{"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/memexqa-visual-memex-question-answering","title":"MemexQA: Visual Memex Question Answering","arxiv_id":"1708.01336","date":"2017-08-04","proceeding":null,"authors":["Lu Jiang","Junwei Liang","Liangliang Cao","Yannis Kalantidis","Sachin Farfade","Alexander Hauptmann"],"abstract":"This paper proposes a new task, MemexQA: given a collection of photos or\nvideos from a user, the goal is to automatically answer questions that help\nusers recover their memory about events captured in the collection. Towards\nsolving the task, we 1) present the MemexQA dataset, a large, realistic\nmultimodal dataset consisting of real personal photos and crowd-sourced\nquestions/answers, 2) propose MemexNet, a unified, end-to-end trainable network\narchitecture for image, text and video question answering. Experimental results\non the MemexQA dataset demonstrate that MemexNet outperforms strong baselines\nand yields the state-of-the-art on this novel and challenging task. The\npromising results on TextQA and VideoQA suggest MemexNet's efficacy and\nscalability across various QA tasks.","url_abs":"http://arxiv.org/abs/1708.01336v1","url_pdf":"http://arxiv.org/pdf/1708.01336v1.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":"memexqa-visual-memex-question-answering","repo_url":"https://github.com/JunweiLiang/FVTA_MemexQA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"memex-question-answering","task_name":"Memex Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"memexqa","name":"MemexQA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.01336","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}