Wildcited by 116
  11. 2014Salient Object Detection: A Discriminative Regional Feature Integration Approachcited by 89
  12. 2020A Survey on Instance Segmentation: State of the artcited by 85
  13. 2020Referring Expression Comprehension: A Survey of Methods and Datasetscited by 78
  14. 2017VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentationcited by 50
  15. 2020Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehensioncited by 50
  16. 2022Grounding Answers for Visual Questions Asked by Visually Impaired Peoplecited by 47
  17. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 42
  18. 2023Described Object Detection: Liberating Object Detection with Flexible Expressionscited by 40
  19. 2019Why Does a Visual Question Have Different Answers?cited by 34
  20. 2024Long-Form Answers to Visual Questions from Blind and Low Vision Peoplecited by 18
  21. 2023OmniLabel: A Challenging Benchmark for Language-Based Object Detectioncited by 16
  22. 2016Modeling Ambiguity, Subjectivity, and Diverging Viewpoints in Opinion Question Answering Systemscited by 15
  23. 2023VQA Therapy: Exploring Answer Differences by Visually Grounding Answerscited by 14
  24. 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Modelscited by 14
  25. 2022Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQAcited by 13
  26. 2022VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairmentscited by 11
  27. 2023Fully Authentic Visual Question Answering Dataset from Online Communitiescited by 9
  28. 2016Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenescited by 6
  29. 2023Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Promptscited by 5
  30. 2017Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)cited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2026VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Modelscited by 3
  2. 2026Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specificationcited by 2
  3. 2025Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Informationcited by 0
  4. 2026GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoningcited by 0
  5. 2026MMBench-Live: A Continuously Evolving Benchmark for Multimodal Modelscited by 0
  6. 2026Estimating Uncertainty in Galaxy Morphology Classificationcited by 0
  7. 2026COMIC: Reference-Aware Safety Gating for Multimodal Large Language Modelscited by 0