{"id":"https://openalex.org/W2055295637","doi":"https://doi.org/10.1145/2647868.2654964","title":"Multi-modal Language Models for Lecture Video Retrieval","display_name":"Multi-modal Language Models for Lecture Video Retrieval","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2055295637","doi":"https://doi.org/10.1145/2647868.2654964","mag":"2055295637"},"language":"en","primary_location":{"id":"doi:10.1145/2647868.2654964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd 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/A5103172393","display_name":"Huizhong Chen","orcid":"https://orcid.org/0000-0002-9160-6571"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huizhong Chen","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069841532","display_name":"Matthew Cooper","orcid":"https://orcid.org/0000-0003-2395-8628"},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Cooper","raw_affiliation_strings":["FX Palo Alto Laboratory, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103960169","display_name":"Dhiraj Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhiraj Joshi","raw_affiliation_strings":["FX Palo Alto Laboratory, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FX Palo Alto Laboratory, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004042863","display_name":"Bernd Girod","orcid":"https://orcid.org/0000-0001-6950-1020"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernd Girod","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9888,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.80543312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1081","last_page":"1084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8269603252410889},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.61534184217453},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.5965743064880371},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5865563750267029},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5751182436943054},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.5630908012390137},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5492779612541199},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5113312602043152},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5065220594406128},{"id":"https://openalex.org/keywords/divergence-from-randomness-model","display_name":"Divergence-from-randomness model","score":0.5032019019126892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5007967948913574},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.4695233404636383},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.45184823870658875},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4448108673095703},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4355148673057556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269603252410889},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.61534184217453},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.5965743064880371},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5865563750267029},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5751182436943054},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.5630908012390137},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5492779612541199},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5113312602043152},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5065220594406128},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.5032019019126892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5007967948913574},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.4695233404636383},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.45184823870658875},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4448108673095703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4355148673057556},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2647868.2654964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1880262756","https://openalex.org/W2020842694","https://openalex.org/W2068491199","https://openalex.org/W2073857938","https://openalex.org/W2101121293","https://openalex.org/W2106277773","https://openalex.org/W2129172019","https://openalex.org/W2134731454","https://openalex.org/W2157341099","https://openalex.org/W2161301211","https://openalex.org/W2166697331","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2588002110","https://openalex.org/W2373137943","https://openalex.org/W2364497041","https://openalex.org/W2042126095","https://openalex.org/W2347927631","https://openalex.org/W2367834105","https://openalex.org/W2367597551","https://openalex.org/W1553347578","https://openalex.org/W2076813128","https://openalex.org/W2390241730"],"abstract_inverted_index":{"We":[0],"propose":[1],"Multi-modal":[2],"Language":[3],"Models":[4],"(MLMs),":[5],"which":[6],"adapt":[7],"latent":[8],"variable":[9],"techniques":[10],"for":[11,49],"document":[12],"analysis":[13],"to":[14,31,88],"exploring":[15],"co-occurrence":[16],"relationships":[17],"in":[18,38,79],"multi-modal":[19,45],"data.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"focus":[25],"on":[26],"the":[27,66,80,91,94,99],"application":[28],"of":[29,93],"MLMs":[30,85],"indexing":[32],"text":[33,96],"from":[34,98],"slides":[35],"and":[36,41,70],"speech":[37],"lecture":[39,50],"videos,":[40],"subsequently":[42],"employ":[43],"a":[44],"probabilistic":[46],"ranking":[47],"function":[48],"video":[51],"retrieval.":[52],"The":[53],"MLM":[54],"achieves":[55],"highly":[56],"competitive":[57],"results":[58],"against":[59],"well":[60],"established":[61],"retrieval":[62,82],"methods":[63],"such":[64],"as":[65],"Vector":[67],"Space":[68],"Model":[69],"Probabilistic":[71],"Latent":[72],"Semantic":[73],"Analysis.":[74],"When":[75],"noise":[76],"is":[77,86],"present":[78],"data,":[81],"performance":[83],"with":[84,90],"shown":[87],"improve":[89],"quality":[92],"spoken":[95],"extracted":[97],"video.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}