{"id":"https://openalex.org/W4402980118","doi":"https://doi.org/10.1109/icme57554.2024.10687550","title":"ProTA: Probabilistic Token Aggregation for Text-Video Retrieval","display_name":"ProTA: Probabilistic Token Aggregation for Text-Video Retrieval","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980118","doi":"https://doi.org/10.1109/icme57554.2024.10687550"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5020428892","display_name":"Han Fang","orcid":"https://orcid.org/0000-0002-4379-2971"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Fang","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&#x0026;AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&#x0026;AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047237045","display_name":"Xianghao Zang","orcid":"https://orcid.org/0000-0001-8421-7167"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghao Zang","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&#x0026;AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&#x0026;AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093130774","display_name":"Chao Ban","orcid":"https://orcid.org/0009-0000-8114-103X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Ban","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&#x0026;AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&#x0026;AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019172074","display_name":"Zerun Feng","orcid":"https://orcid.org/0000-0003-3987-0591"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zerun Feng","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&#x0026;AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&#x0026;AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082212103","display_name":"Lanxiang Zhou","orcid":"https://orcid.org/0009-0009-7003-287X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanxiang Zhou","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&#x0026;AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&#x0026;AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101320954","display_name":"Zhongjiang He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjiang He","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&#x0026;AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&#x0026;AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373511","display_name":"Yongxiang Li","orcid":"https://orcid.org/0000-0003-0618-6857"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxiang Li","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&#x0026;AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&#x0026;AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063142903","display_name":"Hao Sun","orcid":"https://orcid.org/0009-0007-7917-1628"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&#x0026;AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&#x0026;AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2927,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81656704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9973000288009644,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9973000288009644,"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":0.9955999851226807,"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":0.9918000102043152,"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":0.8223254680633545},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7794828414916992},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6445118188858032},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4695813059806824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.369076132774353},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.34539568424224854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223254680633545},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7794828414916992},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6445118188858032},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4695813059806824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.369076132774353},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.34539568424224854}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2796207103","https://openalex.org/W2892605456","https://openalex.org/W2914699769","https://openalex.org/W2963017553","https://openalex.org/W2965458216","https://openalex.org/W3043840704","https://openalex.org/W3145807616","https://openalex.org/W3153005511","https://openalex.org/W3168433561","https://openalex.org/W3168640669","https://openalex.org/W3180463990","https://openalex.org/W3197804339","https://openalex.org/W3204588463","https://openalex.org/W4221146248","https://openalex.org/W4285606530","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312655527","https://openalex.org/W4313007634","https://openalex.org/W4386072365","https://openalex.org/W6682778277","https://openalex.org/W6750041603","https://openalex.org/W6754822074","https://openalex.org/W6766582784","https://openalex.org/W6791353385","https://openalex.org/W6801013943","https://openalex.org/W6810042059","https://openalex.org/W6891781542"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4387768015","https://openalex.org/W4285141722"],"abstract_inverted_index":{"Text-video":[0],"retrieval":[1],"aims":[2],"to":[3,59,72,89,108],"find":[4],"the":[5,19,33,96],"most":[6],"relevant":[7],"cross-modal":[8,61,111],"samples":[9],"for":[10],"a":[11,41],"given":[12],"query.":[13],"Recent":[14],"methods":[15],"focus":[16],"on":[17,115,122],"modeling":[18],"whole":[20],"spatial-temporal":[21],"relations.":[22],"However,":[23],"since":[24],"video":[25],"clips":[26],"contain":[27],"more":[28],"diverse":[29],"content":[30,64],"than":[31],"captions,":[32],"model":[34],"aligning":[35],"these":[36],"asymmetric":[37],"video-text":[38],"pairs":[39],"has":[40],"high":[42],"risk":[43],"of":[44],"retrieving":[45],"many":[46],"false":[47],"positive":[48],"results.":[49],"In":[50,100],"this":[51],"paper,":[52],"we":[53,67],"propose":[54,68,85],"Probabilistic":[55],"Token":[56],"Aggregation":[57],"(ProTA)":[58],"handle":[60],"interaction":[62],"with":[63],"asymmetry.":[65],"Specifically,":[66],"dual":[69],"partial-related":[70],"aggregation":[71],"disentangle":[73],"and":[74,81,94,127],"re-aggregate":[75],"token":[76],"representations":[77],"in":[78],"both":[79],"low-dimension":[80],"high-dimension":[82],"spaces.":[83],"We":[84],"token-based":[86],"probabilistic":[87,92],"alignment":[88],"generate":[90],"token-level":[91],"representation":[93,98],"maintain":[95],"feature":[97],"diversity.":[99],"addition,":[101],"an":[102],"adaptive":[103],"contrastive":[104],"loss":[105],"is":[106],"proposed":[107],"learn":[109],"compact":[110],"distribution":[112],"space.":[113],"Based":[114],"extensive":[116],"experiments,":[117],"ProTA":[118],"achieves":[119],"significant":[120],"improvements":[121],"MSR-VTT":[123],"(50.9%),":[124],"LSMDC":[125],"(25.8%),":[126],"DiDeMo":[128],"(47.2%).":[129]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-21T07:57:09.225873","created_date":"2025-10-10T00:00:00"}
