{"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/visual7w-grounded-question-answering-in","title":"Visual7W: Grounded Question Answering in Images","arxiv_id":"1511.03416","date":"2015-11-11","proceeding":"CVPR 2016 6","authors":["Yuke Zhu","Oliver Groth","Michael Bernstein","Li Fei-Fei"],"abstract":"We have seen great progress in basic perceptual tasks such as object\nrecognition and detection. However, AI models still fail to match humans in\nhigh-level vision tasks due to the lack of capacities for deeper reasoning.\nRecently the new task of visual question answering (QA) has been proposed to\nevaluate a model's capacity for deep image understanding. Previous works have\nestablished a loose, global association between QA sentences and images.\nHowever, many questions and answers, in practice, relate to local regions in\nthe images. We establish a semantic link between textual descriptions and image\nregions by object-level grounding. It enables a new type of QA with visual\nanswers, in addition to textual answers used in previous work. We study the\nvisual QA tasks in a grounded setting with a large collection of 7W\nmultiple-choice QA pairs. Furthermore, we evaluate human performance and\nseveral baseline models on the QA tasks. Finally, we propose a novel LSTM model\nwith spatial attention to tackle the 7W QA tasks.","url_abs":"http://arxiv.org/abs/1511.03416v4","url_pdf":"http://arxiv.org/pdf/1511.03416v4.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":"multiple-choice-qa","task_name":"Multiple Choice Question Answering (MCQA)"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"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":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"visual7w","name":"Visual7W","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.03416","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}