{"id":"https://openalex.org/W4409129241","doi":"https://doi.org/10.1109/tmm.2025.3557615","title":"Multimodal Large Models are Effective Action Anticipators","display_name":"Multimodal Large Models are Effective Action Anticipators","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409129241","doi":"https://doi.org/10.1109/tmm.2025.3557615"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3557615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557615","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5043220498","display_name":"Binglu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I148099405","display_name":"Xi'an University of Architecture and Technology","ror":"https://ror.org/04v2j2k71","country_code":"CN","type":"education","lineage":["https://openalex.org/I148099405"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Binglu Wang","raw_affiliation_strings":["College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China","institution_ids":["https://openalex.org/I148099405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387925","display_name":"Yao Tian","orcid":"https://orcid.org/0009-0002-3530-3944"},"institutions":[{"id":"https://openalex.org/I148099405","display_name":"Xi'an University of Architecture and Technology","ror":"https://ror.org/04v2j2k71","country_code":"CN","type":"education","lineage":["https://openalex.org/I148099405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Tian","raw_affiliation_strings":["College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China","institution_ids":["https://openalex.org/I148099405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006776719","display_name":"Shunzhou Wang","orcid":"https://orcid.org/0000-0001-5401-043X"},"institutions":[{"id":"https://openalex.org/I148099405","display_name":"Xi'an University of Architecture and Technology","ror":"https://ror.org/04v2j2k71","country_code":"CN","type":"education","lineage":["https://openalex.org/I148099405"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunzhou Wang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen, China","College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China","institution_ids":["https://openalex.org/I148099405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102528494","display_name":"Le Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Le Yang","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","Institute of Artificial IntelligenceHefei Comprehensive National Science Center"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial IntelligenceHefei Comprehensive National Science Center","institution_ids":["https://openalex.org/I4210137491","https://openalex.org/I4210105595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043220498"],"corresponding_institution_ids":["https://openalex.org/I148099405"],"apc_list":null,"apc_paid":null,"fwci":16.7272,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.99116858,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"2949","last_page":"2960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.1356000006198883,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.1356000006198883,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.11550000309944153,"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":0.8181672692298889},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47359970211982727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3692384362220764},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34369081258773804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181672692298889},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47359970211982727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3692384362220764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34369081258773804},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3557615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557615","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2099614498","https://openalex.org/W2109698606","https://openalex.org/W2194775991","https://openalex.org/W2913636123","https://openalex.org/W2945792291","https://openalex.org/W2963524571","https://openalex.org/W2963570630","https://openalex.org/W2995301359","https://openalex.org/W2997487053","https://openalex.org/W3021065276","https://openalex.org/W3089870586","https://openalex.org/W3094502228","https://openalex.org/W3096383329","https://openalex.org/W3132567969","https://openalex.org/W3134916662","https://openalex.org/W3166738350","https://openalex.org/W3182236906","https://openalex.org/W3205786327","https://openalex.org/W3208955650","https://openalex.org/W4205991051","https://openalex.org/W4210668396","https://openalex.org/W4225495512","https://openalex.org/W4312519375","https://openalex.org/W4312660844","https://openalex.org/W4312688882","https://openalex.org/W4313023218","https://openalex.org/W4313071313","https://openalex.org/W4313318649","https://openalex.org/W4319299948","https://openalex.org/W4378510493","https://openalex.org/W4382999123","https://openalex.org/W4386065959","https://openalex.org/W4386076167","https://openalex.org/W4386187806","https://openalex.org/W4388430502","https://openalex.org/W4389519587","https://openalex.org/W4390691978","https://openalex.org/W4392437685","https://openalex.org/W4392969524","https://openalex.org/W4394625740","https://openalex.org/W4394910421","https://openalex.org/W4399864536","https://openalex.org/W4400229101","https://openalex.org/W4400647053","https://openalex.org/W4402944023","https://openalex.org/W4402961670","https://openalex.org/W4402969043","https://openalex.org/W4404195371","https://openalex.org/W6759579507","https://openalex.org/W6796581206","https://openalex.org/W6810081322","https://openalex.org/W6843825870","https://openalex.org/W6856926427","https://openalex.org/W6861489518","https://openalex.org/W6868320316"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,23,137,191,206],"long-term":[3,38,65],"action":[4,66,105,120,141,207],"anticipation":[5],"demands":[6],"solutions":[7],"that":[8,79],"can":[9],"effectively":[10],"model":[11,94],"temporal":[12],"dynamics":[13],"over":[14],"extended":[15],"periods":[16],"while":[17],"deeply":[18],"understanding":[19],"the":[20,73,96,110,123,134,166,189,192,204],"inherent":[21],"semantics":[22],"actions.":[24,91],"Traditional":[25],"approaches,":[26],"which":[27],"primarily":[28],"rely":[29],"on":[30,185],"recurrent":[31],"units":[32],"or":[33,128],"Transformer":[34],"layers":[35],"to":[36,88,114,151,164,200],"capture":[37,172],"dependencies,":[39],"often":[40],"fall":[41],"short":[42],"in":[43,203],"addressing":[44],"these":[45],"challenges.":[46],"Large":[47],"Language":[48],"Models":[49],"(LLMs),":[50],"with":[51],"their":[52],"robust":[53],"sequential":[54,148],"modeling":[55],"capabilities":[56],"and":[57,108,146,171,176],"extensive":[58],"commonsense":[59,135],"knowledge,":[60],"present":[61],"new":[62],"opportunities":[63],"for":[64,125,143],"anticipation.":[67,208],"In":[68,155],"this":[69],"work,":[70],"we":[71,139,157],"introduce":[72,158],"ActionLLM":[74,194],"framework,":[75,195],"a":[76,115,159,197],"novel":[77],"approach":[78],"treats":[80],"video":[81],"sequences":[82],"as":[83],"successive":[84],"tokens,":[85,102],"leveraging":[86],"LLMs":[87,202],"anticipate":[89],"future":[90,101],"Our":[92],"baseline":[93],"simplifies":[95],"LLM":[97],"architecture":[98],"by":[99],"setting":[100],"incorporating":[103],"an":[104],"tuning":[106],"module,":[107],"reducing":[109],"textual":[111,149,177],"decoder":[112],"layer":[113],"linear":[116],"layer,":[117],"enabling":[118],"straightforward":[119],"prediction":[121],"without":[122],"need":[124],"complex":[126],"instructions":[127],"redundant":[129],"descriptions.":[130],"To":[131],"further":[132],"harness":[133],"reasoning":[136],"LLMs,":[138],"predict":[140],"categories":[142],"observed":[144],"frames":[145],"use":[147],"clues":[150],"guide":[152],"semantic":[153],"understanding.":[154],"addition,":[156],"Cross-Modality":[160],"Interaction":[161],"Block,":[162],"designed":[163],"explore":[165,201],"specificity":[167],"within":[168],"each":[169],"modality":[170],"interactions":[173],"between":[174],"vision":[175],"modalities,":[178],"thereby":[179],"enhancing":[180],"multimodal":[181],"tuning.":[182],"Extensive":[183],"experiments":[184],"benchmark":[186],"datasets":[187],"demonstrate":[188],"superiority":[190],"proposed":[193],"encouraging":[196],"promising":[198],"direction":[199],"context":[205]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}