{"id":"https://openalex.org/W3195146806","doi":"https://doi.org/10.1145/3474085.3475216","title":"Few-shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning","display_name":"Few-shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3195146806","doi":"https://doi.org/10.1145/3474085.3475216","mag":"3195146806"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475216","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.06647","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiahao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahao Wang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunhong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":null,"display_name":"Annan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Annan Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.971,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.77695912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9925000071525574,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9897000193595886,"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/discriminative-model","display_name":"Discriminative model","score":0.7608000040054321},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6869000196456909},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.651199996471405},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5776000022888184},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4713999927043915},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35839998722076416}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7608000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516000270843506},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6869000196456909},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.651199996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237999796867371},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5776000022888184},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475216","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.06647","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.06647","pdf_url":"https://arxiv.org/pdf/2108.06647","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:2108.06647","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.06647","pdf_url":"https://arxiv.org/pdf/2108.06647","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":[],"awards":[{"id":"https://openalex.org/G7665144123","display_name":null,"funder_award_id":"U20B2069","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1540330701","https://openalex.org/W2145227859","https://openalex.org/W2156761163","https://openalex.org/W2156798932","https://openalex.org/W2164364459","https://openalex.org/W2165728411","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2620429936","https://openalex.org/W2767119328","https://openalex.org/W2884585870","https://openalex.org/W2894608918","https://openalex.org/W2894873912","https://openalex.org/W2910021422","https://openalex.org/W2914868535","https://openalex.org/W2963495494","https://openalex.org/W2963524571","https://openalex.org/W2963811979","https://openalex.org/W2964105864","https://openalex.org/W2970662571","https://openalex.org/W2986056979","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3014195143","https://openalex.org/W3022778813","https://openalex.org/W3035180180","https://openalex.org/W3035374961","https://openalex.org/W3035413240","https://openalex.org/W3035524453","https://openalex.org/W3045564095","https://openalex.org/W3093143829","https://openalex.org/W3093194982","https://openalex.org/W3093352373","https://openalex.org/W3093455342","https://openalex.org/W3093471646","https://openalex.org/W3095374178","https://openalex.org/W3128401049","https://openalex.org/W3173271747"],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"action":[1,14,35,75,114,178],"recognition":[2,36,62,179],"is":[3,26,101],"attracting":[4],"increasing":[5],"attention":[6,98],"due":[7],"to":[8,39,72,164],"the":[9,20,32,70,78,90,124,134],"emerging":[10],"demand":[11],"of":[12,22,155],"specific":[13,171],"understanding":[15],"in":[16,57,80,159],"real-world":[17],"applications,":[18],"whereas":[19],"data":[21,83],"rare":[23],"fine-grained":[24,34,42,68,177],"categories":[25],"very":[27],"limited.":[28],"Therefore,":[29],"we":[30,127,169],"propose":[31],"few-shot":[33,61],"problem,":[37],"aiming":[38],"recognize":[40],"novel":[41],"actions":[43],"with":[44,84,107,133],"only":[45],"few":[46],"samples":[47],"given":[48],"for":[49,145],"each":[50,160],"class.":[51],"Although":[52],"progress":[53],"has":[54],"been":[55],"made":[56],"coarse-grained":[58],"actions,":[59],"existing":[60],"methods":[63],"encounter":[64],"two":[65,175],"issues":[66],"handling":[67],"actions:":[69],"inability":[71],"capture":[73],"subtle":[74,113],"details":[76,115],"and":[77],"inadequacy":[79],"learning":[81],"from":[82],"low":[85,146],"inter-class":[86,147],"variance.":[87],"To":[88,122],"tackle":[89],"first":[91],"issue,":[92,126],"a":[93],"human":[94],"vision":[95],"inspired":[96],"bidirectional":[97],"module":[99],"(BAM)":[100],"proposed.":[102],"Combining":[103],"top-down":[104],"task-driven":[105],"signals":[106],"bottom-up":[108],"salient":[109],"stimuli,":[110],"BAM":[111],"captures":[112],"by":[116],"accurately":[117],"highlighting":[118],"informative":[119],"spatio-temporal":[120],"regions.":[121],"address":[123],"second":[125],"introduce":[128],"contrastive":[129,157],"meta-learning":[130],"(CML).":[131],"Compared":[132],"widely":[135],"adopted":[136],"ProtoNet-based":[137],"method,":[138],"CML":[139],"generates":[140],"more":[141],"discriminative":[142],"video":[143],"representations":[144],"variance":[148],"data,":[149],"since":[150],"it":[151],"makes":[152],"full":[153],"use":[154],"potential":[156],"pairs":[158],"training":[161],"episode.":[162],"Furthermore,":[163],"fairly":[165],"compare":[166],"different":[167],"models,":[168],"establish":[170],"benchmark":[172],"protocols":[173],"on":[174],"large-scale":[176],"datasets.":[180],"Extensive":[181],"experiments":[182],"show":[183],"that":[184],"our":[185],"method":[186],"consistently":[187],"achieves":[188],"state-of-the-art":[189],"performance":[190],"across":[191],"evaluated":[192],"tasks.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2021-08-30T00:00:00"}