InfographicVQA

By Minesh Mathew, Viraj Bagal, Rubèn Pérez Tito, Dimosthenis Karatzas, Ernest Valveny, C. V. Jawahar. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2021

506 citations recorded by the source corpus.

Infographics communicate information using a combination of textual, graphical and visual elements. This work explores the automatic understanding of infographic images by using a Visual Question Answering technique. To this end, we present InfographicVQA, a new dataset comprising a diverse collection of infographics and question-answer annotations. The questions require methods that jointly reason over the document layout, textual content, graphical elements, and data visualizations. We curate the dataset with an emphasis on questions that require elementary reasoning and basic arithmetic skills. For VQA on the dataset, we evaluate two Transformer-based strong baselines. Both the baselines yield unsatisfactory results compared to near perfect human performance on the dataset. The results suggest that VQA on infographics—images that are designed to communicate information quickly and clearly to human brain—is ideal for benchmarking machine understanding of complex document images. The dataset is available for download at docvqa.org

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d5611a92619548e7f2af5adb04070574c0dacac1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Qwen3-VL Technical Report (2025, unknown): “• Document Understanding: We perform comprehensive evaluation on OCR and document understanding ability of Qwen3-VL series across a diverse range OCR related benchmarks: DocVQA (Mathew et al., 2021b), InfoVQA (Mathew et al., 2021a), AI2D (Kembhavi et al., 2016), ChartQA (Masry et al., 2022), OCRBenc”
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models (2024, unknown): “Moreover, we conduct experiments on text-oriented VQA benchmarks such as TextVQA (Singh et al., 2019), OCRVQA (Mishra et al., 2019), DocVQA (Mathew et al., 2021b), ChartQA (Masry et al., 2022), AI2D (Kem-Table (Svetlichnaya, 2020), In-foVQA (Mathew et al., 2021a), TabFact (Chen et al., 2019), Visual”
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models (2025, unknown): “In comparison, our proposed Vision-R1 demonstrates a substantial advantage in reasoning performance, effectively balancing CoT complexity and accuracy.”
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models (2024, methodology): “• PixMo-CapQA : We generated an additional 214k question-answer pairs from 165k images by prompting 21], Infograph-icVQA train [22], AI2D train (transparent and opaque label boxes) [13], A-OKVQA train [28], Android-Control train [14], ScienceQA train [16], TabMWP train [17], ST-VQA train [6],…”
Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks (2023, background): “…OKVQA [79], A-OKVQA [93], VQA 1.1M IconQA [75], AI2D [53], GQA [48] OCR-VQA [82], ChartQA [80], DocVQA [25], ST-VQA [11], EST-VQA [116], InfoVQA [81] model can generate a feature map F ∈ R H/ 14 × W/ 14 × D for dense prediction tasks, or work with global average pooling and linear projection to…”
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency (2025, unknown): “…the comprehensive capabilities of the model across tasks related to text, document, and chart comprehension, we conduct an extensive assessment on nine benchmarks: AI2D [55], ChartQA [87], TextVQA [112], DocVQA [89], InfoVQA [88], OCRBench [72], SEED-2-Plus [59], CharXiv [148], and VCR [176].”
LLaVA-OneVision: Easy Visual Task Transfer (2024, unknown): “In our development, we evaluate on AI2D [54], ChartQA [101], DocVQA [103], and InfoVQA [102] to examine the model’s fine-grained understanding of tables, charts, and diagrams, as well as MME [28] for formatting control, since it requires only Yes or No answers.”
What matters when building vision-language models? (2024, unknown): “…801,579 6,073,824 0.93% VisualMRC (Tanaka et al., 2021) 3,027 11,988 168,828 0.86% IAM (Marti and Bunke, 2002) 5,663 5,663 144,216 0.74% InfoVQA (Mathew et al., 2022) 2, (Tang et al., 2023) 7,057 9,969 1,245,485 1.91% ChartQA (Masry et al., 2022) 18,271 28,299 185,835 1.90% PlotQA (Methani et…”
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models (2025, unknown): “Figure 1 provides a detailed assessment of InternVL3’s performance across a diverse set of benchmarks, including MMMU [141], MathVista [80], AI2D [57], ChartQA [91], DocVQA [93], InfographicVQA [92], HallusionBench [45], OCRBench [76], and LongVideoBench [129].”
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning (2024, methodology): “We select the InfographicsVQA [42] dataset for its high-resolution infographics, which are advantageous for training MLLMs to pinpoint answer locations.”
How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites (2024, unknown): “In testing phases, the model could handle up to 40 tiles, equivalent to 4K resolution, demonstrating its adaptability to high-resolution inputs in a zero-shot manner.”
Monkey: Image Resolution and Text Label are Important Things for Large Multi-Modal Models (2023, unknown): “To effectively evaluate our model, we select representative benchmarks including DocVQA [36], ChartQA [35], InfographicVQA [37], DeepForm [47], KLC [46], and WTQ [40].”
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding (2025, unknown): “…DocVQA [40], Docmatix [41] 1.31M Chart/Figure ChartQA [42], MMC_Instruction [83], DVQA [84], LRV_Instruction [85], ChartGemma [86], InfoVQA [87], PlotQA [88] 1.00M OCR MultiUI [89], in-house data 0.83M Grounding RefCoco [90], VCR [91], in-house data 0.50M Multi-Image Demon-Full [92],…”
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling (2024, unknown): “…(en) [263], Chart2Text (en) [191], FinTabNet (zh) [312], SciTSR (zh) [39], Chart Synthetic Chart2Markdown (en) OCRVQA (en) [188], InfoVQA (en) [183], TextVQA (en) [212], ArT (en & zh) [40], HME100K (en) [288], COCO-Text (en) [238], CTW (zh) [287], LSVT (zh) [222], RCTW-17 (zh) [209], VCR (en…”