{"id":"https://openalex.org/W3033049303","doi":"https://doi.org/10.1145/3372278.3390687","title":"Google Helps YouTube: Learning Few-Shot Video Classification from Historic Tasks and Cross-Domain Sample Transfer","display_name":"Google Helps YouTube: Learning Few-Shot Video Classification from Historic Tasks and Cross-Domain Sample Transfer","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033049303","doi":"https://doi.org/10.1145/3372278.3390687","mag":"3033049303"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","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/A5102328626","display_name":"Xinzhe Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinzhe Zhou","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028877572","display_name":"Yadong Mu","orcid":"https://orcid.org/0000-0001-7815-3750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Mu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102328626"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48060765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"172","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9972000122070312,"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":0.8192049264907837},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6995092630386353},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.6013928651809692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5724870562553406},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5691621899604797},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4833531081676483},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.43678274750709534},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.41329073905944824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40058860182762146},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24360448122024536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192049264907837},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6995092630386353},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6013928651809692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724870562553406},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5691621899604797},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4833531081676483},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.43678274750709534},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.41329073905944824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40058860182762146},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24360448122024536},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3372278.3390687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W99485931","https://openalex.org/W1522734439","https://openalex.org/W1923404803","https://openalex.org/W1927052826","https://openalex.org/W2020163092","https://openalex.org/W2105101328","https://openalex.org/W2115733720","https://openalex.org/W2119821739","https://openalex.org/W2133774033","https://openalex.org/W2140804329","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2401823607","https://openalex.org/W2507009361","https://openalex.org/W2559542432","https://openalex.org/W2561272927","https://openalex.org/W2583010282","https://openalex.org/W2601450892","https://openalex.org/W2619947201","https://openalex.org/W2742093937","https://openalex.org/W2753160622","https://openalex.org/W2761659801","https://openalex.org/W2787501667","https://openalex.org/W2883441015","https://openalex.org/W2894873912","https://openalex.org/W2950527759","https://openalex.org/W2951008357","https://openalex.org/W2951775809","https://openalex.org/W2952186347","https://openalex.org/W2953044442","https://openalex.org/W2963078860","https://openalex.org/W2963341924","https://openalex.org/W2963448850","https://openalex.org/W2963524571","https://openalex.org/W2963716836","https://openalex.org/W2963775850","https://openalex.org/W3091905774","https://openalex.org/W3093116395","https://openalex.org/W4239510810","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W2074502265","https://openalex.org/W2361861616","https://openalex.org/W4214877189","https://openalex.org/W2392004567","https://openalex.org/W2046296964","https://openalex.org/W2263699433","https://openalex.org/W2773965352","https://openalex.org/W2377979023","https://openalex.org/W2576964996"],"abstract_inverted_index":{"The":[0,16,55],"fact":[1],"that":[2,84,91],"video":[3,14,50,147,162,170],"annotation":[4],"is":[5,22,58,141],"labor-intensive":[6],"inspires":[7],"recent":[8],"research":[9],"to":[10,23,39,109,125,143],"endeavor":[11],"on":[12,167],"few-shot":[13,31,49],"classification.":[15],"core":[17],"motivation":[18],"of":[19,159,180],"our":[20,181],"work":[21,75],"mitigate":[24],"the":[25,71,86,100,111,129,151,157,160,178],"supervision":[26],"scarcity":[27],"issue":[28],"in":[29,70,99,150],"this":[30],"setting":[32],"via":[33],"cross-domain":[34],"meta-learning.":[35],"Particularly,":[36],"we":[37],"aim":[38],"harness":[40],"large-scale":[41,169],"richly-annotated":[42],"image":[43],"data":[44,57,89,112],"(i.e.,":[45,52],"source":[46,56,88,116,130,137],"domain)":[47],"for":[48,96],"classification":[51,148],"target":[53,72,101,118,152],"domain).":[54],"heterogeneous":[59],"(image":[60],"v.s.":[61],"video)":[62],"and":[63,127,173],"has":[64,104],"noisy":[65,87,136],"labels,":[66],"not":[67],"directly":[68],"usable":[69],"domain.":[73,102],"This":[74],"proposes":[76],"meta-learning":[77],"input-transformer":[78],"(MLIT),":[79],"a":[80],"novel":[81],"deep":[82],"network":[83],"tames":[85],"such":[90],"they":[92],"are":[93],"more":[94],"amenable":[95],"being":[97],"used":[98],"It":[103],"two":[105,168],"key":[106],"traits.":[107],"First,":[108],"bridge":[110],"distribution":[113],"gap":[114],"between":[115],"/":[117],"domains,":[119],"MLIT":[120,140],"includes":[121],"learnable":[122],"neural":[123],"layers":[124],"reweigh":[126],"transform":[128],"data,":[131],"effectively":[132],"suppressing":[133],"corrupted":[134],"or":[135],"data.":[138],"Secondly,":[139],"designed":[142],"learn":[144],"from":[145],"historic":[146],"tasks":[149],"domain,":[153],"which":[154],"significantly":[155],"elevates":[156],"accuracy":[158],"unseen":[161],"category.":[163],"Comprehensive":[164],"empirical":[165],"evaluations":[166],"datasets,":[171],"ActivityNet":[172],"Kinetics-400,":[174],"have":[175],"strongly":[176],"shown":[177],"superiority":[179],"proposed":[182],"method.":[183]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}