{"id":"https://openalex.org/W4304083971","doi":"https://doi.org/10.1145/3503161.3547888","title":"MaMiCo: Macro-to-Micro Semantic Correspondence for Self-supervised Video Representation Learning","display_name":"MaMiCo: Macro-to-Micro Semantic Correspondence for Self-supervised Video Representation Learning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304083971","doi":"https://doi.org/10.1145/3503161.3547888"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547888","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547888","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547888","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547888","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043412497","display_name":"Bo Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Fang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015819673","display_name":"Wenhao Wu","orcid":"https://orcid.org/0000-0002-8511-743X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Wenhao Wu","raw_affiliation_strings":["The University of Sydney &amp; Baidu Inc., Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney &amp; Baidu Inc., Sydney, NSW, Australia","institution_ids":["https://openalex.org/I98301712","https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353381","display_name":"Chang Liu","orcid":"https://orcid.org/0009-0001-7457-0204"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018276259","display_name":"Dongliang He","orcid":"https://orcid.org/0000-0002-1129-8610"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongliang He","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015344604","display_name":"Weipinng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weipinng Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043412497"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":0.3598,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67303579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1348","last_page":"1357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965999722480774,"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":0.796582818031311},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.6996806263923645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6091204881668091},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5779790282249451},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5701791644096375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3392200469970703},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07875725626945496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796582818031311},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.6996806263923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6091204881668091},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5779790282249451},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5701791644096375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3392200469970703},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07875725626945496},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547888","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547888","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547888","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3547888","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547888","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547888","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304083971.pdf","grobid_xml":"https://content.openalex.org/works/W4304083971.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W569478347","https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2336403884","https://openalex.org/W2425121537","https://openalex.org/W2487442924","https://openalex.org/W2507009361","https://openalex.org/W2550462002","https://openalex.org/W2625366777","https://openalex.org/W2798991696","https://openalex.org/W2799087757","https://openalex.org/W2883429621","https://openalex.org/W2883725317","https://openalex.org/W2948242301","https://openalex.org/W2962934715","https://openalex.org/W2963155035","https://openalex.org/W2963420272","https://openalex.org/W2963631366","https://openalex.org/W2963814513","https://openalex.org/W2964037671","https://openalex.org/W2979579363","https://openalex.org/W2986451890","https://openalex.org/W2987741655","https://openalex.org/W2990138404","https://openalex.org/W2990152177","https://openalex.org/W2997907976","https://openalex.org/W3010010212","https://openalex.org/W3010874390","https://openalex.org/W3034215340","https://openalex.org/W3034381931","https://openalex.org/W3034623254","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3046614818","https://openalex.org/W3047425522","https://openalex.org/W3047573812","https://openalex.org/W3086333990","https://openalex.org/W3094454579","https://openalex.org/W3101999878","https://openalex.org/W3103897295","https://openalex.org/W3104591054","https://openalex.org/W3108655343","https://openalex.org/W3110190397","https://openalex.org/W3110306138","https://openalex.org/W3115964123","https://openalex.org/W3145385912","https://openalex.org/W3168822201","https://openalex.org/W3170837227","https://openalex.org/W3171007011","https://openalex.org/W3172615411","https://openalex.org/W3173623687","https://openalex.org/W3174568846","https://openalex.org/W3176780013","https://openalex.org/W3181598125","https://openalex.org/W3202721444","https://openalex.org/W3204261852","https://openalex.org/W3207340843","https://openalex.org/W3208431284","https://openalex.org/W3208474254","https://openalex.org/W3209483675","https://openalex.org/W3210733870","https://openalex.org/W4214747681","https://openalex.org/W4225463624","https://openalex.org/W4226248135","https://openalex.org/W4287600707","https://openalex.org/W6600403135"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2912956128","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W2611614995","https://openalex.org/W3046775127","https://openalex.org/W4205958290","https://openalex.org/W3107474891"],"abstract_inverted_index":{"Contrastive":[0],"self-supervised":[1,50],"learning":[2,55],"(CSL)":[3],"has":[4],"remarkably":[5],"promoted":[6],"the":[7,83],"progress":[8],"of":[9,72],"visual":[10],"representation":[11],"learning.":[12],"However,":[13],"existing":[14],"video":[15,143,159],"CSL":[16,115],"methods":[17],"mainly":[18],"focus":[19],"on":[20,76,148],"clip-level":[21],"temporal":[22,26,88,102],"semantic":[23,29,93,130],"consistency.":[24],"The":[25],"and":[27,37,74,96,145,158],"spatial":[28,105],"correspondence":[30,89],"across":[31],"different":[32],"granularities,":[33],"i.e.,":[34],"video,":[35],"clip,":[36],"frame":[38],"levels,":[39],"is":[40],"typically":[41],"overlooked.":[42],"To":[43],"tackle":[44],"this":[45],"issue,":[46],"we":[47],"propose":[48],"a":[49,62,68,77],"Macro-to-Micro":[51],"Semantic":[52],"Correspondence":[53],"(MaMiCo)":[54],"framework,":[56],"pursuing":[57],"fine-grained":[58],"spatiotemporal":[59],"representations":[60,95,144],"from":[61],"macro-to-micro":[63],"perspective.":[64],"Specifically,":[65],"MaMiCo":[66,139],"constructs":[67],"multiple":[69],"branch":[70],"architecture":[71],"T-MaMiCo":[73,85],"S-MaMiCo":[75,107],"temporally-nested":[78],"clip":[79],"pyramid":[80],"(video-to-frame).":[81],"On":[82],"pyramid,":[84],"aims":[86],"at":[87],"by":[90,133],"simultaneously":[91],"assimilating":[92],"invariance":[94],"retaining":[97],"appearance":[98],"dynamics":[99],"in":[100],"long":[101],"ranges.":[103],"For":[104],"correspondence,":[106],"perceives":[108],"subtle":[109],"motion":[110],"cues":[111],"via":[112],"ameliorating":[113],"dense":[114,125],"for":[116,123],"videos":[117],"where":[118],"stationary":[119],"clips":[120],"are":[121],"applied":[122],"stably":[124],"contrasting":[126],"reference":[127],"to":[128],"alleviate":[129],"inconsistency":[131],"caused":[132],"''mismatching''.":[134],"Extensive":[135],"experiments":[136],"justify":[137],"that":[138],"learns":[140],"rich":[141],"general":[142],"works":[146],"well":[147],"various":[149],"downstream":[150],"tasks,":[151],"e.g.,":[152],"(fine-grained)":[153],"action":[154,156],"recognition,":[155],"localization,":[157],"retrieval.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
