{"id":"https://openalex.org/W4224214654","doi":"https://doi.org/10.1145/3477495.3531899","title":"Modality-Balanced Embedding for Video Retrieval","display_name":"Modality-Balanced Embedding for Video Retrieval","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4224214654","doi":"https://doi.org/10.1145/3477495.3531899"},"language":"en","primary_location":{"id":"doi:10.1145/3477495.3531899","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531899","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100333854","display_name":"Xun Wang","orcid":"https://orcid.org/0000-0002-2741-433X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xun Wang","raw_affiliation_strings":["Kuaishou, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024761156","display_name":"Bingqing Ke","orcid":"https://orcid.org/0009-0003-4583-8798"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingqing Ke","raw_affiliation_strings":["Kuaishou, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070696659","display_name":"Xuanping Li","orcid":"https://orcid.org/0009-0007-1369-3407"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanping Li","raw_affiliation_strings":["Kuaishou, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026154387","display_name":"Fangyu Liu","orcid":"https://orcid.org/0000-0001-7038-3623"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fangyu Liu","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394511","display_name":"Mingyu Zhang","orcid":"https://orcid.org/0000-0001-5443-2835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyu Zhang","raw_affiliation_strings":["Kuaishou, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029456834","display_name":"Xiao Liang","orcid":"https://orcid.org/0000-0003-4074-340X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Liang","raw_affiliation_strings":["Kuaishou, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111638778","display_name":"Qiushi Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiushi Xiao","raw_affiliation_strings":["Kuaishou, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2578","last_page":"2582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.8254226446151733},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8155533075332642},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6387140154838562},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.591917872428894},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5533928275108337},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5479018688201904},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5321929454803467},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.49049872159957886},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4859408140182495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43031591176986694},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.411590039730072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19046670198440552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254226446151733},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8155533075332642},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6387140154838562},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.591917872428894},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5533928275108337},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5479018688201904},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5321929454803467},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.49049872159957886},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4859408140182495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43031591176986694},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.411590039730072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19046670198440552},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477495.3531899","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531899","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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":11,"referenced_works":["https://openalex.org/W2136189984","https://openalex.org/W2163922914","https://openalex.org/W2987875759","https://openalex.org/W2997035654","https://openalex.org/W3021397474","https://openalex.org/W3034969702","https://openalex.org/W3036320503","https://openalex.org/W3043840704","https://openalex.org/W3098468692","https://openalex.org/W3167329294","https://openalex.org/W3168640669"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2004831463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Video":[0,137],"search":[1,30],"has":[2],"become":[3],"the":[4,39,52,67,82,91,95,118,126,160],"main":[5],"routine":[6],"for":[7,125,134],"users":[8],"to":[9,13,79,116,163,167],"discover":[10],"videos":[11,53],"relevant":[12],"a":[14,24,34,70,73,86,149,174,201,211],"text":[15,46,75,109],"query":[16,71,83],"on":[17,45,154,173],"large":[18,202],"short-video":[19],"sharing":[20],"platforms.":[21],"During":[22],"training":[23,102],"query-video":[25],"bi-encoder":[26],"model":[27],"using":[28],"online":[29],"logs,\\textit":[31],"we":[32,112,178],"identify":[33],"modality":[35,60,65,93,127,191],"bias":[36,192],"phenomenon":[37],"that":[38,181],"video":[40,74,96,161,203],"encoder":[41,162],"almost":[42],"entirely":[43],"relies":[44],"matching,":[47],"neglecting":[48],"other":[49],"modalities":[50],"of":[51,88],"such":[54],"as":[55,81,94],"vision,":[56],"audio,":[57],"\\etc":[58],"This":[59],"imbalance":[61,128],"results":[62],"from":[63],"a)":[64],"gap:":[66],"relevance":[68],"between":[69],"and":[72,148,187,205,219],"is":[76,84,184],"much":[77],"easier":[78],"learn":[80],"also":[85,196],"piece":[87],"text,":[89],"with":[90,139],"same":[92],"text;":[97],"b)":[98],"data":[99],"bias:":[100],"most":[101],"samples":[103,147],"can":[104,158],"be":[105],"solved":[106],"solely":[107],"by":[108],"matching.":[110],"Here":[111],"share":[113],"our":[114,123,182,198],"practices":[115],"improve":[117],"first":[119],"retrieval":[120],"stage":[121],"including":[122],"solution":[124],"issue.":[129],"We":[130,194],"propose":[131],"\\modelname":[132],"(short":[133],"Modality":[135],"Balanced":[136],"Retrieval)":[138],"two":[140],"key":[141],"components:":[142],"manually":[143],"generated":[144],"modality-shuffled":[145],"(MS)":[146],"dynamic":[150],"margin":[151],"(DM)":[152],"based":[153],"visual":[155],"relevance.":[156],"They":[157],"encourage":[159],"pay":[164],"balanced":[165],"attentions":[166],"each":[168],"modality.":[169],"Through":[170],"extensive":[171],"experiments":[172],"real":[175],"world":[176],"dataset,":[177],"show":[179],"empirically":[180],"method":[183],"both":[185],"effective":[186],"efficient":[188],"in":[189,200,215],"solving":[190],"problem.":[193],"have":[195],"deployed":[197],"~\\modelname~":[199],"platform":[204],"observed":[206],"statistically":[207],"significant":[208],"boost":[209],"over":[210],"highly":[212],"optimized":[213],"baseline":[214],"an":[216],"A/B":[217],"test":[218],"manual":[220],"GSB":[221],"evaluations.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}