{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/image-captioning-and-visual-question","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","arxiv_id":"1603.02814","date":"2016-03-09","proceeding":null,"authors":["Qi Wu","Chunhua Shen","Anton Van Den Hengel","Peng Wang","Anthony Dick"],"abstract":"Much recent progress in Vision-to-Language problems has been achieved through\na combination of Convolutional Neural Networks (CNNs) and Recurrent Neural\nNetworks (RNNs). This approach does not explicitly represent high-level\nsemantic concepts, but rather seeks to progress directly from image features to\ntext. In this paper we first propose a method of incorporating high-level\nconcepts into the successful CNN-RNN approach, and show that it achieves a\nsignificant improvement on the state-of-the-art in both image captioning and\nvisual question answering. We further show that the same mechanism can be used\nto incorporate external knowledge, which is critically important for answering\nhigh level visual questions. Specifically, we design a visual question\nanswering model that combines an internal representation of the content of an\nimage with information extracted from a general knowledge base to answer a\nbroad range of image-based questions. It particularly allows questions to be\nasked about the contents of an image, even when the image itself does not\ncontain a complete answer. Our final model achieves the best reported results\non both image captioning and visual question answering on several benchmark\ndatasets.","url_abs":"http://arxiv.org/abs/1603.02814v2","url_pdf":"http://arxiv.org/pdf/1603.02814v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-coco-visual-4","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 1.0 open ended","model":"CNN-RNN","rank_in_archive_order":9,"of":14,"metrics":{"Percentage correct":"59.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.02814","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}