TY - CONF AU - Minesh Mathew AU - Viraj Bagal AU - Ruben Tito AU - Dimosthenis Karatzas AU - Ernest Valveny AU - C.V. Jawahar A2 - WACV PY - 2022// TI - InfographicVQA BT - Winter Conference on Applications of Computer Vision SP - 1697 EP - 1706 KW - Document Analysis Datasets KW - Evaluation and Comparison of Vision Algorithms KW - Vision and Languages N2 - 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 UR - https://ieeexplore.ieee.org/document/9706887 L1 - http://refbase.cvc.uab.es/files/MBT2022.pdf UR - http://dx.doi.org/10.1109/WACV51458.2022.00264 N1 - DAG; 600.155 ID - Minesh Mathew2022 ER -