Data to 7 Oct 2026

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

arXiv 2002.10215 ↗First posted 24 Feb 2020cs.CVcited by 78

Not on the map. Why?

Cited by 30 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Visual Question Answering (VQA) methods have made incredible progress, but suffer from a failure to generalize. This is visible in the fact that they are vulnerable to learning coincidental correlations in the data rather than deeper relations between image content and ideas expressed in language. We present a dataset that takes a step towards addressing this problem in that it contains questions expressed in two languages, and an evaluation process that co-opts a well understood image-based metric to reflect the method's ability to reason. Measuring reasoning directly encourages generalization by penalizing answers that are coincidentally correct. The dataset reflects the scene-text version of the VQA problem, and the reasoning evaluation can be seen as a text-based version of a referring expression challenge. Experiments and analysis are provided that show the value of the dataset.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 10; 2023: 10; 2024: 20; 2025: 18; 2026: 10.

78 papers.

Sort:

By area:

2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
2023Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Modelscited by 356
2021IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoningcited by 262
2024NVILA: Efficient Frontier Visual Language Modelscited by 206
2021TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene textcited by 170
2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 165
2021VisualMRC: Machine Reading Comprehension on Document Imagescited by 150
2023BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questionscited by 125
2024NVLM: Open Frontier-Class Multimodal LLMscited by 124
2022Hierarchical multimodal transformers for Multi-Page DocVQAcited by 102
2021Medical Visual Question Answering: A Surveycited by 93

38 more

2024MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizercited by 80
2021LaTr: Layout-Aware Transformer for Scene-Text VQAcited by 72
2024OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Textcited by 58
2022Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Groundingcited by 52
2025FineVision: Open Data Is All You Needcited by 51
2025EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answeringcited by 43
2024TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokenscited by 32
2025One RL to See Them All: Visual Triple Unified Reinforcement Learningcited by 29
2023PDFVQA: A New Dataset for Real-World VQA on PDF Documentscited by 28
2022PreSTU: Pre-Training for Scene-Text Understandingcited by 27
2024PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Modelscited by 25
2024The Evolution of Multimodal Model Architecturescited by 21
2021Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learningcited by 20
2022Watching the News: Towards VideoQA Models that can Readcited by 20
2025Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understandingcited by 20
2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 20
2025Are Large Vision Language Models Good Game Players?cited by 19
2024ModaVerse: Efficiently Transforming Modalities with LLMscited by 18
2023Advancing Visual Grounding with Scene Knowledge: Benchmark and Methodcited by 17
2025NVIDIA Nemotron Nano V2 VLcited by 15
2021Localize, Group, and Select: Boosting Text-VQA by Scene Text Modelingcited by 14
2021Asking questions on handwritten document collectionscited by 14
2022Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learningcited by 14
2024Exploring the Capabilities of Large Multimodal Models on Dense Textcited by 14
2024SegVG: Transferring Object Bounding Box to Segmentation for Visual Groundingcited by 14
2021Continual learning in cross-modal retrievalcited by 10
2023MPMQA: Multimodal Question Answering on Product Manualscited by 10
2024HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embeddingcited by 10
2026What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoomcited by 9
2024DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthinesscited by 8
2024LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformercited by 8
2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sightcited by 8
2023Separate and Locate: Rethink the Text in Text-based Visual Question Answeringcited by 7
2024Visual Grounding with Attention-Driven Constraint Balancingcited by 7
2024ACTRESS: Active Retraining for Semi-supervised Visual Groundingcited by 7
2024Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Studycited by 7
2021A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statisticscited by 6
2023Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQAcited by 6

50 most cited of 78 All 78 (JSON)