{"id":"https://openalex.org/W4392903023","doi":"https://doi.org/10.1109/icassp48485.2024.10445997","title":"Hierarchical Home Action Understanding with Implicit and Explicit Prior Knowledge","display_name":"Hierarchical Home Action Understanding with Implicit and Explicit Prior Knowledge","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903023","doi":"https://doi.org/10.1109/icassp48485.2024.10445997"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5075343261","display_name":"Yuchen Zhou","orcid":"https://orcid.org/0000-0003-2290-066X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Zhou","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University,School of Intelligent Systems Engineering","School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University,School of Intelligent Systems Engineering","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062708755","display_name":"Guang Tan","orcid":"https://orcid.org/0000-0002-0658-8867"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Tan","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University,School of Intelligent Systems Engineering","School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University,School of Intelligent Systems Engineering","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042895349","display_name":"Chao Gou","orcid":"https://orcid.org/0000-0002-4128-886X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Gou","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University,School of Intelligent Systems Engineering","School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University,School of Intelligent Systems Engineering","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-Sen University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.0712,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76680179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4015","last_page":"4019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8124163150787354},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6781600117683411},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6289185285568237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6189345121383667},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5893833637237549},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5323892831802368},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5306434035301208},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.526395320892334},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45055392384529114},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.4465475082397461},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37673038244247437},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3378579914569855},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14518305659294128},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0850600004196167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124163150787354},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6781600117683411},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6289185285568237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6189345121383667},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5893833637237549},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5323892831802368},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5306434035301208},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.526395320892334},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45055392384529114},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.4465475082397461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37673038244247437},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3378579914569855},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14518305659294128},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0850600004196167},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2747329762","https://openalex.org/W3126721948","https://openalex.org/W3138516171","https://openalex.org/W3173599944","https://openalex.org/W4206711354","https://openalex.org/W4225308875","https://openalex.org/W4225319992","https://openalex.org/W4226138051","https://openalex.org/W4285225554","https://openalex.org/W4296912696","https://openalex.org/W4302362921","https://openalex.org/W4312443924","https://openalex.org/W4313046672","https://openalex.org/W4318618520","https://openalex.org/W4372348095","https://openalex.org/W4386075591","https://openalex.org/W4386231006","https://openalex.org/W4386590862","https://openalex.org/W4387694723","https://openalex.org/W4387969759","https://openalex.org/W4388543762","https://openalex.org/W4389988439","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2362939901","https://openalex.org/W2734554632","https://openalex.org/W2379200451","https://openalex.org/W2356257939","https://openalex.org/W4254623023"],"abstract_inverted_index":{"Existing":[0],"investigations":[1,20],"on":[2],"action":[3,82],"understanding":[4,72],"have":[5,21],"made":[6],"noteworthy":[7],"advancements":[8],"by":[9],"treating":[10],"activities":[11],"as":[12,38,52],"holistic":[13,81],"events":[14],"occurring":[15],"in":[16,108,155],"videos.":[17],"However,":[18],"these":[19],"limited":[22],"ability":[23],"to":[24,114,127],"comprehensively":[25],"extract":[26],"and":[27,40,59,111,158],"represent":[28],"human":[29,46],"experiential":[30],"knowledge,":[31],"which":[32,77],"hampers":[33],"various":[34],"practical":[35],"applications,":[36],"such":[37],"robotics":[39],"human-computer":[41],"interaction.":[42],"We":[43],"argue":[44],"that":[45,103],"actions":[47,61],"can":[48],"be":[49],"better":[50],"understood":[51],"hierarchical":[53,71],"compositions":[54],"of":[55,86,131,139],"multiple":[56,84,105],"interactive":[57,92],"objects":[58],"atomic":[60],"with":[62],"spatio-temporal":[63],"relations.":[64],"To":[65],"this":[66,95],"end,":[67],"we":[68,97,122],"propose":[69],"a":[70,79,99],"framework":[73],"for":[74,149],"home":[75],"actions,":[76],"decomposes":[78],"single":[80],"into":[83],"quintuples":[85],"<subject,":[87],"spatial":[88],"relation,":[89],"operation,":[90],"gaze,":[91],"object>.":[93],"Within":[94],"framework,":[96],"introduce":[98],"two-stage":[100],"network":[101],"architecture":[102],"leverages":[104],"prior":[106],"knowledge":[107,126],"both":[109],"implicit":[110],"explicit":[112],"ways":[113],"facilitate":[115],"mutual":[116],"learning":[117],"within":[118],"quintuples.":[119],"In":[120],"particular,":[121],"fully":[123],"exploit":[124],"statistical":[125],"enhance":[128],"the":[129,137,146],"inference":[130],"data-driven":[132],"visual":[133],"model.":[134],"Experiments":[135],"validate":[136],"effectiveness":[138],"our":[140,159],"proposed":[141],"method.":[142],"This":[143],"is":[144,163],"also":[145],"winning":[147],"solution":[148],"HOMAGE":[150],"Competition":[151],"@":[152],"ActivityNet":[153],"Challenge":[154],"CVPR":[156],"2022":[157],"brief":[160],"oral":[161],"representation":[162],"available":[164],"at":[165],"https://youtu.be/KK3SPK6iueE?si=hrFZzSABNyrrL6jF&t=1727.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}