{"id":"https://openalex.org/W4387968456","doi":"https://doi.org/10.1145/3581783.3611756","title":"Mask to Reconstruct: Cooperative Semantics Completion for Video-text Retrieval","display_name":"Mask to Reconstruct: Cooperative Semantics Completion for Video-text Retrieval","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968456","doi":"https://doi.org/10.1145/3581783.3611756"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/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":true,"raw_author_name":"Han Fang","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4379-2971","affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047206667","display_name":"Zhifei Yang","orcid":"https://orcid.org/0000-0003-0054-8896"},"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":"Zhifei Yang","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0054-8896","affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China","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&amp;AI Technology Company, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8421-7167","affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China","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&amp;AI Technology Company, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8114-103X","affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101722779","display_name":"Zhongjiang He","orcid":"https://orcid.org/0009-0000-1835-9271"},"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&amp;AI Technology Company, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-1835-9271","affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063142903","display_name":"Hao Sun","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":"Hao Sun","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-7917-1628","affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","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&amp;AI Technology Company, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7003-287X","affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&amp;AI Technology Company, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5020428892"],"corresponding_institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"],"apc_list":null,"apc_paid":null,"fwci":0.3532,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60332542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3847","last_page":"3856"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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":0.9980999827384949,"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":0.8496731519699097},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7332882881164551},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6550906300544739},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6394869685173035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5226135849952698},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5111637711524963},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48371392488479614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4615578353404999},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4375460743904114},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3972378671169281}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496731519699097},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7332882881164551},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6550906300544739},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6394869685173035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5226135849952698},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5111637711524963},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48371392488479614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4615578353404999},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4375460743904114},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3972378671169281},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2425121537","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2897439619","https://openalex.org/W2914699769","https://openalex.org/W2963017553","https://openalex.org/W2963916161","https://openalex.org/W2984008963","https://openalex.org/W3035356601","https://openalex.org/W3043840704","https://openalex.org/W3145807616","https://openalex.org/W3153005511","https://openalex.org/W3168640669","https://openalex.org/W3174873881","https://openalex.org/W3207042189","https://openalex.org/W3212610063","https://openalex.org/W4214612132","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312655527","https://openalex.org/W4313156423","https://openalex.org/W6601676141"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"Recently,":[0],"masked":[1,37,61,82,93],"video":[2,67,141],"modeling":[3],"has":[4],"been":[5],"widely":[6],"explored":[7],"and":[8,28,72,100,146,165],"improved":[9],"the":[10,30,36,43,92,96,106,119],"model's":[11],"understanding":[12],"ability":[13],"of":[14,121],"visual":[15,98],"regions":[16,99,131],"at":[17,112],"a":[18,113],"local":[19],"level.":[20,115],"However,":[21],"existing":[22],"methods":[23],"usually":[24],"adopt":[25],"random":[26],"masking":[27,68],"follow":[29],"same":[31],"reconstruction":[32,122],"paradigm":[33],"to":[34,69,80,126,129,139],"complete":[35],"regions,":[38],"which":[39,104],"do":[40],"not":[41],"leverage":[42],"correlations":[44],"between":[45],"cross-modal":[46],"content.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,75,117,136],"present":[52],"MAsk":[53],"for":[54],"Semantics":[55,78],"COmpleTion":[56],"(MASCOT)":[57],"based":[58],"on":[59,156],"semantic-based":[60],"modeling.":[62],"Specifically,":[63],"after":[64],"applying":[65],"attention-based":[66],"generate":[70],"high-informed":[71],"low-informed":[73,133],"masks,":[74],"propose":[76],"Informed":[77],"Completion":[79],"recover":[81],"semantics":[83],"information.":[84],"The":[85],"recovery":[86],"mechanism":[87],"is":[88],"achieved":[89],"by":[90],"aligning":[91],"content":[94],"with":[95,132],"unmasked":[97],"corresponding":[101],"textual":[102],"context,":[103],"makes":[105],"model":[107],"capture":[108],"more":[109,148],"text-related":[110],"details":[111],"patch":[114],"Additionally,":[116],"shift":[118],"emphasis":[120],"from":[123],"irrelevant":[124],"backgrounds":[125],"discriminative":[127],"parts":[128],"ignore":[130],"masks.":[134],"Furthermore,":[135],"design":[137],"co-learning":[138],"incorporate":[140],"cues":[142],"under":[143],"different":[144],"masks":[145],"learn":[147],"aligned":[149],"representation.":[150],"Our":[151],"MASCOT":[152],"performs":[153],"state-of-the-art":[154],"performance":[155],"four":[157],"text-video":[158],"retrieval":[159],"benchmarks,":[160],"including":[161],"MSR-VTT,":[162],"LSMDC,":[163],"ActivityNet,":[164],"DiDeMo.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
