{"id":"https://openalex.org/W4375869002","doi":"https://doi.org/10.1109/icassp49357.2023.10097186","title":"One-Shot Medical Action Recognition With A Cross-Attention Mechanism And Dynamic Time Warping","display_name":"One-Shot Medical Action Recognition With A Cross-Attention Mechanism And Dynamic Time Warping","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869002","doi":"https://doi.org/10.1109/icassp49357.2023.10097186"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097186","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":"conference-paper","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/A5076795285","display_name":"Leiyu Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leiyu Xie","raw_affiliation_strings":["Newcastle University,Intelligent Sensing and Communications Research Group,UK","Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University,Intelligent Sensing and Communications Research Group,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002976962","display_name":"Yuxing Yang","orcid":"https://orcid.org/0000-0003-4415-8080"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuxing Yang","raw_affiliation_strings":["Newcastle University,Intelligent Sensing and Communications Research Group,UK","Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University,Intelligent Sensing and Communications Research Group,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012939991","display_name":"Zeyu Fu","orcid":"https://orcid.org/0000-0002-2076-7597"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zeyu Fu","raw_affiliation_strings":["University of Exeter,Department of Computer Science,UK","Department of Computer Science, University of Exeter, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Exeter,Department of Computer Science,UK","institution_ids":["https://openalex.org/I23923803"]},{"raw_affiliation_string":"Department of Computer Science, University of Exeter, UK","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053121936","display_name":"Syed Mohsen Naqvi","orcid":"https://orcid.org/0000-0002-1547-0908"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Mohsen Naqvi","raw_affiliation_strings":["Newcastle University,Intelligent Sensing and Communications Research Group,UK","Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University,Intelligent Sensing and Communications Research Group,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7283,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78761716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"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":0.9995999932289124,"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":0.9995999932289124,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9868000149726868,"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/dynamic-time-warping","display_name":"Dynamic time warping","score":0.7992513179779053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7923712134361267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6394267082214355},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5472724437713623},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5214756727218628},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5115126371383667},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5053172707557678},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5000662803649902},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47984668612480164},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.47666648030281067},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47390520572662354},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.468906044960022},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4300318956375122},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.4283331036567688},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4215894937515259},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.085330069065094}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.7992513179779053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923712134361267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6394267082214355},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5472724437713623},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5214756727218628},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5115126371383667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5053172707557678},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5000662803649902},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47984668612480164},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.47666648030281067},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47390520572662354},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.468906044960022},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4300318956375122},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.4283331036567688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4215894937515259},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.085330069065094},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097186","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2160144863","https://openalex.org/W2194775991","https://openalex.org/W2410961113","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2736334449","https://openalex.org/W2739179646","https://openalex.org/W2936468594","https://openalex.org/W2944006115","https://openalex.org/W2950568498","https://openalex.org/W2977470591","https://openalex.org/W3117493944","https://openalex.org/W3123784868","https://openalex.org/W3129528737","https://openalex.org/W3186213478","https://openalex.org/W4224932104","https://openalex.org/W4293252637","https://openalex.org/W4312556031","https://openalex.org/W6631190155","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6761327410"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W4205140848","https://openalex.org/W2095618524","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698"],"abstract_inverted_index":{"In":[0],"this":[1,172],"paper,":[2],"we":[3,35],"address":[4],"the":[5,38,43,55,59,66,71,85,90,104,116,119,130,136,139,148,154,161,166],"classification":[6],"of":[7,156,171],"medical":[8],"actions":[9,137],"with":[10,118],"only":[11],"one":[12],"single":[13],"sample":[14],"by":[15],"developing":[16],"a":[17,49,123],"novel":[18],"one-shot":[19,61],"learning":[20,51,62],"framework":[21,63],"which":[22,53,73],"contains":[23],"both":[24],"cross-attention":[25,99],"and":[26,64,106,114,141,160],"dynamic":[27],"time":[28],"warping":[29],"(DTW)":[30],"modules.":[31],"To":[32],"be":[33,110],"concrete,":[34],"firstly":[36],"transform":[37],"raw":[39],"skeleton":[40],"sequence":[41],"into":[42],"signal-level":[44],"image":[45],"representation.":[46],"We":[47],"exploit":[48],"metric":[50],"approach,":[52],"is":[54,74,81,126,174],"prototypical":[56],"network":[57,68,86],"for":[58,83,112],"proposed":[60,158],"choose":[65],"residual":[67],"(ResNet18)":[69],"as":[70],"backbone":[72],"widely":[75],"used":[76],"in":[77],"recent":[78],"years.":[79],"Cross-attention":[80],"applied":[82],"guiding":[84],"to":[87,128,165],"focus":[88],"on":[89,147],"more":[91],"important":[92],"joints":[93],"from":[94,138],"each":[95],"specific":[96],"action.":[97],"The":[98,144,169],"mechanism":[100],"that":[101],"applies":[102],"between":[103,135],"support":[105,140],"query":[107,142],"set":[108],"will":[109],"adapted":[111],"mining":[113],"matching":[115],"relationships":[117],"human":[120],"body.":[121],"Furthermore,":[122],"DTW":[124],"module":[125],"introduced":[127],"mitigate":[129],"temporal":[131],"information":[132],"mismatching":[133],"issue":[134],"sets.":[143],"experimental":[145],"results":[146],"NTU":[149],"RGB+D":[150],"120":[151],"dataset":[152],"demonstrate":[153],"effectiveness":[155],"our":[157],"approach":[159],"improved":[162],"performance":[163],"compared":[164],"baseline":[167],"approach.":[168],"code":[170],"work":[173],"available":[175],"at1.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}