{"id":"https://openalex.org/W1592570482","doi":"https://doi.org/10.7916/d8rv0vxx","title":"Multimodal Indexing of Presentation Videos","display_name":"Multimodal Indexing of Presentation Videos","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W1592570482","doi":"https://doi.org/10.7916/d8rv0vxx","mag":"1592570482"},"language":"en","primary_location":{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D8RV0VXX","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D8RV0VXX","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Theses"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7916/d8rv0vxx","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Merler, Michele","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Merler, Michele","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03768171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9890999794006348,"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":0.9890999794006348,"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":0.9824000000953674,"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":0.9659000039100647,"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":0.8198202848434448},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7270859479904175},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.5976067185401917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5463398694992065},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5368633270263672},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47764742374420166},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.4771042466163635},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4729977250099182},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42996945977211},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36944282054901123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35611531138420105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32671958208084106},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20904722809791565},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14265182614326477},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.12424352765083313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198202848434448},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7270859479904175},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.5976067185401917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5463398694992065},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5368633270263672},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47764742374420166},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.4771042466163635},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4729977250099182},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42996945977211},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36944282054901123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35611531138420105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32671958208084106},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20904722809791565},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14265182614326477},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.12424352765083313},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D8RV0VXX","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D8RV0VXX","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Theses"},{"id":"mag:1592570482","is_oa":false,"landing_page_url":"https://academiccommons.columbia.edu/doi/10.7916/D8RV0VXX","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.7916/d8rv0vxx","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8rv0vxx","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.7916/d8rv0vxx","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8rv0vxx","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2112539679","https://openalex.org/W3157219960","https://openalex.org/W2318501646","https://openalex.org/W3009261243","https://openalex.org/W2982625128","https://openalex.org/W1633480526","https://openalex.org/W79176538","https://openalex.org/W2612599221","https://openalex.org/W1999075139","https://openalex.org/W2024376602","https://openalex.org/W2122202368","https://openalex.org/W1919425483","https://openalex.org/W1991294445","https://openalex.org/W2466549857","https://openalex.org/W194564207","https://openalex.org/W2152433968","https://openalex.org/W2045029957","https://openalex.org/W3164862801","https://openalex.org/W2156919901","https://openalex.org/W38405592"],"abstract_inverted_index":{"This":[0,90],"thesis":[1,442],"presents":[2],"four":[3,69],"novel":[4,126,416],"methods":[5],"to":[6,46,272,291,332,344,353,380,395,421,445],"help":[7],"users":[8,444],"efficiently":[9],"and":[10,16,25,39,49,53,78,86,120,181,203,222,250,282,285,287,313,390,411,425],"effectively":[11],"retrieve":[12],"information":[13,108],"from":[14,154,240,366],"unstructured":[15,242],"unsourced":[17],"multimedia":[18],"sources,":[19],"in":[20,33,398,431],"particular":[21],"the":[22,55,58,64,98,101,110,144,155,158,187,235,354,367,382,402],"increasing":[23],"amount":[24,219],"variety":[26],"of":[27,57,138,157,166,173,190,220,231,245,280,306,318,342,387,401,406,440,462],"presentation":[28,175,243,463],"videos":[29,176,244,319],"such":[30,51],"as":[31,61,168,451,453],"those":[32],"e-learning,":[34],"conference":[35],"recordings,":[36],"corporate":[37],"talks,":[38],"student":[40],"presentations.":[41,323],"We":[42,67,161,224,300],"demonstrate":[43],"a":[44,116,125,148,206,226,266,278,348,385,448,455,460],"system":[45,102],"summarize,":[47],"index":[48],"cross-reference":[50],"videos,":[52],"measure":[54],"quality":[56,216],"produced":[59],"indexes":[60,237],"perceived":[62],"by":[63,433,464],"end":[65],"users.":[66],"introduce":[68],"major":[70],"semantic":[71],"indexing":[72],"cues:":[73],"text,":[74,114],"speaker":[75,197],"faces,":[76,198],"graphics,":[77],"mosaics,":[79,325],"going":[80],"beyond":[81],"standard":[82],"tag":[83],"based":[84,213,276,374],"searches":[85],"simple":[87],"video":[88,111,334,388,449,457],"playbacks.":[89],"work":[91,439],"aims":[92],"at":[93],"recognizing":[94],"visual":[95,281],"content":[96],"\"in":[97],"wild\",":[99],"where":[100],"cannot":[103],"rely":[104],"on":[105,214,277,315,467],"any":[106],"additional":[107],"besides":[109],"itself.":[112,160],"For":[113,196,258,324,404],"within":[115,147,454],"scene":[117],"text":[118],"detection":[119],"recognition":[121,164],"framework,":[122],"we":[123,199,260,326,413],"present":[124,414],"locally":[127],"optimal":[128,140],"adaptive":[129],"binarization":[130],"algorithm,":[131],"implemented":[132],"with":[133,150],"integral":[134],"histograms.":[135],"It":[136],"determines":[137],"an":[139,191,273],"threshold":[141],"that":[142,427],"maximizes":[143],"between-classes":[145],"variance":[146],"subwindow,":[149],"computational":[151],"complexity":[152],"independent":[153],"size":[156],"window":[159],"obtain":[162],"character":[163],"rates":[165],"74%,":[167],"validated":[169],"against":[170],"ground":[171],"truth":[172],"8":[174],"spanning":[177],"over":[178],"1":[179],"hour":[180],"45":[182,247],"minutes,":[183],"which":[184,358],"almost":[185],"doubles":[186],"baseline":[188],"performance":[189],"open":[192],"source":[193],"OCR":[194],"engine.":[195],"detect,":[200],"track,":[201],"match,":[202],"finally":[204],"select":[205,286],"humanly":[207],"preferred":[208],"face":[209,236],"icon":[210],"per":[211],"speaker,":[212],"three":[215,241,316],"measures:":[217],"resolution,":[218],"skin,":[221],"pose.":[223],"register":[225,301],"87%":[227],"accordance":[228],"(51":[229],"out":[230,305],"58":[232],"speakers)":[233],"between":[234],"automatically":[238],"generated":[239],"approximately":[246],"minutes":[248],"each,":[249],"human":[251,293],"preferences":[252,294],"recorded":[253,295],"through":[254,296,361],"Mechanical":[255,297],"Turk":[256,298],"experiments.":[257,299],"diagrams,":[259,412],"locate":[261],"graphics":[262],"inside":[263,447],"frames":[264,343,389],"showing":[265],"projected":[267],"slide,":[268],"cluster":[269],"them":[270],"according":[271,352],"on-line":[274],"algorithm":[275,376],"combination":[279],"temporal":[283],"information,":[284],"color-correct":[288],"their":[289],"representatives":[290],"match":[292],"71%":[302],"accuracy":[303],"(57":[304],"81":[307],"unique":[308],"diagrams":[309],"properly":[310],"identified,":[311],"selected":[312],"color-corrected)":[314],"hours":[317],"containing":[320,470],"five":[321],"different":[322],"combine":[327],"two":[328,405,415],"existing":[329],"suturing":[330],"measures,":[331],"extend":[333],"images":[335],"into":[336,347],"in-the-world":[337],"coordinate":[338],"system.":[339],"A":[340,371],"set":[341,386],"be":[345],"registered":[346],"mosaic":[349],"are":[350,429],"sampled":[351],"PTZ":[355],"camera":[356],"movement,":[357],"is":[359,377,393],"computed":[360],"least":[362],"square":[363],"estimation":[364],"starting":[365],"luminance":[368],"constancy":[369],"assumption.":[370],"local":[372],"features":[373],"stitching":[375],"then":[378],"applied":[379],"estimate":[381],"homography":[383],"among":[384],"median":[391],"blending":[392],"used":[394],"render":[396],"pixels":[397],"overlapping":[399],"regions":[400],"mosaic.":[403],"these":[407],"indexes,":[408],"namely":[409],"faces":[410],"MTurk-derived":[417],"user":[418],"data":[419],"collections":[420],"determine":[422],"viewer":[423],"preferences,":[424],"show":[426],"they":[428],"matched":[430],"selection":[432],"our":[434],"methods.":[435],"The":[436],"net":[437],"result":[438],"this":[441],"allows":[443],"search,":[446],"collection":[450],"well":[452],"single":[456],"clip,":[458],"for":[459],"segment":[461],"professor":[465],"X":[466],"topic":[468],"Y,":[469],"graph":[471],"Z.":[472]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
