{"id":"https://openalex.org/W4319348862","doi":"https://doi.org/10.1145/3583138","title":"Self-contained Entity Discovery from Captioned Videos","display_name":"Self-contained Entity Discovery from Captioned Videos","publication_year":2023,"publication_date":"2023-02-07","ids":{"openalex":"https://openalex.org/W4319348862","doi":"https://doi.org/10.1145/3583138"},"language":"en","primary_location":{"id":"doi:10.1145/3583138","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583138","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583138","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583138","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087029929","display_name":"Melika Ayoughi","orcid":"https://orcid.org/0000-0002-6847-5999"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Melika Ayoughi","raw_affiliation_strings":["University of Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000845063","display_name":"Pascal Mettes","orcid":"https://orcid.org/0000-0001-9275-5942"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Pascal Mettes","raw_affiliation_strings":["University of Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034924491","display_name":"Paul Groth","orcid":"https://orcid.org/0000-0003-0183-6910"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paul Groth","raw_affiliation_strings":["University of Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087029929"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.1215,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35978048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"19","issue":"5s","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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":0.8444439768791199},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7234601974487305},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7122812271118164},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5765906572341919},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.47771739959716797},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4455323815345764},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4430631101131439},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4377206861972809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40108492970466614},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3241911232471466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8444439768791199},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7234601974487305},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7122812271118164},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5765906572341919},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.47771739959716797},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4455323815345764},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4430631101131439},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4377206861972809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40108492970466614},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3241911232471466},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3583138","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583138","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583138","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:publications/afbdc147-7c6c-4667-bdc1-277c58f64a13","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/selfcontained-entity-discovery-from-captioned-videos(afbdc147-7c6c-4667-bdc1-277c58f64a13).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ayoughi, M, Mettes, P & Groth, P 2023, 'Self-Contained Entity Discovery from Captioned Videos', ACM Transactions on Multimedia Computing Communications and Applications, vol. 19, no. 5s, 177. https://doi.org/10.1145/3583138","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:openaire/afbdc147-7c6c-4667-bdc1-277c58f64a13","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/afbdc147-7c6c-4667-bdc1-277c58f64a13","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ayoughi, M, Mettes, P & Groth, P 2023, 'Self-Contained Entity Discovery from Captioned Videos', ACM Transactions on Multimedia Computing Communications and Applications, vol. 19, no. 5s, 177. https://doi.org/10.1145/3583138","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3583138","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583138","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583138","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319348862.pdf","grobid_xml":"https://content.openalex.org/works/W4319348862.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1976561871","https://openalex.org/W2911132372","https://openalex.org/W2913822893","https://openalex.org/W2913950831","https://openalex.org/W2914699769","https://openalex.org/W2953461088","https://openalex.org/W3206241239","https://openalex.org/W4242079786"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2073713056","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W3110702597"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"the":[3,13,58,68,108,150,173,183,186,212,223,239],"task":[4],"of":[5,61,188,226,229],"visual":[6,144,231],"named":[7,194],"entity":[8,145,151,195,232],"discovery":[9,228],"in":[10,33,118,216],"videos":[11,119,121],"without":[12],"need":[14],"for":[15,233],"task-specific":[16,19,87],"supervision":[17],"or":[18,31,125,200],"external":[20,72],"knowledge":[21,73,88],"sources.":[22],"Assigning":[23],"specific":[24],"names":[25],"to":[26,98,115,191,197,206],"entities":[27,53,117],"(e.g.,":[28],"faces,":[29],"scenes,":[30],"objects)":[32],"video":[34],"frames":[35],"is":[36,43],"a":[37,46,110,129,207],"long-standing":[38],"challenge.":[39],"Commonly,":[40],"this":[41,62,104,159],"problem":[42,69,109],"addressed":[44],"as":[45,76],"supervised":[47,208],"learning":[48],"objective":[49],"by":[50,70],"manually":[51],"annotating":[52],"with":[54,202],"labels.":[55],"To":[56,157],"bypass":[57],"annotation":[59],"burden":[60],"setup,":[63],"several":[64],"works":[65],"have":[66],"investigated":[67],"utilizing":[71],"sources":[74,89],"such":[75,81],"movie":[77],"databases.":[78],"While":[79],"effective,":[80],"approaches":[82],"do":[83],"not":[84,91],"work":[85],"when":[86],"are":[90,241],"provided":[92],"and":[93,100,113,122,147,168,175,238],"can":[94],"only":[95],"be":[96],"applied":[97],"movies":[99],"TV":[101,179],"series.":[102,180],"In":[103],"work,":[105],"we":[106,133,162],"take":[107],"step":[111],"further":[112],"propose":[114],"discover":[116,192],"from":[120,139,211],"corresponding":[123],"captions":[124],"subtitles.":[126],"We":[127],"introduce":[128],"three-stage":[130],"method":[131],"where":[132],"(i)":[134],"create":[135],"bipartite":[136],"entity-name":[137],"graphs":[138],"frame\u2013caption":[140],"pairs,":[141],"(ii)":[142],"find":[143],"agreements,":[146],"(iii)":[148],"refine":[149],"assignment":[152],"through":[153],"entity-level":[154],"prototype":[155],"construction.":[156],"tackle":[158],"new":[160,165],"problem,":[161],"outline":[163],"two":[164],"benchmarks,":[166],"SC-Friends":[167],"SC-BBT":[169],",":[170],"based":[171],"on":[172,182,243],"Friends":[174],"Big":[176],"Bang":[177],"Theory":[178],"Experiments":[181],"benchmarks":[184],"demonstrate":[185],"ability":[187],"our":[189,219],"approach":[190],"which":[193,198],"belongs":[196],"face":[199],"scene,":[201],"an":[203],"accuracy":[204],"close":[205],"oracle,":[209],"just":[210],"multimodal":[213],"information":[214],"present":[215],"videos.":[217],"Additionally,":[218],"qualitative":[220],"examples":[221],"show":[222],"potential":[224],"challenges":[225],"self-contained":[227],"any":[230],"future":[234],"work.":[235],"The":[236],"code":[237],"data":[240],"available":[242],"GitHub.":[244],"1":[245]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
