# TextCaps: a Dataset for Image Captioning with Reading Comprehension Source: [TextCaps: a Dataset for Image Captioning with Reading Comprehension]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:29:00.055Z Authors: Oleksii Sidorov, Ronghang Hu, Marcus Rohrbach, Amanpreet Singh Published: 2020-03-24T02:38:35.000Z ## Abstract Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include written text in their descriptions, although text is omnipresent in human environments and frequently critical to understand our surroundings. To study how to comprehend text in the context of an image we collect a novel dataset, TextCaps, with 145k captions for 28k images. Our dataset challenges a model to recognize text, relate it to its visual context, and decide what part of the text to copy or paraphrase, requiring spatial, semantic, and visual reasoning between multiple text tokens and visual entities, such as objects. We study baselines and adapt existing approaches to this new task, which we refer to as image captioning with reading comprehension. Our analysis with automatic and human studies shows that our new TextCaps dataset provides many new technical challenges over previous datasets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Visual Question Answering on MMVP-VLM](): Visual Question Answering; MMVP-VLM; Orientation & Direction Score: 16.7. - [Image Classification on ImageNet-1k (Zero-shot)](): Image Classification; ImageNet-1K; Zero-shot Accuracy: 78.5. ## Original sources and implementation [Original paper]() [PDF]()