{"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/exploring-nearest-neighbor-approaches-for","title":"Exploring Nearest Neighbor Approaches for Image Captioning","arxiv_id":"1505.04467","date":"2015-05-17","proceeding":null,"authors":["Jacob Devlin","Saurabh Gupta","Ross Girshick","Margaret Mitchell","C. Lawrence Zitnick"],"abstract":"We explore a variety of nearest neighbor baseline approaches for image\ncaptioning. These approaches find a set of nearest neighbor images in the\ntraining set from which a caption may be borrowed for the query image. We\nselect a caption for the query image by finding the caption that best\nrepresents the \"consensus\" of the set of candidate captions gathered from the\nnearest neighbor images. When measured by automatic evaluation metrics on the\nMS COCO caption evaluation server, these approaches perform as well as many\nrecent approaches that generate novel captions. However, human studies show\nthat a method that generates novel captions is still preferred over the nearest\nneighbor approach.","url_abs":"http://arxiv.org/abs/1505.04467v1","url_pdf":"http://arxiv.org/pdf/1505.04467v1.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":"exploring-nearest-neighbor-approaches-for","repo_url":"https://github.com/mjhucla/mRNN-CR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.04467","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}