{"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/attention-on-attention-architectures-for","title":"Attention on Attention: Architectures for Visual Question Answering (VQA)","arxiv_id":"1803.07724","date":"2018-03-21","proceeding":null,"authors":["Jasdeep Singh","Vincent Ying","Alex Nutkiewicz"],"abstract":"Visual Question Answering (VQA) is an increasingly popular topic in deep\nlearning research, requiring coordination of natural language processing and\ncomputer vision modules into a single architecture. We build upon the model\nwhich placed first in the VQA Challenge by developing thirteen new attention\nmechanisms and introducing a simplified classifier. We performed 300 GPU hours\nof extensive hyperparameter and architecture searches and were able to achieve\nan evaluation score of 64.78%, outperforming the existing state-of-the-art\nsingle model's validation score of 63.15%.","url_abs":"http://arxiv.org/abs/1803.07724v1","url_pdf":"http://arxiv.org/pdf/1803.07724v1.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":[{"paper_slug":"attention-on-attention-architectures-for","repo_url":"https://github.com/SinghJasdeep/Attention-on-Attention-for-VQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attention-on-attention-architectures-for","repo_url":"https://github.com/VincentYing/Attention-on-Attention-for-VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"attention-on-attention-architectures-for","repo_url":"https://github.com/feifengwhu/question_attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.07724","atlas_url":"https://app.syntology.ai/?focus=1803.07724","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}