mlsanityData to 7 Oct 2026

K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition

arXiv 2203.07890 ↗First posted 15 Mar 2022cs.CV cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Visual Question Generation (VQG) is a task to generate questions from images. When humans ask questions about an image, their goal is often to acquire some new knowledge. However, existing studies on VQG have mainly addressed question generation from answers or question categories, overlooking the objectives of knowledge acquisition. To introduce a knowledge acquisition perspective into VQG, we constructed a novel knowledge-aware VQG dataset called K-VQG. This is the first large, humanly annotated dataset in which questions regarding images are tied to structured knowledge. We also developed a new VQG model that can encode and use knowledge as the target for a question. The experiment results show that our model outperforms existing models on the K-VQG dataset.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

22 of 31 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  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. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  8. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  9. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  10. 2019OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledgecited by 1,114
  11. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  12. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
10 more
  1. 2016FVQA: Fact-based Visual Question Answeringcited by 181
  2. 2016Generating Natural Questions About an Imagecited by 56
  3. 2017Visual Question Generation as Dual Task of Visual Question Answeringcited by 41
  4. 2019Information Maximizing Visual Question Generationcited by 40
  5. 2019CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsensecited by 27
  6. 2017Learning by Asking Questionscited by 25
  7. 2017Creativity: Generating Diverse Questions using Variational Autoencoderscited by 24
  8. 2017iVQA: Inverse Visual Question Answeringcited by 22
  9. 2020C3VQG: Category Consistent Cyclic Visual Question Generationcited by 8
  10. 2018Visual Question Generation for Class Acquisition of Unknown Objectscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 3; 2025: 2; 2026: 3.

9 papers.

  1. 2024ConVQG: Contrastive Visual Question Generation with Multimodal Guidancecited by 4
  2. 2022Learning by Asking Questions for Knowledge-based Novel Object Recognitioncited by 2
  3. 2024Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generationcited by 2
  4. 2024Diagram-Driven Course Questions Generationcited by 2
  5. 2026Questions beyond Pixels: Integrating Commonsense Knowledge in Visual Question Generation for Remote Sensingcited by 2
  6. 2025Toward Ownership Understanding of Objects: Active Question Generation with Large Language Model and Probabilistic Generative Modelcited by 1
  7. 2026Knowledge-aware Visual Question Generation for Remote Sensing Imagescited by 1
  8. 2026Self-Evolving Visual Questionercited by 1
  9. 2025Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitationcited by 0