{"id":"https://openalex.org/W4403791161","doi":"https://doi.org/10.1145/3664647.3681196","title":"Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition","display_name":"Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791161","doi":"https://doi.org/10.1145/3664647.3681196"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5100602455","display_name":"Yang Chen","orcid":"https://orcid.org/0009-0008-5752-1639"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yang Chen","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0008-5752-1639","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038505509","display_name":"Jingcai Guo","orcid":"https://orcid.org/0000-0002-0449-4525"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingcai Guo","raw_affiliation_strings":["The Hong Kong Polytechnic University & Hong Kong Polytechnic University Shenzhen Research Institute, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-0449-4525","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University & Hong Kong Polytechnic University Shenzhen Research Institute, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052482693","display_name":"Tian He","orcid":"https://orcid.org/0009-0007-1404-7183"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian He","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0007-1404-7183","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113151802","display_name":"Xiaocheng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaocheng Lu","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0006-1071-8122","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037035790","display_name":"Ling Wang","orcid":"https://orcid.org/0000-0002-1235-1241"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1235-1241","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100602455"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.1904,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80654297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"778","last_page":"786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.743999719619751},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.6811814904212952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6724837422370911},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5885979533195496},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.551315426826477},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4354056119918823},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.404060035943985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39864489436149597},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12259942293167114},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09553325176239014},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06751769781112671}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.743999719619751},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.6811814904212952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6724837422370911},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5885979533195496},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.551315426826477},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4354056119918823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.404060035943985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39864489436149597},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12259942293167114},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09553325176239014},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06751769781112671},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-148929","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-148929","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2056898157","https://openalex.org/W2400717490","https://openalex.org/W2944006115","https://openalex.org/W2962716320","https://openalex.org/W2963076818","https://openalex.org/W2963283377","https://openalex.org/W2964134613","https://openalex.org/W2972073579","https://openalex.org/W2982407353","https://openalex.org/W2991813857","https://openalex.org/W3035050855","https://openalex.org/W3035655772","https://openalex.org/W3096741441","https://openalex.org/W3195429019","https://openalex.org/W3203634062","https://openalex.org/W4200633401","https://openalex.org/W4297899821","https://openalex.org/W4301409532","https://openalex.org/W4313123992","https://openalex.org/W4379985979","https://openalex.org/W4386075765","https://openalex.org/W4386076660","https://openalex.org/W4387969459","https://openalex.org/W4390871852"],"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/W4298312966","https://openalex.org/W2958550830"],"abstract_inverted_index":{"Skeleton-based":[0],"zero-shot":[1,94],"action":[2,58,75],"recognition":[3],"aims":[4],"to":[5,149,166],"recognize":[6],"unknown":[7,30,57],"human":[8,125],"actions":[9,19],"based":[10,111],"on":[11,37,112,185],"the":[12,16,39,42,52,61,99,106,118,131,134,138,144,151,155,162,168],"learned":[13],"priors":[14],"of":[15,64,124],"known":[17,28,43],"skeleton-based":[18,93],"and":[20,29,47,89,116,133,146,158,182,191],"a":[21,83],"semantic":[22,48,135,163],"descriptor":[23],"space":[24,46,50,136,157],"shared":[25],"by":[26],"both":[27],"categories.":[31,76],"However,":[32],"previous":[33],"works":[34],"mainly":[35],"focus":[36],"establishing":[38],"bridges":[40],"between":[41,130],"skeleton":[44,107,132,156],"representation":[45],"descriptions":[49,123],"at":[51,98,137],"coarse-grained":[53],"level":[54],"for":[55,92,128],"recognizing":[56],"categories,":[59],"ignoring":[60],"fine-grained":[62,100,139],"alignment":[63,129],"these":[65,79],"two":[66],"spaces,":[67],"resulting":[68],"in":[69,72,180],"suboptimal":[70],"performance":[71,179],"distinguishing":[73],"high-similarity":[74,169],"To":[77],"address":[78],"challenges,":[80],"we":[81,104,142],"propose":[82],"novel":[84],"method":[85,176],"via":[86],"Side":[87],"information":[88,120],"dual-prompTs":[90],"learning":[91],"Action":[95],"Recognition":[96],"(STAR)":[97],"level.":[101],"Specifically,":[102],"1)":[103],"decompose":[105],"into":[108],"several":[109],"parts":[110],"its":[113],"topology":[114],"structure":[115],"introduce":[117],"side":[119],"concerning":[121],"multi-part":[122],"body":[126],"movements":[127],"level;":[140],"2)":[141],"design":[143],"visual-attribute":[145],"semantic-part":[147],"prompts":[148],"improve":[150],"intra-class":[152],"compactness":[153],"within":[154,161],"inter-class":[159],"separability":[160],"space,":[164],"respectively,":[165],"distinguish":[167],"actions.":[170],"Extensive":[171],"experiments":[172],"show":[173],"that":[174],"our":[175],"achieves":[177],"state-of-the-art":[178],"ZSL":[181],"GZSL":[183],"settings":[184],"NTU":[186,188],"RGB+D,":[187],"RGB+D":[189],"120,":[190],"PKU-MMD":[192],"datasets.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}