{"id":"https://openalex.org/W4390696496","doi":"https://doi.org/10.1007/s44267-023-00034-7","title":"Controllable augmentations for video representation learning","display_name":"Controllable augmentations for video representation learning","publication_year":2024,"publication_date":"2024-01-10","ids":{"openalex":"https://openalex.org/W4390696496","doi":"https://doi.org/10.1007/s44267-023-00034-7"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-023-00034-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-023-00034-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-023-00034-7.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-023-00034-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003750064","display_name":"Rui Qian","orcid":"https://orcid.org/0000-0002-0378-6438"},"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":"Rui Qian","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/A5059372830","display_name":"Weiyao Lin","orcid":"https://orcid.org/0000-0001-8307-7107"},"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":true,"raw_author_name":"Weiyao Lin","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/A5076753547","display_name":"John See","orcid":"https://orcid.org/0000-0003-3005-4109"},"institutions":[{"id":"https://openalex.org/I4210085930","display_name":"Heriot-Watt University Malaysia","ror":"https://ror.org/0059w0420","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210085930"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"John See","raw_affiliation_strings":["Heriot-Watt University, Putrajaya, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heriot-Watt University, Putrajaya, Malaysia","institution_ids":["https://openalex.org/I4210085930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100675450","display_name":"Dian Li","orcid":"https://orcid.org/0000-0002-7183-0090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dian Li","raw_affiliation_strings":["Tencent Platform and Content Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Platform and Content Group, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059372830"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.8289,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91753429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"2","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9944000244140625,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9930999875068665,"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":0.7895936965942383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6587249636650085},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5489365458488464},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.47707855701446533},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47509777545928955},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.45347148180007935},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43811601400375366},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.424140602350235},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4209935665130615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38766250014305115},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37056922912597656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32754141092300415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10880410671234131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895936965942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6587249636650085},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5489365458488464},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.47707855701446533},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47509777545928955},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.45347148180007935},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43811601400375366},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.424140602350235},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4209935665130615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38766250014305115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37056922912597656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32754141092300415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10880410671234131},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":1,"locations":[{"id":"doi:10.1007/s44267-023-00034-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-023-00034-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-023-00034-7.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s44267-023-00034-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-023-00034-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-023-00034-7.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6201002723","display_name":null,"funder_award_id":"U21B2013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G659896734","display_name":"\u9762\u5411\u65b0\u4e00\u4ee3\u76d1\u63a7\u89c6\u9891\u6570\u636e\u7684\u8bed\u4e49\u4fe1\u606f\u63d0\u53d6\u4e0e\u7f16\u7801\u7814\u7a76","funder_award_id":"61971277","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390696496.pdf"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1927052826","https://openalex.org/W2126579184","https://openalex.org/W2138621090","https://openalex.org/W2151834591","https://openalex.org/W2152790380","https://openalex.org/W2296073425","https://openalex.org/W2487442924","https://openalex.org/W2507009361","https://openalex.org/W2578257192","https://openalex.org/W2602856279","https://openalex.org/W2604738573","https://openalex.org/W2615413256","https://openalex.org/W2618799552","https://openalex.org/W2619082050","https://openalex.org/W2623660146","https://openalex.org/W2742901952","https://openalex.org/W2743563068","https://openalex.org/W2748434587","https://openalex.org/W2798991696","https://openalex.org/W2883429621","https://openalex.org/W2887997457","https://openalex.org/W2895243423","https://openalex.org/W2900712189","https://openalex.org/W2912269676","https://openalex.org/W2913954081","https://openalex.org/W2914304175","https://openalex.org/W2948242301","https://openalex.org/W2948859046","https://openalex.org/W2970235454","https://openalex.org/W2972780057","https://openalex.org/W2987283559","https://openalex.org/W2990408345","https://openalex.org/W2991133498","https://openalex.org/W2997302140","https://openalex.org/W3005680577","https://openalex.org/W3008930492","https://openalex.org/W3034381931","https://openalex.org/W3035060230","https://openalex.org/W3037195468","https://openalex.org/W3037618862","https://openalex.org/W3044365806","https://openalex.org/W3046614818","https://openalex.org/W3047425522","https://openalex.org/W3047740097","https://openalex.org/W3047826509","https://openalex.org/W3048918001","https://openalex.org/W3082302528","https://openalex.org/W3084872285","https://openalex.org/W3086333990","https://openalex.org/W3094454579","https://openalex.org/W3099634177","https://openalex.org/W3101999878","https://openalex.org/W3104591054","https://openalex.org/W3106528393","https://openalex.org/W3123599388","https://openalex.org/W3135858279","https://openalex.org/W3151935374","https://openalex.org/W3159663901","https://openalex.org/W3172726419","https://openalex.org/W3192881536","https://openalex.org/W3202428230","https://openalex.org/W3202721444","https://openalex.org/W3209483675","https://openalex.org/W3210733870","https://openalex.org/W3214803096","https://openalex.org/W4213304546","https://openalex.org/W4223528518","https://openalex.org/W4225674167","https://openalex.org/W4229971152","https://openalex.org/W4236965008","https://openalex.org/W4247924304","https://openalex.org/W4285428931","https://openalex.org/W4288099299","https://openalex.org/W4301409532","https://openalex.org/W4312107698","https://openalex.org/W4362597616","https://openalex.org/W4375809607","https://openalex.org/W6752051073","https://openalex.org/W6752558669","https://openalex.org/W6760478504","https://openalex.org/W6763442200","https://openalex.org/W6776359809","https://openalex.org/W6799876724"],"related_works":["https://openalex.org/W2417253731","https://openalex.org/W2350469024","https://openalex.org/W2491583298","https://openalex.org/W2327827625","https://openalex.org/W2395860100","https://openalex.org/W2036154621","https://openalex.org/W795077857","https://openalex.org/W2074513378","https://openalex.org/W2376416463","https://openalex.org/W3164304719"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"focuses":[3],"on":[4,103,171],"self-supervised":[5],"video":[6,173,179],"representation":[7],"learning.":[8],"Most":[9],"existing":[10],"approaches":[11],"follow":[12],"the":[13,33,48,56,126,139,152],"contrastive":[14],"learning":[15],"pipeline":[16],"to":[17,31,81,89,137,149],"construct":[18],"positive":[19,49],"and":[20,36,64,86,114,156,178,181],"negative":[21],"pairs":[22],"by":[23],"sampling":[24],"different":[25,52],"clips.":[26],"However,":[27],"this":[28],"formulation":[29,124],"tends":[30],"bias":[32],"static":[34],"background":[35],"has":[37],"difficulty":[38],"establishing":[39],"global":[40,87],"temporal":[41,61,100,146,161,185],"structures.":[42],"The":[43],"major":[44],"reason":[45],"is":[46,169],"that":[47,166],"pairs,":[50],"i.e.,":[51],"clips":[53,85],"sampled":[54],"from":[55,91],"same":[57],"video,":[58],"have":[59],"limited":[60],"receptive":[62],"fields,":[63],"usually":[65],"share":[66],"similar":[67],"backgrounds":[68],"but":[69],"differ":[70],"in":[71,175],"motions.":[72],"To":[73],"address":[74],"these":[75],"problems,":[76],"we":[77,110,143],"propose":[78],"a":[79,104],"framework":[80,168],"jointly":[82],"utilize":[83],"local":[84],"videos":[88],"learn":[90],"detailed":[92],"region-level":[93],"correspondence":[94],"as":[95,97],"well":[96],"general":[98],"long-term":[99],"relations.":[101],"Based":[102],"set":[105],"of":[106],"designed":[107],"controllable":[108],"augmentations,":[109],"implement":[111],"accurate":[112,184],"appearance":[113],"motion":[115],"pattern":[116],"alignment":[117],"through":[118],"soft":[119],"spatio-temporal":[120],"region":[121],"contrast.":[122],"Our":[123],"avoids":[125],"low-level":[127],"redundancy":[128],"shortcut":[129],"with":[130],"an":[131],"adversarial":[132],"mutual":[133],"information":[134],"minimization":[135],"objective":[136],"improve":[138],"generalization":[140],"ability.":[141],"Moreover,":[142],"introduce":[144],"local-global":[145],"order":[147],"dependency":[148],"further":[150],"bridge":[151],"gap":[153],"between":[154],"clip-level":[155],"video-level":[157],"representations":[158],"for":[159],"robust":[160],"modeling.":[162],"Extensive":[163],"experiments":[164],"demonstrate":[165],"our":[167],"superior":[170],"three":[172],"benchmarks":[174],"action":[176],"recognition":[177],"retrieval,":[180],"captures":[182],"more":[183],"dynamics.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}