{"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/bags-of-local-convolutional-features-for","title":"Bags of Local Convolutional Features for Scalable Instance Search","arxiv_id":"1604.04653","date":"2016-04-15","proceeding":null,"authors":["Eva Mohedano","Amaia Salvador","Kevin McGuinness","Ferran Marques","Noel E. O'Connor","Xavier Giro-i-Nieto"],"abstract":"This work proposes a simple instance retrieval pipeline based on encoding the\nconvolutional features of CNN using the bag of words aggregation scheme (BoW).\nAssigning each local array of activations in a convolutional layer to a visual\nword produces an \\textit{assignment map}, a compact representation that relates\nregions of an image with a visual word. We use the assignment map for fast\nspatial reranking, obtaining object localizations that are used for query\nexpansion. We demonstrate the suitability of the BoW representation based on\nlocal CNN features for instance retrieval, achieving competitive performance on\nthe Oxford and Paris buildings benchmarks. We show that our proposed system for\nCNN feature aggregation with BoW outperforms state-of-the-art techniques using\nsum pooling at a subset of the challenging TRECVid INS benchmark.","url_abs":"http://arxiv.org/abs/1604.04653v1","url_pdf":"http://arxiv.org/pdf/1604.04653v1.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":"bags-of-local-convolutional-features-for","repo_url":"https://github.com/imatge-upc/retrieval-2016-icmr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok"}},{"paper_slug":"bags-of-local-convolutional-features-for","repo_url":"https://github.com/hbwang1427/image_retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instance-search","task_name":"Instance Search"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1604.04653","atlas_url":"https://app.syntology.ai/?focus=1604.04653","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}