{"id":"https://openalex.org/W4402979746","doi":"https://doi.org/10.1109/icme57554.2024.10688372","title":"A Lightweight Multi-Level Relation Network for Few-shot Action Recognition","display_name":"A Lightweight Multi-Level Relation Network for Few-shot Action Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979746","doi":"https://doi.org/10.1109/icme57554.2024.10688372"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5102394700","display_name":"Enqi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Enqi Liu","raw_affiliation_strings":["Beijing Institute of Technology,School of Computing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computing,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064162540","display_name":"Liyuan Pan","orcid":"https://orcid.org/0000-0002-9025-173X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyuan Pan","raw_affiliation_strings":["Beijing Institute of Technology,School of Computing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computing,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102394700"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.5248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66268136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9904000163078308,"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":0.9602000117301941,"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":0.7477105855941772},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7368990182876587},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6314169764518738},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.47768479585647583},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45431965589523315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44155237078666687},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1793287694454193},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.10633105039596558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477105855941772},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7368990182876587},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6314169764518738},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.47768479585647583},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45431965589523315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44155237078666687},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1793287694454193},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.10633105039596558},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/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/icme57554.2024.10688372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327514","display_name":"Beijing Institute of Technology Research Fund Program for Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2625366777","https://openalex.org/W2907214745","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2964350391","https://openalex.org/W2980535048","https://openalex.org/W2990503944","https://openalex.org/W3034587791","https://openalex.org/W3035374961","https://openalex.org/W3041485444","https://openalex.org/W3095374178","https://openalex.org/W3173271747","https://openalex.org/W3200749679","https://openalex.org/W4237044863","https://openalex.org/W4281740559","https://openalex.org/W4285184936","https://openalex.org/W4294691489","https://openalex.org/W4297697565","https://openalex.org/W4312259618","https://openalex.org/W4312875607","https://openalex.org/W4312959318","https://openalex.org/W4313046672"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Few-shot":[0],"(FS)":[1],"action":[2,38,67],"recognition":[3],"classifies":[4],"new":[5],"actions":[6],"with":[7],"limited":[8],"training":[9,28,75],"samples.":[10],"Most":[11],"existing":[12],"works":[13],"focus":[14],"on":[15,73,98],"the":[16,33,63,86,91,104],"variability":[17,64],"between":[18],"actions/videos":[19],"by":[20,89],"designing":[21],"for":[22,35],"either":[23],"feature":[24,92],"extraction":[25],"methods":[26,109],"or":[27],"strategies.":[29,76],"However,":[30],"they":[31],"ignore":[32],"relations":[34],"a":[36,55,78],"same":[37],"at":[39,94],"different":[40,95],"time":[41],"clips,":[42],"which":[43],"is":[44,82],"crucial":[45],"to":[46,84],"improve":[47,85],"class-specific":[48],"discriminability.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"lightweight":[56],"multi-level":[57],"relation":[58],"network":[59],"(MLRN)":[60],"that":[61,68,103],"considers":[62],"of":[65],"an":[66],"inner-":[69],"and":[70],"cross-video,":[71],"based":[72],"episodic":[74],"Furthermore,":[77],"query-support":[79],"similarity":[80],"classifier":[81],"introduced":[83],"class":[87],"identifiability":[88],"enhancing":[90],"utilisation":[93],"levels.":[96],"Experiments":[97],"three":[99],"challenging":[100],"benchmarks":[101],"demonstrate":[102],"proposed":[105],"MLRN":[106],"outperforms":[107],"state-of-the-art":[108],"while":[110],"using":[111],"approximately":[112],"50%":[113],"fewer":[114],"trainable":[115],"parameters.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}