{"id":"https://openalex.org/W1963617585","doi":"https://doi.org/10.1145/1180639.1180856","title":"Toward bridging the annotation-retrieval gap in image search by a generative modeling approach","display_name":"Toward bridging the annotation-retrieval gap in image search by a generative modeling approach","publication_year":2006,"publication_date":"2006-10-23","ids":{"openalex":"https://openalex.org/W1963617585","doi":"https://doi.org/10.1145/1180639.1180856","mag":"1963617585"},"language":"en","primary_location":{"id":"doi:10.1145/1180639.1180856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1180639.1180856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Multimedia","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/A5022942500","display_name":"Ritendra Datta","orcid":"https://orcid.org/0000-0002-6547-0543"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ritendra Datta","raw_affiliation_strings":["Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103583462","display_name":"Weina Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weina Ge","raw_affiliation_strings":["Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405681","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-3108-8645"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100687159","display_name":"James Z. Wang","orcid":"https://orcid.org/0000-0003-4379-4173"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Z. Wang","raw_affiliation_strings":["Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3109,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96979949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"977","last_page":"986"},"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9854000210762024,"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":0.8040560483932495},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.7951527833938599},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.7777012586593628},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.6448875665664673},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6119641661643982},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5968285799026489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5751548409461975},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4823014736175537},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4529409408569336},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4528837502002716},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44728559255599976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43410491943359375},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.42206352949142456},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4149155020713806},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.4137979745864868},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4117893576622009},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39629632234573364},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.31772080063819885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040560483932495},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.7951527833938599},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.7777012586593628},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.6448875665664673},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6119641661643982},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5968285799026489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5751548409461975},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4823014736175537},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4529409408569336},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4528837502002716},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44728559255599976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43410491943359375},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.42206352949142456},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4149155020713806},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4137979745864868},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4117893576622009},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39629632234573364},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.31772080063819885},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1180639.1180856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1180639.1180856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W79749824","https://openalex.org/W2024368999","https://openalex.org/W2039118116","https://openalex.org/W2044542000","https://openalex.org/W2066060819","https://openalex.org/W2070473734","https://openalex.org/W2081580037","https://openalex.org/W2102734279","https://openalex.org/W2107034620","https://openalex.org/W2109868644","https://openalex.org/W2111103876","https://openalex.org/W2117489663","https://openalex.org/W2118886759","https://openalex.org/W2121004760","https://openalex.org/W2129758682","https://openalex.org/W2130660124","https://openalex.org/W2133598579","https://openalex.org/W2136595724","https://openalex.org/W2137918516","https://openalex.org/W2138454757","https://openalex.org/W2143314306","https://openalex.org/W2144407188","https://openalex.org/W2150692003","https://openalex.org/W2156336347","https://openalex.org/W2158275940","https://openalex.org/W2534712034","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2111630109","https://openalex.org/W2172231696","https://openalex.org/W2496710287","https://openalex.org/W2735794310","https://openalex.org/W2095842132","https://openalex.org/W2186394444","https://openalex.org/W2605741187","https://openalex.org/W2155479236","https://openalex.org/W2373526234","https://openalex.org/W2285171871"],"abstract_inverted_index":{"While":[0],"automatic":[1],"image":[2,12,26,45,63],"annotation":[3,150],"remains":[4],"an":[5,24],"actively":[6],"pursued":[7],"research":[8],"topic,":[9],"enhancement":[10],"of":[11,35,57,118,131,169,182,197],"search":[13],"through":[14,202],"its":[15],"use":[16],"has":[17],"not":[18],"been":[19],"extensively":[20],"explored.":[21],"We":[22],"propose":[23],"annotation-driven":[25],"retrieval":[27,95],"approach":[28,81,199],"and":[29,60,68,146,165],"argue":[30],"that":[31],"under":[32],"a":[33,86,100,166],"number":[34],"different":[36],"scenarios,":[37],"this":[38,98],"is":[39,51,108,189,200],"very":[40],"effective":[41],"for":[42],"semantically":[43],"meaningful":[44],"search.":[46],"In":[47],"particular,":[48],"our":[49,80,198],"system":[50],"demonstrated":[52],"to":[53,110,139,156,171,191],"effectively":[54],"handle":[55],"cases":[56],"partially":[58],"tagged":[59],"completely":[61],"untagged":[62],"databases,":[64],"multiple":[65],"keyword":[66],"queries,":[67],"example":[69],"based":[70,94,159,186],"queries":[71],"with":[72,123],"or":[73],"without":[74],"tags,":[75],"all":[76],"in":[77,144],"near-realtime.":[78],"Because":[79],"utilizes":[82,152],"extra":[83],"knowledge":[84],"from":[85,105],"training":[87],"dataset,":[88],"it":[89],"outperforms":[90],"state-of-the-art":[91],"visual":[92],"similarity":[93],"techniques.":[96],"For":[97],"purpose,":[99],"novel":[101,149],"structure-composition":[102],"model":[103,121,127],"constructed":[104],"Beta":[106],"distributions":[107],"developed":[109],"capture":[111],"the":[112,124,153],"spatial":[113],"relationship":[114],"among":[115],"segmented":[116],"regions":[117],"images.":[119,133],"This":[120],"combined":[122],"Gaussian":[125],"mixture":[126],"produces":[128],"scalable":[129],"categorization":[130,135,154],"generic":[132],"The":[134,195],"results":[136,143,155],"are":[137],"found":[138],"surpass":[140],"previously":[141],"reported":[142],"speed":[145],"accuracy.":[147],"Our":[148],"framework":[151],"select":[157],"tags":[158,174],"on":[160,187],"term":[161,163],"frequency,":[162],"saliency,":[164],"WordNet-based":[167],"measure":[168,185],"congruity,":[170],"boost":[172],"salient":[173],"while":[175],"penalizing":[176],"potentially":[177],"unrelated":[178],"ones.":[179],"A":[180],"bag":[181],"words":[183],"distance":[184],"WordNet":[188],"used":[190],"compute":[192],"semantic":[193],"similarity.":[194],"effectiveness":[196],"shown":[201],"extensive":[203],"experiments.":[204]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}