mlsanityData to 7 Oct 2026

Document Collection Visual Question Answering

arXiv 2104.14336 ↗First posted 27 Apr 2021cs.IRcited by 45

Not on the map. Why?

Abstract (arXiv)

Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Apr 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 7; 2024: 18; 2025: 12; 2026: 4.

45 papers.

Sort:

By area:

  1. 2024Mini-Gemini: Mining the Potential of Multi-modality Vision Language Modelscited by 361
  2. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 175
  3. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
  4. 2022Hierarchical multimodal transformers for Multi-Page DocVQAcited by 102
  5. 2024Benchmarking and Improving Detail Image Captioncited by 81
  6. 2024CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Expertscited by 56
  7. 2023A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagramcited by 55
  8. 2024Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmarkcited by 53
  9. 2025MMDocIR: Benchmarking Multimodal Retrieval for Long Documentscited by 43
  10. 2022OCR-IDL: OCR Annotations for Industry Document Library Datasetcited by 35
  11. 2024SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understandingcited by 25
  12. 2023u-LLaVA: Unifying Multi-Modal Tasks via Large Language Modelcited by 24
33 more
  1. 2023LANS: A Layout-Aware Neural Solver for Plane Geometry Problemcited by 23
  2. 2024GRAM: Global Reasoning for Multi-Page VQAcited by 23
  3. 2024MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understandingcited by 23
  4. 2024MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuningcited by 22
  5. 2022Watching the News: Towards VideoQA Models that can Readcited by 20
  6. 2024Lyra: An Efficient and Speech-Centric Framework for Omni-Cognitioncited by 20
  7. 2021ICDAR 2021 Competition on Document VisualQuestion Answeringcited by 19
  8. 2024Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignmentcited by 19
  9. 2023Privacy-Aware Document Visual Question Answeringcited by 17
  10. 2024World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filteringcited by 14
  11. 2024Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagramcited by 13
  12. 2023Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answeringcited by 10
  13. 2024ANLS* -- A Universal Document Processing Metric for Generative Large Language Modelscited by 10
  14. 2024JDocQA: Japanese Document Question Answering Dataset for Generative Language Modelscited by 9
  15. 2024LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformercited by 8
  16. 2024PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answeringcited by 7
  17. 2025Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognitioncited by 7
  18. 2025Vision-Speech Models: Teaching Speech Models to Converse about Imagescited by 4
  19. 2025Where is this coming from? Making groundedness count in the evaluation of Document VQA modelscited by 4
  20. 2024FILA: Fine-Grained Vision Language Modelscited by 3
  21. 2025NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understandingcited by 3
  22. 2025Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuningcited by 3
  23. 2025T2-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generationcited by 3
  24. 2025SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understandingcited by 3
  25. 2024NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQAcited by 2
  26. 2025Enhancing Document VQA Models via Retrieval-Augmented Generationcited by 2
  27. 2025EncouRAGe: Evaluating RAG Local, Fast, and Reliablecited by 2
  28. 2025FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint Analysiscited by 1
  29. 2026Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Modelscited by 1
  30. 2025Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmarkcited by 0
  31. 2026Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QAcited by 0
  32. 2026Do MLLMs Really Understand Low-Resource Khmer Documents? A Pilot Study on Khmer Document VQAcited by 0
  33. 2026Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligencecited by 0