{"id":"https://openalex.org/W4372270168","doi":"https://doi.org/10.1109/icassp49357.2023.10095638","title":"One-Shot Action Detection via Attention Zooming In","display_name":"One-Shot Action Detection via Attention Zooming In","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270168","doi":"https://doi.org/10.1109/icassp49357.2023.10095638"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095638","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103130251","display_name":"He\u2010Yen Hsieh","orcid":"https://orcid.org/0000-0001-7657-6549"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"He-Yen Hsieh","raw_affiliation_strings":["Institute of Information Science,Academia Sinica,Taiwan","Academia Sinica, Institute of Information Science, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science,Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003705508","display_name":"Ding-Jie Chen","orcid":"https://orcid.org/0000-0001-7649-7824"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ding-Jie Chen","raw_affiliation_strings":["Institute of Information Science,Academia Sinica,Taiwan","Academia Sinica, Institute of Information Science, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science,Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089953732","display_name":"Cheng-Wei Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Wei Chang","raw_affiliation_strings":["Institute of Information Science,Academia Sinica,Taiwan","Academia Sinica, Institute of Information Science, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science,Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043386280","display_name":"Tyng-Luh Liu","orcid":"https://orcid.org/0000-0002-8366-5213"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tyng-Luh Liu","raw_affiliation_strings":["Institute of Information Science,Academia Sinica,Taiwan","Academia Sinica, Institute of Information Science, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science,Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103130251"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03686031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 2211 14905","issue":null,"first_page":"1","last_page":"5"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9984999895095825,"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":0.9976000189781189,"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":0.8170641660690308},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6689472198486328},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6422551870346069},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.608116626739502},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5940382480621338},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5226947069168091},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5153374075889587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5019612312316895},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.41621607542037964},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4146900475025177},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38829225301742554},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.363986611366272},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3319622278213501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170641660690308},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6689472198486328},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6422551870346069},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.608116626739502},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5940382480621338},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5226947069168091},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5153374075889587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019612312316895},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.41621607542037964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4146900475025177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38829225301742554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.363986611366272},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3319622278213501},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095638","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W2016053056","https://openalex.org/W2194775991","https://openalex.org/W2336403884","https://openalex.org/W2755876276","https://openalex.org/W2887928923","https://openalex.org/W2890502146","https://openalex.org/W2963091558","https://openalex.org/W2963247196","https://openalex.org/W2966098360","https://openalex.org/W2983918066","https://openalex.org/W2997706915","https://openalex.org/W2998525594","https://openalex.org/W3009353929","https://openalex.org/W3034623254","https://openalex.org/W3035590142","https://openalex.org/W3094502228","https://openalex.org/W3106690272","https://openalex.org/W3170310247","https://openalex.org/W4286899649","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6640295108","https://openalex.org/W6739901393","https://openalex.org/W6784333009","https://openalex.org/W6802611020","https://openalex.org/W6983570979"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W4294892107","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Hinted":[0],"by":[1,48],"a":[2,31],"modest":[3],"support":[4,54,69],"set,":[5],"few-shot":[6],"action":[7,14,35,107,112],"detection":[8,113],"(FSAD)":[9],"aims":[10],"at":[11],"localizing":[12],"the":[13,38,44,53,68,73,79,85,120,127],"instances":[15],"of":[16,33],"unseen":[17],"classes":[18],"within":[19],"an":[20],"untrimmed":[21],"query":[22,39],"video.":[23],"Existing":[24],"FSAD":[25],"techniques":[26],"mostly":[27],"rely":[28],"on":[29,78,119],"generating":[30,72,99],"set":[32],"class-agnostic":[34],"proposals":[36,108],"from":[37],"video":[40],"and":[41,83,92,122],"then":[42],"finding":[43],"most":[45],"plausible":[46],"ones":[47],"assessing":[49],"their":[50],"correlation":[51],"to":[52,66,90],"set.":[55],"Such":[56],"two-stage":[57],"approaches":[58],"are":[59],"feasible":[60],"but":[61],"not":[62],"efficient,":[63],"largely":[64],"due":[65],"neglecting":[67],"information":[70],"in":[71,88,134],"proposals.":[74,100],"This":[75],"work":[76],"focuses":[77],"one-shot":[80,111],"image":[81],"scenario":[82],"introduces":[84],"attention":[86],"zooming":[87],"strategy":[89],"effectively":[91],"progressively":[93],"carry":[94],"out":[95],"support-query":[96],"cross-attention":[97],"while":[98],"The":[101],"resulting":[102],"one-stage":[103],"model":[104],"yields":[105],"high-quality":[106],"for":[109],"boosting":[110],"(OSAD)":[114],"performance.":[115],"Our":[116],"extensive":[117],"experiments":[118],"ActivityNet-1.3":[121],"THUMOS-14":[123],"datasets":[124],"demonstrate":[125],"that":[126],"proposed":[128],"framework":[129],"can":[130],"achieve":[131],"state-of-the-art":[132],"performance":[133],"tack-ling":[135],"challenging":[136],"image-based":[137],"OSAD":[138],"tasks.":[139]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}