{"id":"https://openalex.org/W4415539923","doi":"https://doi.org/10.1145/3746027.3755134","title":"Zero-shot Compositional Action Recognition with Neural Logic Constraints","display_name":"Zero-shot Compositional Action Recognition with Neural Logic Constraints","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539923","doi":"https://doi.org/10.1145/3746027.3755134"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755134","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5112929224","display_name":"G Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gefan Ye","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412889","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-5678-4487"},"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":"Lin Li","raw_affiliation_strings":["AI Chip Center for Emerging Smart Systems, Hong Kong, China and The Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart Systems, Hong Kong, China and The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021381008","display_name":"Kexin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2800556661","display_name":"China Tobacco","ror":"https://ror.org/030d08e08","country_code":"CN","type":"government","lineage":["https://openalex.org/I2800556661"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexin Li","raw_affiliation_strings":["Zhejiang Tobacco Monopoly Administration, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Tobacco Monopoly Administration, Hangzhou, China","institution_ids":["https://openalex.org/I2800556661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"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":"Long Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112929224"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16022658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3625","last_page":"3634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9835000038146973,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9835000038146973,"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/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9632999897003174,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12386","display_name":"Advanced X-ray and CT Imaging","score":0.9559999704360962,"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/principle-of-compositionality","display_name":"Principle of compositionality","score":0.554099977016449},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5511999726295471},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5166000127792358},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5013999938964844},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4787999987602234},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4438000023365021},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.43799999356269836},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4189999997615814},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3880999982357025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098999977111816},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43459999561309814},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32659998536109924},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C173856430","wikidata":"https://www.wikidata.org/wiki/Q3257964","display_name":"Separation logic","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755134","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167655","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167655","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":[{"id":"https://openalex.org/G5102038799","display_name":null,"funder_award_id":"62441617","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6689777572","display_name":null,"funder_award_id":"226-2025-00057","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1503384494","https://openalex.org/W1835689390","https://openalex.org/W2005530747","https://openalex.org/W2056715049","https://openalex.org/W2119018096","https://openalex.org/W2625366777","https://openalex.org/W2755624598","https://openalex.org/W2805029945","https://openalex.org/W2982863468","https://openalex.org/W3034679267","https://openalex.org/W3088102655","https://openalex.org/W3109754877","https://openalex.org/W3160967194","https://openalex.org/W3162332195","https://openalex.org/W3164354101","https://openalex.org/W3205663647","https://openalex.org/W3216178672","https://openalex.org/W4210618466","https://openalex.org/W4250216568","https://openalex.org/W4312310776","https://openalex.org/W4386065691","https://openalex.org/W4386113259","https://openalex.org/W4387848745","https://openalex.org/W4387969137"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"compositional":[1,27,38,80,118],"action":[2],"recognition":[3],"(ZS-CAR)":[4],"aims":[5],"to":[6,42,53,74],"identify":[7],"unseen":[8],"verb-object":[9],"compositions":[10],"in":[11,30,144],"the":[12,16,58,108,111,114,117,127,134,157,168,180],"videos":[13],"by":[14,77],"exploiting":[15],"learned":[17],"knowledge":[18],"of":[19,121,182],"verb":[20],"and":[21,56,81,103,147,162],"object":[22],"primitives":[23],"during":[24],"training.":[25],"Despite":[26],"learning's":[28],"progress":[29],"ZS-CAR,":[31],"two":[32],"critical":[33],"challenges":[34,76],"persist:":[35],"1)":[36],"Missing":[37],"structure":[39],"constraint,":[40,51],"leading":[41,52],"spurious":[43],"correlations":[44],"between":[45,159],"primitives;":[46],"2)":[47],"Neglecting":[48],"semantic":[49,54],"hierarchy":[50],"ambiguity":[55],"impairing":[57],"training":[59],"process.":[60],"In":[61],"this":[62,86],"paper,":[63],"we":[64,88],"argue":[65],"that":[66,95,172],"human-like":[67],"symbolic":[68,98,160],"reasoning":[69,119,138],"offers":[70],"a":[71,90],"principled":[72],"solution":[73],"these":[75,142],"explicitly":[78],"modeling":[79],"hierarchical":[82],"structured":[83],"abstraction.":[84],"To":[85],"end,":[87],"propose":[89],"logic-driven":[91,184],"ZS-CAR":[92],"framework":[93],"LogicCAR":[94,154,174],"integrates":[96],"dual":[97],"constraints:":[99],"Explicit":[100],"Compositional":[101],"Logic":[102],"Hierarchical":[104],"Primitive":[105],"Logic.":[106],"Specifically,":[107],"former":[109],"models":[110,135],"restrictions":[112],"within":[113],"compositions,":[115],"enhancing":[116],"ability":[120],"our":[122,173,183],"model.":[123],"The":[124],"latter":[125],"investigates":[126],"semantical":[128],"dependencies":[129],"among":[130],"different":[131],"primitives,":[132],"empowering":[133],"with":[136],"fine-to-coarse":[137],"capacity.":[139],"By":[140],"formalizing":[141],"constraints":[143],"first-order":[145],"logic":[146],"embedding":[148],"them":[149],"into":[150],"neural":[151],"network":[152],"architectures,":[153],"systematically":[155],"bridges":[156],"gap":[158],"abstraction":[161],"existing":[163,176],"models.":[164],"Extensive":[165],"experiments":[166],"on":[167],"Sth-com":[169],"dataset":[170],"demonstrate":[171],"outperforms":[175],"baseline":[177],"methods,":[178],"proving":[179],"effectiveness":[181],"constraints.":[185]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}