{"id":141877,"date":"2011-10-24T01:43:17","date_gmt":"2011-10-24T01:43:17","guid":{"rendered":"https:\/\/staging2.simonw59.sg-host.com\/flickr-distance-a-relationship-measure-for-visual-concepts\/"},"modified":"2022-05-26T13:43:12","modified_gmt":"2022-05-26T13:43:12","slug":"flickr-distance-a-relationship-measure-for-visual-concepts","status":"publish","type":"post","link":"https:\/\/force11.org\/post\/flickr-distance-a-relationship-measure-for-visual-concepts\/","title":{"rendered":"Flickr Distance: A Relationship Measure for Visual Concepts."},"content":{"rendered":"<div class=\"ct_body\">\n<p>Authors: Wu, Lei<\/p>\n<p>Hua, Xian-Sheng<\/p>\n<p>Yu, Nenghai<\/p>\n<p>Ma, Wei-Ying<\/p>\n<p>Li, Shipeng<\/p>\n<p>This paper proposes the Flickr Distance (FD) to measure the visual correlation between concepts. For each concept, a collection of related images are obtained from the Flickr website. We assume that each concept consists of several states, e.g. different views, different semantics, etc., which are considered as latent topics. Then a latent topic visual language model (LTVLM) is built to capture these states. The Flickr distance between two concepts is defined as the Jensen-Shannon (JS) divergence between their LTVLM. Different from traditional conceptual distance measurements, which are based on Web textual documents, FD is based on the visual information. Comparing with the WordNet distance, FD can easily scale up with the increasing size of conceptual corpus. Comparing with the Google Distance (NGD) and Tag Concurrence Distance (TCD), FD uses the visual information and can properly measure the conceptual relations. We apply FD to multimedia related tasks and find methods based on FD significantly outperform those based on NGD and TCD. With the FD measurement, we also construct a large-scale visual conceptual network (VCNet) to store the knowledge of conceptual relationship. Experiments show that FD is more coherent to human cognition and it also outperforms text based distances in real-world applications.<\/p>\n<p>Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence 2011<\/p>\n<p>PMID: 21987557<\/p>\n<p>PMCID: 0<\/p>\n<p>ISSN: 1939-3539<\/p>\n<\/div>\n<p class=\"ct_meta\"><span class=\"ct_label\">Archive:<\/span>&nbsp;<a class=\"ct_archive\" target=\"_blank\" href=\"https:\/\/archive.force11.net\/node\/6354\" rel=\"noopener\">https:\/\/archive.force11.net\/node\/6354<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Authors: Wu, Lei Hua, Xian-Sheng Yu, Nenghai Ma, Wei-Ying Li, Shipeng This paper proposes the Flickr Distance (FD) to measure the visual correlation between concepts. For each concept, a collection of related images are obtained from the Flickr website. We assume that each concept consists of several states, e.g. different views, different semantics, etc., which &#8230; <a title=\"Flickr Distance: A Relationship Measure for Visual Concepts.\" class=\"read-more\" href=\"https:\/\/force11.org\/post\/flickr-distance-a-relationship-measure-for-visual-concepts\/\" aria-label=\"More on Flickr Distance: A Relationship Measure for Visual Concepts.\">Read more<\/a><\/p>\n","protected":false},"author":205903,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"advgb_blocks_editor_width":"","advgb_blocks_columns_visual_guide":"","footnotes":""},"categories":[151],"tags":[],"force11":[],"blog_series":[],"working_group":[],"class_list":["post-141877","post","type-post","status-publish","format-standard","hentry","category-news"],"acf":[],"author_meta":{"display_name":"FORCE11 Admin","author_link":"\/members\/admin"},"featured_img":null,"coauthors":[],"tax_additional":{"categories":{"linked":["<a href=\"https:\/\/force11.org\/category\/news\/\" class=\"advgb-post-tax-term\">News<\/a>"],"unlinked":["<span class=\"advgb-post-tax-term\">News<\/span>"]}},"comment_count":"0","relative_dates":{"created":"Posted 14 years ago","modified":"Updated 4 years ago"},"absolute_dates":{"created":"Posted on 24 Oct 2011","modified":"Updated on 26 May 2022"},"absolute_dates_time":{"created":"Posted on 24 Oct 2011 01:43","modified":"Updated on 26 May 2022 13:43"},"featured_img_caption":"","series_order":"","_links":{"self":[{"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/posts\/141877","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/users\/205903"}],"replies":[{"embeddable":true,"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/comments?post=141877"}],"version-history":[{"count":0,"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/posts\/141877\/revisions"}],"wp:attachment":[{"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/media?parent=141877"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/categories?post=141877"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/tags?post=141877"},{"taxonomy":"force11","embeddable":true,"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/force11?post=141877"},{"taxonomy":"blog_series","embeddable":true,"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/blog_series?post=141877"},{"taxonomy":"working_group","embeddable":true,"href":"https:\/\/force11.org\/wp-json\/wp\/v2\/working_group?post=141877"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}