{"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/guiding-long-short-term-memory-for-image","title":"Guiding Long-Short Term Memory for Image Caption Generation","arxiv_id":"1509.04942","date":"2015-09-16","proceeding":null,"authors":["Xu Jia","Efstratios Gavves","Basura Fernando","Tinne Tuytelaars"],"abstract":"In this work we focus on the problem of image caption generation. We propose\nan extension of the long short term memory (LSTM) model, which we coin gLSTM\nfor short. In particular, we add semantic information extracted from the image\nas extra input to each unit of the LSTM block, with the aim of guiding the\nmodel towards solutions that are more tightly coupled to the image content.\nAdditionally, we explore different length normalization strategies for beam\nsearch in order to prevent from favoring short sentences. On various benchmark\ndatasets such as Flickr8K, Flickr30K and MS COCO, we obtain results that are on\npar with or even outperform the current state-of-the-art.","url_abs":"http://arxiv.org/abs/1509.04942v1","url_pdf":"http://arxiv.org/pdf/1509.04942v1.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":"guiding-long-short-term-memory-for-image","repo_url":"https://github.com/liuqihan/Image-Caption","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"}],"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":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1509.04942","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}