{"id":"https://openalex.org/W4408593028","doi":"https://doi.org/10.1109/tcsvt.2025.3552895","title":"A Multi-Modal Architecture With Spatio-Temporal-Text Adaptation for Video-Based Traffic Accident Anticipation","display_name":"A Multi-Modal Architecture With Spatio-Temporal-Text Adaptation for Video-Based Traffic Accident Anticipation","publication_year":2025,"publication_date":"2025-03-19","ids":{"openalex":"https://openalex.org/W4408593028","doi":"https://doi.org/10.1109/tcsvt.2025.3552895"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3552895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3552895","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5107553187","display_name":"Patrik Patera","orcid":"https://orcid.org/0000-0002-7597-1923"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Patrik Patera","raw_affiliation_strings":["Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077826217","display_name":"Yie\u2010Tarng Chen","orcid":"https://orcid.org/0000-0002-7221-1603"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yie-Tarng Chen","raw_affiliation_strings":["Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111446401","display_name":"Wen\u2010Hsien Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Hsien Fang","raw_affiliation_strings":["Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107553187"],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":2.0359,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84334509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"35","issue":"9","first_page":"8989","last_page":"9002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.955299973487854,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.955299973487854,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9117000102996826,"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/T14270","display_name":"Simulation and Modeling Applications","score":0.902999997138977,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/computer-science","display_name":"Computer science","score":0.7498484253883362},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.7364698648452759},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6430263519287109},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6077600121498108},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5318108797073364},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4519292712211609},{"id":"https://openalex.org/keywords/accident","display_name":"Accident (philosophy)","score":0.4265231490135193},{"id":"https://openalex.org/keywords/traffic-accident","display_name":"Traffic accident","score":0.415016233921051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4037815034389496},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.375149667263031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3665000796318054},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.225989431142807},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13413551449775696},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12312966585159302},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10492175817489624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498484253883362},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.7364698648452759},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6430263519287109},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6077600121498108},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5318108797073364},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4519292712211609},{"id":"https://openalex.org/C2780289543","wikidata":"https://www.wikidata.org/wiki/Q424630","display_name":"Accident (philosophy)","level":2,"score":0.4265231490135193},{"id":"https://openalex.org/C2989506057","wikidata":"https://www.wikidata.org/wiki/Q9687","display_name":"Traffic accident","level":2,"score":0.415016233921051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4037815034389496},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.375149667263031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3665000796318054},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.225989431142807},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13413551449775696},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12312966585159302},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10492175817489624},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3552895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3552895","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.7300000190734863,"display_name":"Good health and well-being"}],"awards":[{"id":"https://openalex.org/G3955517149","display_name":null,"funder_award_id":"113-2221-E-011-132-MY2","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G7434853276","display_name":null,"funder_award_id":"112-2221-E-011-099-MY2","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2592008540","https://openalex.org/W2770446450","https://openalex.org/W2806282362","https://openalex.org/W2962858109","https://openalex.org/W2963692464","https://openalex.org/W2963737762","https://openalex.org/W2964217160","https://openalex.org/W3046330049","https://openalex.org/W3094502228","https://openalex.org/W3095632107","https://openalex.org/W3162428900","https://openalex.org/W3176454305","https://openalex.org/W3184612208","https://openalex.org/W3195949276","https://openalex.org/W4205991051","https://openalex.org/W4212876679","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4225724731","https://openalex.org/W4309918472","https://openalex.org/W4312532041","https://openalex.org/W4312560592","https://openalex.org/W4312986563","https://openalex.org/W4316660744","https://openalex.org/W4323797084","https://openalex.org/W4324290198","https://openalex.org/W4379984073","https://openalex.org/W4385245566","https://openalex.org/W4385569741","https://openalex.org/W4386065447","https://openalex.org/W4386071598","https://openalex.org/W4386075796","https://openalex.org/W4387967270","https://openalex.org/W4389252877","https://openalex.org/W4390873054","https://openalex.org/W4390874610","https://openalex.org/W4393153999","https://openalex.org/W4398152834","https://openalex.org/W4402275786","https://openalex.org/W4402916233","https://openalex.org/W4403600578","https://openalex.org/W4404035381"],"related_works":["https://openalex.org/W2359303428","https://openalex.org/W2488460099","https://openalex.org/W4401743298","https://openalex.org/W852515486","https://openalex.org/W2384322858","https://openalex.org/W2366187940","https://openalex.org/W2364212620","https://openalex.org/W2352065077","https://openalex.org/W2527775010","https://openalex.org/W596831420"],"abstract_inverted_index":{"Early":[0],"and":[1,30,57,66,93,124,131,146,168,178],"precise":[2],"accident":[3,41,161],"anticipation":[4],"is":[5,82],"critical":[6],"for":[7,39],"preventing":[8],"road":[9],"traffic":[10,14,40,64],"incidents":[11],"in":[12,103,134,174],"advanced":[13],"systems.":[15],"This":[16,142],"paper":[17],"presents":[18],"a":[19,27,31,35,85,89,121,135],"Multi-modal":[20],"Architecture":[21],"with":[22,120],"Spatio-Temporal-Text":[23],"Adaptation":[24],"(MASTTA),":[25],"featuring":[26],"Visual":[28,78],"Encoder":[29,33],"Text":[32,117,122],"within":[34],"streamlined":[36],"end-to-end":[37],"framework":[38],"anticipation.":[42,162],"Both":[43],"encoders":[44],"leverage":[45],"the":[46,71,77,107,176],"CLIP":[47],"model,":[48],"pre-trained":[49],"on":[50,166],"large-scale":[51],"text-image":[52],"pairs,":[53],"to":[54,151,181],"utilize":[55],"visual":[56,114,132,147],"textual":[58,130],"information":[59],"effectively.":[60],"MASTTA":[61,150,165],"captures":[62,110],"complex":[63,153],"patterns":[65],"relationships":[67],"by":[68],"fine-tuning":[69],"only":[70],"adapters,":[72],"reducing":[73],"retraining":[74],"demands.":[75],"In":[76],"Encoder,":[79,118],"spatio-temporal":[80,111],"adaptation":[81],"achieved":[83],"through":[84],"novel":[86,90],"Temporal":[87,98],"Adapter,":[88,92,127],"Spatial":[91,108],"an":[94,125],"MLP":[95,126],"Adapter.":[96],"The":[97,116],"Adapter":[99,109,123],"enhances":[100],"temporal":[101,158],"consistency":[102],"accident-prone":[104],"areas,":[105],"while":[106],"interactions":[112,155],"among":[113],"cues.":[115],"equipped":[119],"aligns":[128],"latent":[129],"features":[133],"joint":[136],"embedding":[137],"space,":[138],"refining":[139],"semantic":[140],"representation.":[141],"synergy":[143],"of":[144],"text":[145],"adapters":[148],"enables":[149],"model":[152],"spatial":[154],"across":[156],"long-range":[157],"context,":[159],"improving":[160],"We":[163],"validate":[164],"DAD":[167],"CCD":[169],"datasets,":[170],"demonstrating":[171],"significant":[172],"improvements":[173],"both":[175],"earliness":[177],"correctness":[179],"compared":[180],"state-of-the-art":[182],"methods.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}