{"id":"https://openalex.org/W4312347893","doi":"https://doi.org/10.1109/icpr56361.2022.9956701","title":"Cosine Similarity based Few-Shot Video Classifier with Attention-based Aggregation","display_name":"Cosine Similarity based Few-Shot Video Classifier with Attention-based Aggregation","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312347893","doi":"https://doi.org/10.1109/icpr56361.2022.9956701"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956701","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5046274165","display_name":"Biplob Debnath","orcid":"https://orcid.org/0009-0006-6932-0311"},"institutions":[{"id":"https://openalex.org/I2800295664","display_name":"RCA (United States)","ror":"https://ror.org/010k8n340","country_code":"US","type":"company","lineage":["https://openalex.org/I2800295664"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Biplob Debnath","raw_affiliation_strings":["NEC Laboratories America,Princeton,New Jersey,USA","NEC Laboratories America, Princeton, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America,Princeton,New Jersey,USA","institution_ids":["https://openalex.org/I2800295664","https://openalex.org/I20089843"]},{"raw_affiliation_string":"NEC Laboratories America, Princeton, New Jersey, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000883652","display_name":"Oliver Po","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I2800295664","display_name":"RCA (United States)","ror":"https://ror.org/010k8n340","country_code":"US","type":"company","lineage":["https://openalex.org/I2800295664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oliver Po","raw_affiliation_strings":["NEC Laboratories America,Princeton,New Jersey,USA","NEC Laboratories America, Princeton, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America,Princeton,New Jersey,USA","institution_ids":["https://openalex.org/I2800295664","https://openalex.org/I20089843"]},{"raw_affiliation_string":"NEC Laboratories America, Princeton, New Jersey, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112619825","display_name":"Farhan Asif Chowdhury","orcid":null},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farhan Asif Chowdhury","raw_affiliation_strings":["The University of New Mexico,Albuquerque,NM,USA","The University of New Mexico, Albuquerque, NM, USA"],"affiliations":[{"raw_affiliation_string":"The University of New Mexico,Albuquerque,NM,USA","institution_ids":["https://openalex.org/I169521973"]},{"raw_affiliation_string":"The University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042424184","display_name":"Srimat Chakradhar","orcid":"https://orcid.org/0000-0003-3530-3901"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I2800295664","display_name":"RCA (United States)","ror":"https://ror.org/010k8n340","country_code":"US","type":"company","lineage":["https://openalex.org/I2800295664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srimat Chakradhar","raw_affiliation_strings":["NEC Laboratories America,Princeton,New Jersey,USA","NEC Laboratories America, Princeton, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America,Princeton,New Jersey,USA","institution_ids":["https://openalex.org/I2800295664","https://openalex.org/I20089843"]},{"raw_affiliation_string":"NEC Laboratories America, Princeton, New Jersey, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046274165"],"corresponding_institution_ids":["https://openalex.org/I20089843","https://openalex.org/I2800295664"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43561956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"1273","last_page":"1279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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":0.998199999332428,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9876999855041504,"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":0.9754999876022339,"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":0.7731695175170898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7539643049240112},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6350465416908264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5979490876197815},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5930429697036743},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5736123919487},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5639446377754211},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4941263496875763},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.467974454164505},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4552430808544159},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43974006175994873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731695175170898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7539643049240112},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6350465416908264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5979490876197815},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5930429697036743},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5736123919487},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5639446377754211},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4941263496875763},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.467974454164505},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4552430808544159},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43974006175994873},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956701","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W787785461","https://openalex.org/W1522734439","https://openalex.org/W1983364832","https://openalex.org/W2051224630","https://openalex.org/W2126579184","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2292288263","https://openalex.org/W2594833348","https://openalex.org/W2611596598","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2796346823","https://openalex.org/W2798836702","https://openalex.org/W2894873912","https://openalex.org/W2896457183","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2963741406","https://openalex.org/W2964105864","https://openalex.org/W2990503944","https://openalex.org/W3035374961","https://openalex.org/W3094502228","https://openalex.org/W3095374178","https://openalex.org/W3096805028","https://openalex.org/W3113370935","https://openalex.org/W3124568760","https://openalex.org/W3126721948","https://openalex.org/W3173271747","https://openalex.org/W4214516465","https://openalex.org/W4214612132","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6600983433","https://openalex.org/W6622789128","https://openalex.org/W6631456553","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6756911974","https://openalex.org/W6758126075","https://openalex.org/W6766978945","https://openalex.org/W6787254463","https://openalex.org/W6789158709","https://openalex.org/W6790307280","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W2360571912","https://openalex.org/W2619127353","https://openalex.org/W2786094008","https://openalex.org/W3131501806","https://openalex.org/W2799683370","https://openalex.org/W2807745940"],"abstract_inverted_index":{"Meta":[0],"learning":[1],"algorithms":[2],"for":[3,75],"few-shot":[4,28,49,244,279],"video":[5,29,50,66,91,100,143,175,207,251,258,280],"recognition":[6,30],"use":[7,35,154,248],"complex,":[8],"episodic":[9,155],"training":[10,156,204],"but":[11,37],"they":[12],"often":[13],"fail":[14],"to":[15,137,157,237,254,325],"learn":[16,63,158],"effective":[17],"feature":[18,67,73,92,101,109,161,170,176,182,208,252,321],"representations.":[19],"In":[20,58],"contrast,":[21],"we":[22,62,88,151,178,247],"propose":[23],"a":[24,64,72,79,90,114,123,139,173,186,256],"new":[25,48,115,187,257],"and":[26,272,286,303],"simpler":[27],"method":[31,297],"that":[32,70,126,167,190,211,235,276,295],"does":[33],"not":[34,153],"meta-learning,":[36],"its":[38],"performance":[39],"compares":[40],"well":[41],"with":[42],"the":[43,59,86,95,133,159,193,198,206,212,221,224,230,238,243,249,262,283,288],"best":[44,289],"meta-learning":[45],"proposals.":[46],"Our":[47,98],"classification":[51],"pipeline":[52],"consists":[53,105],"of":[54,106,132,141,200,205,233],"two":[55],"distinct":[56],"phases.":[57],"pre-training":[60],"phase,":[61,246],"good":[65],"extraction":[68,110],"network":[69,111],"generates":[71],"vector":[74,93],"each":[76],"video.":[77],"After":[78],"sparse":[80],"sampling":[81],"strategy":[82],"selects":[83],"frames":[84],"from":[85,94,266],"video,":[87,222],"generate":[89],"sampled":[96,201],"frames.":[97,202],"proposed":[99,213,278],"extractor":[102,209,253],"network,":[103],"which":[104,318],"an":[107],"image":[108,160,320],"followed":[112],"by":[113,121,184,260],"transformer":[116],"encoder,":[117],"is":[118,323],"trained":[119],"end-to-end":[120],"including":[122],"classifier":[124,259,281],"head":[125],"uses":[127],"cosine":[128,225],"similarity":[129,226],"layer":[130,136,227],"instead":[131],"traditional":[134],"linear":[135],"classify":[138],"corpus":[140],"labeled":[142],"examples.":[144],"Unlike":[145],"prior":[146,165,316],"work":[147,166],"in":[148,197,220,242],"meta":[149],"learning,":[150],"do":[152,326],"vector.":[162],"Also,":[163],"unlike":[164],"averages":[168,319],"frame-level":[169,181],"vectors":[171,183],"into":[172],"single":[174],"vector,":[177],"combine":[179],"individual":[180],"using":[185,261],"Transformer":[188,214],"encoder":[189,215],"explicitly":[191,228],"captures":[192,216],"key,":[194],"temporal":[195,218],"properties":[196,219],"sequence":[199],"End-to-end":[203],"ensures":[210],"important":[217],"while":[223,315],"reduces":[229],"intra-class":[231],"variance":[232],"videos":[234],"belong":[236],"same":[239],"class.":[240],"Next,":[241],"adaptation":[245],"learned":[250],"train":[255],"few":[263],"available":[264],"examples":[265],"novel":[267],"classes.":[268],"Results":[269],"on":[270],"SSV2-100":[271],"Kinetics-100":[273],"benchmarks":[274],"show":[275,294],"our":[277,296],"outperforms":[282],"meta-learning-based":[284],"methods":[285],"achieves":[287],"state-of-the-art":[290],"accuracy.":[291],"We":[292],"also":[293],"can":[298],"easily":[299],"discern":[300],"between":[301],"actions":[302],"their":[304],"inverse":[305],"(for":[306],"example,":[307],"picking":[308],"something":[309,313],"up":[310],"vs.":[311],"putting":[312],"down),":[314],"art,":[317],"vectors,":[322],"unable":[324],"so.":[327]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}