{"id":"https://openalex.org/W4401991019","doi":"https://doi.org/10.1109/icmew63481.2024.10645431","title":"Leveraging Multimodal Knowledge for Spatio-Temporal Action Localization","display_name":"Leveraging Multimodal Knowledge for Spatio-Temporal Action Localization","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401991019","doi":"https://doi.org/10.1109/icmew63481.2024.10645431"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew63481.2024.10645431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103104903","display_name":"Keke Chen","orcid":"https://orcid.org/0009-0006-2985-8918"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Chen","raw_affiliation_strings":["Nanjing university of science and technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing university of science and technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106833708","display_name":"T. Zhewei","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"T. Zhewei","raw_affiliation_strings":["Nanjing university of science and technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing university of science and technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbo Shu","raw_affiliation_strings":["Nanjing university of science and technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing university of science and technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9857000112533569,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9639000296592712,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.744281530380249},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5856800079345703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4057101607322693},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.393207311630249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744281530380249},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5856800079345703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4057101607322693},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.393207311630249},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew63481.2024.10645431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew63481.2024.10645431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5950360714","display_name":null,"funder_award_id":"BK20211520","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G6608055184","display_name":null,"funder_award_id":"62222207,62072245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2618799552","https://openalex.org/W2883275382","https://openalex.org/W2904080086","https://openalex.org/W2963150697","https://openalex.org/W2963524571","https://openalex.org/W2990503944","https://openalex.org/W3034572008","https://openalex.org/W3109173645","https://openalex.org/W3173407577","https://openalex.org/W3200114289","https://openalex.org/W3204116406","https://openalex.org/W4221167396","https://openalex.org/W4312509322","https://openalex.org/W4386076295","https://openalex.org/W4387969909","https://openalex.org/W4390190606","https://openalex.org/W4390872527","https://openalex.org/W6801567822","https://openalex.org/W6810265253"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Locating":[0],"persons":[1],"and":[2,35,78,93,163],"recognizing":[3],"their":[4],"actions":[5,26],"in":[6,14,33,61,137,192],"chaotic":[7,29],"scenes":[8],"is":[9,197],"a":[10,43,55,69,95,112,131,170],"more":[11,171],"challenging":[12],"task":[13],"video":[15,147],"understanding.":[16],"Contrary":[17],"to":[18,149,165],"the":[19,25,36,85,117,151,180,186,189],"quotidian":[20],"conduct":[21],"observed":[22],"amongst":[23],"humans,":[24],"exhibited":[27],"during":[28],"incidents":[30],"markedly":[31],"diverge":[32],"execution":[34],"resultant":[37],"influence":[38],"on":[39,54,179],"surrounding":[40],"individuals,":[41],"engendering":[42],"heightened":[44],"complexity.":[45],"Conventional":[46],"spatio-temporal":[47],"action":[48,126],"localization":[49],"methods":[50],"that":[51,115],"rely":[52],"solely":[53],"single":[56],"visual":[57,91,138,143],"modality":[58],"fall":[59],"short":[60],"complex":[62,154,176],"scenarios.":[63],"This":[64],"paper":[65],"explores":[66],"STAL":[67,92,155],"from":[68,121],"multimodal":[70],"perspective":[71],"by":[72],"leveraging":[73],"large":[74],"language":[75],"models":[76,124],"(LLMs)":[77],"vision-language":[79],"(VL)":[80],"foundation":[81,102,123],"models.":[82],"We":[83],"analyze":[84],"inherent":[86],"feature":[87],"aggregation":[88,97],"phase":[89],"of":[90,119,153,175,188],"introduce":[94],"knowledge":[96,120],"approach":[98],"tailored":[99],"for":[100,134],"VL":[101,122],"models,":[103],"termed":[104],"Multimodal":[105],"Foundation":[106],"Knowledge":[107],"Integration":[108],"(MFKI).":[109],"MFKI":[110,140],"includes":[111],"generic":[113,142],"decoder":[114,133],"facilitates":[116],"association":[118],"with":[125,145],"features,":[127],"as":[128,130],"well":[129],"specific":[132,146],"relational":[135],"reasoning":[136],"STAL.":[139],"combines":[141],"representations":[144],"features":[148],"meet":[150],"demands":[152],"tasks.":[156],"Additionally,":[157],"we":[158],"utilize":[159],"LLMs":[160],"(i.e.":[161],"GPT)":[162],"prompting":[164],"enrich":[166],"label":[167],"augmentation,":[168],"fostering":[169],"comprehensive":[172],"linguistic":[173],"understanding":[174],"actions.":[177],"Experiments":[178],"Chaotic":[181],"World":[182],"dataset":[183],"have":[184],"proven":[185],"effectiveness":[187],"method":[190],"proposed":[191],"this":[193],"paper.":[194],"The":[195],"code":[196],"available":[198],"at":[199],"https://github.com/CKK-coder/Chaotic_World/tree/master.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}