{"id":"https://openalex.org/W2140369944","doi":"https://doi.org/10.1109/mmsp.2004.1436589","title":"Mapping image segments to words for image retrieval","display_name":"Mapping image segments to words for image retrieval","publication_year":2005,"publication_date":"2005-06-07","ids":{"openalex":"https://openalex.org/W2140369944","doi":"https://doi.org/10.1109/mmsp.2004.1436589","mag":"2140369944"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2004.1436589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109045955","display_name":"Akihiko Nakagawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Nakagawa","raw_affiliation_strings":["Japan Systems Company Limited, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Systems Company Limited, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103000544","display_name":"Shogo Arai","orcid":"https://orcid.org/0000-0001-9736-3008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Arai","raw_affiliation_strings":["Japan Systems Company Limited, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Systems Company Limited, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037140642","display_name":"Andrea Kutics","orcid":null},"institutions":[{"id":"https://openalex.org/I148798404","display_name":"Tokyo University of Technology","ror":"https://ror.org/021a26605","country_code":"JP","type":"education","lineage":["https://openalex.org/I148798404"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"A. Kutics","raw_affiliation_strings":["School of Media Science, Tokyo University of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Media Science, Tokyo University of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I148798404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102991360","display_name":"Hiroshi Tanaka","orcid":"https://orcid.org/0000-0002-3856-8588"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Tanaka","raw_affiliation_strings":["Media Handling Technology Group, NTT Data Corporation Limited, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Handling Technology Group, NTT Data Corporation Limited, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19653179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"438","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8389468193054199},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.8014795184135437},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.7689016461372375},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.6892300248146057},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.6068570613861084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6050618290901184},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5900825262069702},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5831331014633179},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5765115022659302},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5310830473899841},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.49569547176361084},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4661024808883667},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.45523619651794434},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.42695310711860657},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41965028643608093},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4125830829143524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4052804708480835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389468193054199},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.8014795184135437},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.7689016461372375},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.6892300248146057},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.6068570613861084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050618290901184},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5900825262069702},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5831331014633179},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5765115022659302},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5310830473899841},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.49569547176361084},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4661024808883667},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.45523619651794434},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.42695310711860657},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41965028643608093},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4125830829143524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4052804708480835},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2004.1436589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1505889224","https://openalex.org/W1964468377","https://openalex.org/W2011671268","https://openalex.org/W2020045104","https://openalex.org/W2095650959","https://openalex.org/W2098031085","https://openalex.org/W2136507825","https://openalex.org/W2137471889","https://openalex.org/W4235505822","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2416959398","https://openalex.org/W1987618107","https://openalex.org/W1595732891","https://openalex.org/W2735794310","https://openalex.org/W2186394444","https://openalex.org/W2095842132","https://openalex.org/W2761229199","https://openalex.org/W2605741187","https://openalex.org/W1968020859","https://openalex.org/W2373526234"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,90],"new":[4],"method":[5,53,109],"for":[6,15,126],"mapping":[7,102],"image":[8,16,50,93,133],"segments":[9],"to":[10,23,67,73,104,122],"words":[11,82],"in":[12,100,131],"three":[13],"layers":[14],"retrieval.":[17],"Our":[18],"main":[19],"goal":[20],"here":[21],"is":[22,54,120],"incorporate":[24],"higher-level":[25],"semantics":[26],"into":[27],"the":[28,34,37,41,48],"retrieval":[29,106,130],"process":[30],"and":[31,40,63,70,81,116,119,129],"thus":[32],"narrow":[33],"gap":[35],"between":[36,77],"user's":[38],"interpretation":[39],"automatically":[42],"extracted":[43],"low-level":[44],"visual":[45,69,78,114],"features":[46,72],"of":[47,83],"same":[49],"content.":[51],"The":[52,108],"based":[55],"on":[56,89],"nonlinear":[57],"segmentation,":[58],"as":[59,61],"well":[60],"clustering":[62],"statistical":[64],"learning":[65],"applied":[66],"both":[68],"textual":[71,112],"find":[74],"semantic":[75,98],"relations":[76],"segment":[79],"clusters":[80],"various":[84,111],"abstraction":[85],"levels.":[86],"Experiments":[87],"conducted":[88],"wide,":[91],"natural":[92],"domain":[94],"shows":[95],"that":[96],"step-by-step":[97],"inferencing":[99],"image-word":[101],"helps":[103],"improve":[105],"performance.":[107],"supports":[110],"and/or":[113],"browsing":[115,128],"searching":[117],"schemes":[118],"proved":[121],"be":[123],"very":[124],"useful":[125],"effective":[127],"large":[132],"data":[134],"sets.":[135]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}