{"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/socializing-the-semantic-gap-a-comparative","title":"Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval","arxiv_id":"1503.08248","date":"2015-03-28","proceeding":null,"authors":["Xirong Li","Tiberio Uricchio","Lamberto Ballan","Marco Bertini","Cees G. M. Snoek","Alberto del Bimbo"],"abstract":"Where previous reviews on content-based image retrieval emphasize on what can\nbe seen in an image to bridge the semantic gap, this survey considers what\npeople tag about an image. A comprehensive treatise of three closely linked\nproblems, i.e., image tag assignment, refinement, and tag-based image retrieval\nis presented. While existing works vary in terms of their targeted tasks and\nmethodology, they rely on the key functionality of tag relevance, i.e.\nestimating the relevance of a specific tag with respect to the visual content\nof a given image and its social context. By analyzing what information a\nspecific method exploits to construct its tag relevance function and how such\ninformation is exploited, this paper introduces a taxonomy to structure the\ngrowing literature, understand the ingredients of the main works, clarify their\nconnections and difference, and recognize their merits and limitations. For a\nhead-to-head comparison between the state-of-the-art, a new experimental\nprotocol is presented, with training sets containing 10k, 100k and 1m images\nand an evaluation on three test sets, contributed by various research groups.\nEleven representative works are implemented and evaluated. Putting all this\ntogether, the survey aims to provide an overview of the past and foster\nprogress for the near future.","url_abs":"http://arxiv.org/abs/1503.08248v3","url_pdf":"http://arxiv.org/pdf/1503.08248v3.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":"socializing-the-semantic-gap-a-comparative","repo_url":"https://github.com/li-xirong/jingwei","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"content-based-image-retrieval","task_name":"Content-Based Image Retrieval"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"survey","task_name":"Survey"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}