{"id":"https://openalex.org/W4385767810","doi":"https://doi.org/10.24963/ijcai.2023/191","title":"HOI-aware Adaptive Network for Weakly-supervised Action Segmentation","display_name":"HOI-aware Adaptive Network for Weakly-supervised Action Segmentation","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767810","doi":"https://doi.org/10.24963/ijcai.2023/191"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/191","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/191","pdf_url":"https://www.ijcai.org/proceedings/2023/0191.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0191.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015881752","display_name":"Runzhong Zhang","orcid":"https://orcid.org/0000-0001-6144-5546"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Runzhong Zhang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020106541","display_name":"Suchen Wang","orcid":"https://orcid.org/0000-0002-4086-0713"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Suchen Wang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013973037","display_name":"Yueqi Duan","orcid":"https://orcid.org/0000-0002-1190-6663"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueqi Duan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926293","display_name":"Yansong Tang","orcid":"https://orcid.org/0000-0002-1534-4549"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Tang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333769","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0003-0179-1396"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Beijing Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103379503","display_name":"Yap\u2010Peng Tan","orcid":"https://orcid.org/0000-0002-0645-9109"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yap-Peng Tan","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8446,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8157603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1722","last_page":"1730"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9966999888420105,"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":0.8030509948730469},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7378612160682678},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6969883441925049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6418622136116028},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5974102020263672},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5947073698043823},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5615419149398804},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5316221117973328},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5080933570861816},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4576091468334198},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4430016875267029},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37179815769195557},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3408013582229614},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.06877371668815613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030509948730469},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7378612160682678},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6969883441925049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6418622136116028},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5974102020263672},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5947073698043823},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5615419149398804},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5316221117973328},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5080933570861816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4576091468334198},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4430016875267029},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37179815769195557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3408013582229614},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.06877371668815613},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.24963/ijcai.2023/191","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/191","pdf_url":"https://www.ijcai.org/proceedings/2023/0191.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.26227","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.26227","pdf_url":"https://arxiv.org/pdf/2604.26227","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.26227","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26227","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/191","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/191","pdf_url":"https://www.ijcai.org/proceedings/2023/0191.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4782915672","display_name":null,"funder_award_id":"62206147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767810.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W611457968","https://openalex.org/W1924770834","https://openalex.org/W1988650444","https://openalex.org/W2019660985","https://openalex.org/W2099614498","https://openalex.org/W2108710284","https://openalex.org/W2109698606","https://openalex.org/W2144506857","https://openalex.org/W2194775991","https://openalex.org/W2314362175","https://openalex.org/W2461621749","https://openalex.org/W2477205648","https://openalex.org/W2530494944","https://openalex.org/W2550143307","https://openalex.org/W2600081845","https://openalex.org/W2799262584","https://openalex.org/W2883697687","https://openalex.org/W2888096830","https://openalex.org/W2962202279","https://openalex.org/W2962916463","https://openalex.org/W2963642716","https://openalex.org/W2964311439","https://openalex.org/W3009622574","https://openalex.org/W3014792118","https://openalex.org/W3034687522","https://openalex.org/W3034802267","https://openalex.org/W3034891989","https://openalex.org/W3034951775","https://openalex.org/W3035440494","https://openalex.org/W3035557275","https://openalex.org/W3035598501","https://openalex.org/W3083550439","https://openalex.org/W3106121867","https://openalex.org/W3108772932","https://openalex.org/W3151099711","https://openalex.org/W3168371806","https://openalex.org/W3168488421","https://openalex.org/W3180945712","https://openalex.org/W3202074654","https://openalex.org/W3207346664","https://openalex.org/W4225271941","https://openalex.org/W4307765037","https://openalex.org/W4313055276","https://openalex.org/W4394642966"],"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/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"In":[0],"this":[1,34],"paper,":[2],"we":[3,53,99,119],"propose":[4,120],"an":[5,126],"HOI-aware":[6],"adaptive":[7,127],"network":[8,21,86],"named":[9],"AdaAct":[10],"for":[11,69],"weakly-supervised":[12],"action":[13,25,70],"segmentation.":[14,71],"Most":[15],"existing":[16],"methods":[17],"learn":[18,125],"a":[19,102,121],"fixed":[20],"to":[22,55,80,89,124],"predict":[23],"the":[24,30,90,111,116,133,137,144,157],"of":[26,140,159],"each":[27],"frame":[28],"with":[29],"neighboring":[31],"frames.":[32],"However,":[33],"would":[35],"result":[36],"in":[37],"ambiguity":[38],"when":[39],"estimating":[40],"similar":[41],"actions,":[42,83],"such":[43],"as":[44,65],"pouring":[45,48],"juice":[46],"and":[47,109,154],"coffee.":[49],"To":[50],"address":[51],"this,":[52],"aim":[54],"exploit":[56],"temporally":[57],"global":[58],"but":[59],"spatially":[60],"local":[61],"human-object":[62],"interactions":[63],"(HOI)":[64],"video-level":[66],"prior":[67],"knowledge":[68],"The":[72],"long-term":[73],"HOI":[74,92,104,114,138],"sequence":[75,93],"provides":[76],"crucial":[77],"contextual":[78],"information":[79,139],"distinguish":[81],"ambiguous":[82],"where":[84],"our":[85,160],"dynamically":[87],"adapts":[88],"given":[91],"at":[94],"test":[95],"time.":[96],"More":[97],"specifically,":[98],"first":[100],"design":[101],"video":[103],"encoder":[105],"that":[106],"extracts,":[107],"selects,":[108],"integrates":[110],"most":[112],"representative":[113],"throughout":[115],"video.":[117],"Then,":[118],"two-branch":[122],"HyperNetwork":[123],"temporal":[128],"encoder,":[129],"which":[130],"automatically":[131],"adjusts":[132],"parameters":[134],"based":[135],"on":[136,143,148],"various":[141],"videos":[142],"fly.":[145],"Extensive":[146],"experiments":[147],"two":[149],"widely-used":[150],"datasets":[151],"including":[152],"Breakfast":[153],"50Salads":[155],"demonstrate":[156],"effectiveness":[158],"method":[161],"under":[162],"different":[163],"evaluation":[164],"metrics.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}