{"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/attend-to-you-personalized-image-captioning","title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","arxiv_id":"1704.06485","date":"2017-04-21","proceeding":"CVPR 2017 7","authors":["Cesc Chunseong Park","Byeongchang Kim","Gunhee Kim"],"abstract":"We address personalization issues of image captioning, which have not been\ndiscussed yet in previous research. For a query image, we aim to generate a\ndescriptive sentence, accounting for prior knowledge such as the user's active\nvocabularies in previous documents. As applications of personalized image\ncaptioning, we tackle two post automation tasks: hashtag prediction and post\ngeneration, on our newly collected Instagram dataset, consisting of 1.1M posts\nfrom 6.3K users. We propose a novel captioning model named Context Sequence\nMemory Network (CSMN). Its unique updates over previous memory network models\ninclude (i) exploiting memory as a repository for multiple types of context\ninformation, (ii) appending previously generated words into memory to capture\nlong-term information without suffering from the vanishing gradient problem,\nand (iii) adopting CNN memory structure to jointly represent nearby ordered\nmemory slots for better context understanding. With quantitative evaluation and\nuser studies via Amazon Mechanical Turk, we show the effectiveness of the three\nnovel features of CSMN and its performance enhancement for personalized image\ncaptioning over state-of-the-art captioning models.","url_abs":"http://arxiv.org/abs/1704.06485v2","url_pdf":"http://arxiv.org/pdf/1704.06485v2.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":"attend-to-you-personalized-image-captioning","repo_url":"https://github.com/cesc-park/attend2u","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attend-to-you-personalized-image-captioning","repo_url":"https://github.com/ctr4si/attend2u","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"memory-network","method_name":"Memory Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.06485","atlas_url":"https://app.syntology.ai/?focus=1704.06485","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}