{"id":"https://openalex.org/W2069021608","doi":"https://doi.org/10.1145/2324796.2324856","title":"Large vocabulary quantization for searching instances from videos","display_name":"Large vocabulary quantization for searching instances from videos","publication_year":2012,"publication_date":"2012-06-05","ids":{"openalex":"https://openalex.org/W2069021608","doi":"https://doi.org/10.1145/2324796.2324856","mag":"2069021608"},"language":"en","primary_location":{"id":"doi:10.1145/2324796.2324856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324856","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","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/A5014425044","display_name":"Cai-Zhi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Cai-Zhi Zhu","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","(National Institute of Informatics, Tokyo, Japan)"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"(National Institute of Informatics, Tokyo, Japan)","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102743927","display_name":"Shin\u2019ichi Satoh","orcid":"https://orcid.org/0000-0001-6995-6447"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shin'ichi Satoh","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","(National Institute of Informatics, Tokyo, Japan)"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"(National Institute of Informatics, Tokyo, Japan)","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014425044"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":6.8637,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97448266,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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":0.9969000220298767,"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":0.8313959836959839},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6391788721084595},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.6367469429969788},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6324692964553833},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5568251013755798},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5306749939918518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5121800899505615},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4567472040653229},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3569791316986084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.327333927154541},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.25111687183380127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313959836959839},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6391788721084595},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.6367469429969788},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6324692964553833},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5568251013755798},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5306749939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5121800899505615},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4567472040653229},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3569791316986084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.327333927154541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25111687183380127},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2324796.2324856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324856","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1967879792","https://openalex.org/W2001287648","https://openalex.org/W2101087387","https://openalex.org/W2104978738","https://openalex.org/W2118355530","https://openalex.org/W2128017662","https://openalex.org/W2131846894","https://openalex.org/W2141362318","https://openalex.org/W2147237076","https://openalex.org/W2148809531","https://openalex.org/W2151103935","https://openalex.org/W2152898476","https://openalex.org/W2166742463","https://openalex.org/W2172188317","https://openalex.org/W6675021974"],"related_works":["https://openalex.org/W2385368906","https://openalex.org/W2902924992","https://openalex.org/W2626642044","https://openalex.org/W2619807045","https://openalex.org/W2388758053","https://openalex.org/W93537448","https://openalex.org/W2949734191","https://openalex.org/W2017333877","https://openalex.org/W2048332520","https://openalex.org/W4233821346"],"abstract_inverted_index":{"A":[0],"very":[1],"promising":[2,188],"application":[3],"involving":[4],"video":[5,12,16],"collections":[6],"is":[7,36,76,155,177,208],"to":[8,39,72,102,158,192,209,214],"search":[9,130,138],"for":[10,75,128,204,230,234],"relevant":[11],"segments":[13],"from":[14,108],"a":[15,28,58,69,88,187,228],"database":[17],"when":[18],"given":[19],"few":[20],"visual":[21],"examples":[22],"of":[23,60,68,115,163,218],"the":[24,40,66,136,146,164,173,195,202],"specific":[25,70],"instance,":[26,181],"e.g.":[27],"person,":[29],"object,":[30],"or":[31],"place.":[32],"However,":[33],"this":[34,53,85,116,206],"problem":[35,86],"difficult":[37],"due":[38,157],"lighting":[41],"variations,":[42],"different":[43],"viewpoints,":[44],"partial":[45],"occlusion,":[46],"and":[47,182],"large":[48,89],"changes":[49],"in":[50,87,120,172,190],"appearance.":[51],"In":[52],"paper,":[54],"we":[55,105,124,149],"focus":[56],"on":[57,79,100,135],"kind":[59],"restricted":[61],"instance":[62,71,111,129,137,166,221],"searching":[63,235],"task,":[64],"where":[65],"region":[67],"be":[73,201],"searched":[74],"manually":[77],"labeled":[78,110,220],"each":[80],"query":[81],"image.":[82],"We":[83,223],"formulate":[84],"vocabulary":[90],"quantization":[91],"based":[92],"Bag-of-Words":[93],"framework,":[94],"while":[95],"putting":[96],"more":[97,178,211],"research":[98,226],"emphasis":[99],"investigating":[101],"what":[103],"extent":[104],"can":[106],"benefit":[107],"these":[109],"regions.":[112,222],"The":[113],"contribution":[114],"paper":[117],"mainly":[118,156],"lies":[119],"two":[121],"aspects:":[122],"first,":[123],"proposed":[125],"an":[126],"algorithm":[127],"that":[131,151,171,186],"outperformed":[132],"all":[133],"submissions":[134],"dataset":[139,175],"TRECVID":[140],"2011.":[141],"Secondly,":[142],"after":[143],"thoroughly":[144],"analyzing":[145],"experiment":[147],"results,":[148],"show":[150],"our":[152,225],"top":[153],"performance":[154],"similar":[159],"scene":[160],"retrieval,":[161],"instead":[162],"same":[165],"search.":[167],"This":[168],"observation":[169],"reveals":[170],"current":[174,196],"background":[176],"dominated":[179],"than":[180],"it":[183],"also":[184,200],"suggests":[185],"direction":[189],"which":[191,198],"further":[193],"improve":[194],"algorithm,":[197],"may":[199],"breakthrough":[203],"achieving":[205],"challenge,":[207],"investigate":[210],"about":[212],"how":[213],"truly":[215],"take":[216],"advantage":[217],"additional":[219],"believe":[224],"opens":[227],"window":[229],"future":[231],"new":[232],"methods":[233],"instance.":[236]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}