{"id":"https://openalex.org/W4285428931","doi":"https://doi.org/10.1145/3503161.3547783","title":"Dual Contrastive Learning for Spatio-temporal Representation","display_name":"Dual Contrastive Learning for Spatio-temporal Representation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4285428931","doi":"https://doi.org/10.1145/3503161.3547783"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547783","pdf_url":null,"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":null,"license_id":null,"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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.05340","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013238521","display_name":"Shuangrui Ding","orcid":"https://orcid.org/0000-0001-7033-774X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangrui Ding","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003750064","display_name":"Rui Qian","orcid":"https://orcid.org/0000-0002-0378-6438"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rui Qian","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Xiong","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5649","last_page":"5658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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":0.9959999918937683,"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":0.6956702470779419},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6900665163993835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6854187250137329},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6155158281326294},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6053129434585571},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5801023244857788},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47524499893188477},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4623014032840729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4591073989868164},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4576011002063751},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4186950623989105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956702470779419},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6900665163993835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6854187250137329},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6155158281326294},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6053129434585571},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5801023244857788},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47524499893188477},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4623014032840729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4591073989868164},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4576011002063751},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4186950623989105},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"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":2,"locations":[{"id":"doi:10.1145/3503161.3547783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547783","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2207.05340","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.05340","pdf_url":"https://arxiv.org/pdf/2207.05340","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2207.05340","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.05340","pdf_url":"https://arxiv.org/pdf/2207.05340","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W343636949","https://openalex.org/W2126579184","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2422305492","https://openalex.org/W2487442924","https://openalex.org/W2511671220","https://openalex.org/W2578257192","https://openalex.org/W2615413256","https://openalex.org/W2785325870","https://openalex.org/W2798711578","https://openalex.org/W2798991696","https://openalex.org/W2883429621","https://openalex.org/W2895243423","https://openalex.org/W2900712189","https://openalex.org/W2926645869","https://openalex.org/W2948242301","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963814513","https://openalex.org/W2963826423","https://openalex.org/W2964700958","https://openalex.org/W2976252039","https://openalex.org/W2990408345","https://openalex.org/W2991133498","https://openalex.org/W2997138816","https://openalex.org/W2997907976","https://openalex.org/W3005680577","https://openalex.org/W3010874390","https://openalex.org/W3034215340","https://openalex.org/W3034381931","https://openalex.org/W3034748927","https://openalex.org/W3034781633","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3037618862","https://openalex.org/W3046614818","https://openalex.org/W3047425522","https://openalex.org/W3082302528","https://openalex.org/W3094454579","https://openalex.org/W3097877556","https://openalex.org/W3101999878","https://openalex.org/W3104591054","https://openalex.org/W3106939553","https://openalex.org/W3108655343","https://openalex.org/W3110190397","https://openalex.org/W3110306138","https://openalex.org/W3115964123","https://openalex.org/W3118817977","https://openalex.org/W3145385912","https://openalex.org/W3149106692","https://openalex.org/W3158714121","https://openalex.org/W3162768636","https://openalex.org/W3168531333","https://openalex.org/W3170837227","https://openalex.org/W3173623687","https://openalex.org/W3176780013","https://openalex.org/W3180846417","https://openalex.org/W3181598125","https://openalex.org/W3192881536","https://openalex.org/W3197113684","https://openalex.org/W3204261852","https://openalex.org/W3208431284","https://openalex.org/W4214507759","https://openalex.org/W4214514833","https://openalex.org/W4214642259","https://openalex.org/W4237044863","https://openalex.org/W4286951705","https://openalex.org/W4287100985","https://openalex.org/W4287668581","https://openalex.org/W4297801846","https://openalex.org/W4297808394","https://openalex.org/W6600376255"],"related_works":["https://openalex.org/W3103825105","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550","https://openalex.org/W2004102934","https://openalex.org/W4366455350","https://openalex.org/W2329266651","https://openalex.org/W4321844193","https://openalex.org/W2099777870","https://openalex.org/W2044090405"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1],"has":[2],"shown":[3],"promising":[4],"potential":[5],"in":[6],"self-supervised":[7],"spatio-temporal":[8,183,193],"representation":[9],"learning.":[10],"Most":[11],"works":[12],"naively":[13],"sample":[14],"different":[15],"clips":[16,60],"to":[17,52,84,130,168],"construct":[18],"positive":[19,78],"and":[20,50,119,134,146,171,195,204],"negative":[21],"pairs.":[22],"However,":[23],"we":[24,106],"observe":[25],"that":[26,189],"this":[27,95,97,141],"formulation":[28],"inclines":[29],"the":[30,33,43,55,59,63,82,85,90,108,123,131,135,143,147,154,161],"model":[31,83],"towards":[32],"background":[34,87],"scene":[35,44,118,145],"bias.":[36],"The":[37],"underlying":[38],"reasons":[39],"are":[40,127,150],"twofold.":[41],"First,":[42],"difference":[45],"is":[46],"usually":[47],"more":[48],"noticeable":[49],"easier":[51],"discriminate":[53],"than":[54,89],"motion":[56,91,149],"difference.":[57],"Second,":[58],"sampled":[61],"from":[62],"same":[64],"video":[65,111],"often":[66],"share":[67],"similar":[68],"backgrounds":[69],"but":[70],"have":[71],"distinct":[72],"motions.":[73],"Simply":[74],"regarding":[75],"them":[76],"as":[77,178],"pairs":[79],"will":[80],"draw":[81],"static":[86,117,132,144],"rather":[88],"pattern.":[92],"To":[93],"tackle":[94],"challenge,":[96],"paper":[98],"presents":[99],"a":[100],"novel":[101],"dual":[102],"contrastive":[103],"formulation.":[104],"Concretely,":[105],"decouple":[107],"input":[109],"RGB":[110,125,156],"sequence":[112],"into":[113,153],"two":[114],"complementary":[115],"modes,":[116],"dynamic":[120,137,148],"motion.":[121],"Then,":[122],"original":[124],"features":[126,133],"pulled":[128],"closer":[129],"aligned":[136],"features,":[138],"respectively.":[139],"In":[140],"way,":[142],"simultaneously":[151],"encoded":[152],"compact":[155],"representation.":[157],"We":[158,174],"further":[159],"conduct":[160],"feature":[162],"space":[163],"decoupling":[164],"via":[165],"activation":[166],"maps":[167],"distill":[169],"static-":[170],"dynamic-related":[172],"features.":[173],"term":[175],"our":[176],"method":[177],"\\textbf{D}ual":[179],"\\textbf{C}ontrastive":[180],"\\textbf{L}earning":[181],"for":[182],"\\textbf{R}epresentation":[184],"(DCLR).":[185],"Extensive":[186],"experiments":[187],"demonstrate":[188],"DCLR":[190],"learns":[191],"effective":[192],"representations":[194],"obtains":[196],"state-of-the-art":[197],"or":[198],"comparable":[199],"performance":[200],"on":[201],"UCF-101,":[202],"HMDB-51,":[203],"Diving-48":[205],"datasets.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}