{"id":"https://openalex.org/W7138160201","doi":"https://doi.org/10.1609/aaai.v40i11.37900","title":"Decompose and Conquer: Compositional Reasoning for Zero-Shot Temporal Action Localization","display_name":"Decompose and Conquer: Compositional Reasoning for Zero-Shot Temporal Action Localization","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138160201","doi":"https://doi.org/10.1609/aaai.v40i11.37900"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37900","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37900","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i11.37900","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129651293","display_name":"Haoyu Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Tang","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129703518","display_name":"Tianyuan Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyuan Liang","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129664396","display_name":"Han Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Jiang","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129682394","display_name":"Xuesong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xuesong Liu","raw_affiliation_strings":["University of Glasgow"],"affiliations":[{"raw_affiliation_string":"University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006269744","display_name":"Qinghai Zheng","orcid":"https://orcid.org/0000-0002-8684-1577"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghai Zheng","raw_affiliation_strings":["Fuzhou University"],"affiliations":[{"raw_affiliation_string":"Fuzhou University","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129727013","display_name":"Yupeng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Hu","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129651293"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47761194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"9404","last_page":"9412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9186000227928162,"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":0.9186000227928162,"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":0.03759999945759773,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0071000000461936,"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/action","display_name":"Action (physics)","score":0.6362000107765198},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6237999796867371},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5978000164031982},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5922999978065491},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5353000164031982},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5145999789237976},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5109000205993652},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.38960000872612},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3725000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6678000092506409},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6237999796867371},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5978000164031982},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3653999865055084},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3456999957561493},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C162670838","wikidata":"https://www.wikidata.org/wiki/Q6057295","display_name":"Interval temporal logic","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37900","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37900","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37900","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37900","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"Zero-Shot":[1],"Temporal":[2],"Action":[3,69],"Localization":[4],"(ZSTAL)":[5],"methods,":[6],"whether":[7],"training-based":[8,210],"or":[9],"training-free":[10,89,201],"ones,":[11],"still":[12],"predominantly":[13],"rely":[14],"on":[15,176,187,212],"a":[16,59,66,88,99,114,156,159,197],"single,":[17],"unified":[18,26],"query":[19],"to":[20,38,46,105,141],"localize":[21],"an":[22],"entire":[23],"action.":[24],"This":[25],"representation":[27],"is":[28],"fundamentally":[29],"ill-suited":[30],"for":[31,118],"complex":[32],"real-world":[33],"activities,":[34],"as":[35,58,138],"it":[36],"fails":[37],"capture":[39],"their":[40,177],"internal":[41],"compositional":[42,60],"structure":[43],"and":[44,63,83,111,180,184,189],"adapt":[45],"dynamic,":[47],"multi-stage":[48],"variations":[49],"across":[50],"videos.":[51],"To":[52],"address":[53],"this,":[54],"we":[55],"regard":[56],"ZSTAL":[57],"reasoning":[61],"task":[62],"introduce":[64],"CASCADE,":[65],"Context-Aware":[67],"Staged":[68],"DEcomposition":[70],"framework.":[71],"Inspired":[72],"by":[73,97,168],"the":[74,94,123,143],"human":[75],"cognitive":[76],"process":[77],"of":[78],"perceiving":[79],"context,":[80],"decomposing":[81],"events,":[82],"reconstructing":[84],"instances,":[85],"CASCADE":[86,193],"follows":[87],"pipeline.":[90],"It":[91],"first":[92],"perceives":[93],"video's":[95],"context":[96],"leveraging":[98],"Multimodal":[100],"Large":[101],"Language":[102],"Model":[103],"(MLLM)":[104],"both":[106],"filter":[107],"out":[108],"irrelevant":[109],"actions":[110],"then":[112,127,164],"generate":[113],"rich,":[115],"video-specific":[116],"caption":[117,130],"each":[119],"action":[120],"present":[121],"in":[122,145],"video.":[124],"An":[125],"LLM":[126],"decomposes":[128],"this":[129,152],"into":[131],"multiple,":[132],"temporally":[133],"ordered":[134],"stages,":[135],"which":[136],"serve":[137],"fine-grained":[139],"queries":[140],"guide":[142],"MLLM":[144],"estimating":[146],"frame-level":[147],"confidence":[148],"scores.":[149],"Recognizing":[150],"that":[151,192],"decomposition":[153],"can":[154],"fragment":[155],"single":[157],"action,":[158],"novel":[160],"hierarchical":[161],"merging":[162],"logic":[163],"reconstructs":[165],"complete":[166],"instances":[167],"intelligently":[169],"fusing":[170],"these":[171],"preliminary":[172],"temporal":[173],"segments":[174],"based":[175],"semantic":[178],"progression":[179],"coherence.":[181],"Extensive":[182],"experiments":[183],"ablation":[185],"studies":[186],"THUMOS14":[188],"ActivityNet-1.3":[190],"show":[191],"not":[194],"only":[195],"sets":[196],"new":[198],"state-of-the-art":[199],"among":[200],"methods":[202],"but,":[203],"most":[204],"notably,":[205],"significantly":[206],"outperforms":[207],"all":[208],"prior":[209],"approaches":[211],"ActivityNet-1.3.":[213]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}