{"id":"https://openalex.org/W7160283105","doi":"https://doi.org/10.1109/wacv61042.2026.00703","title":"Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs","display_name":"Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160283105","doi":"https://doi.org/10.1109/wacv61042.2026.00703"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5093703605","display_name":"Sainithin Artham","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sainithin Artham","raw_affiliation_strings":["IIIT Hyderabad,CVIT,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,CVIT,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135309406","display_name":"Avijit Dasgupta","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avijit Dasgupta","raw_affiliation_strings":["IIIT Hyderabad,CVIT,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,CVIT,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082105653","display_name":"Shankar Gangisetty","orcid":"https://orcid.org/0000-0003-4448-5794"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shankar Gangisetty","raw_affiliation_strings":["IIIT Hyderabad,CVIT,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,CVIT,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064321215","display_name":"C V Jawahar","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. V. Jawahar","raw_affiliation_strings":["IIIT Hyderabad,CVIT,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,CVIT,India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65229826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7281","last_page":"7290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.12020000070333481,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.12020000070333481,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.07339999824762344,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T11373","display_name":"Sleep and Work-Related Fatigue","score":0.0658000037074089,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.27239999175071716},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2662000060081482},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.26170000433921814},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.25540000200271606},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2515000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5662000179290771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25060001015663147},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2401999980211258}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1789187189","https://openalex.org/W2963692464","https://openalex.org/W2970069713","https://openalex.org/W3036171677","https://openalex.org/W3095753995","https://openalex.org/W3117025268","https://openalex.org/W3170224286","https://openalex.org/W4291184140","https://openalex.org/W4383097607","https://openalex.org/W4389519587","https://openalex.org/W4390889756","https://openalex.org/W4391770362","https://openalex.org/W4393148430","https://openalex.org/W4394625870","https://openalex.org/W4394862623","https://openalex.org/W4394862786","https://openalex.org/W4403842289","https://openalex.org/W4403843558","https://openalex.org/W4403906537","https://openalex.org/W4404654684","https://openalex.org/W4404820176","https://openalex.org/W4404970806","https://openalex.org/W4409264011","https://openalex.org/W4413145425","https://openalex.org/W4413145476","https://openalex.org/W4413157780","https://openalex.org/W4415798317","https://openalex.org/W7133193597"],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"a":[1,9,53,91,186],"drivers\u2019":[2],"intent":[3],"(e.g.,":[4],"turns,":[5],"lane":[6],"changes)":[7],"is":[8],"critical":[10],"capability":[11],"for":[12,42,188],"modern":[13],"Advanced":[14],"Driver":[15,43],"Assistance":[16],"Systems":[17],"(ADAS).":[18],"While":[19],"recent":[20],"Multimodal":[21],"Large":[22],"Language":[23],"Models":[24],"(MLLMs)":[25],"show":[26,104],"promise":[27],"in":[28,162,180,195],"general":[29],"vision-language":[30],"tasks,":[31],"we":[32,50],"find":[33],"that":[34,59,105,156],"zero-shot":[35,54,166],"MLLMs":[36,58],"still":[37],"lag":[38],"behind":[39],"domain-specific":[40,168],"approaches":[41],"Intention":[44],"Prediction":[45],"(DIP).":[46],"To":[47],"address":[48],"this,":[49],"introduce":[51],"DriveXplain,":[52],"framework":[55],"based":[56],"on":[57,118],"leverages":[60],"rich":[61,79],"visual":[62],"cues":[63],"such":[64],"as":[65,120],"optical":[66],"flow":[67],"and":[68,78,100,151,167,191],"road":[69],"semantics":[70],"to":[71,97,111,130,136,175],"automatically":[72],"generate":[73],"both":[74],"intention":[75,193],"maneuver":[76],"(what)":[77],"natural":[80],"language":[81],"explanations":[82,107,122],"(why).":[83],"These":[84],"maneuver\u2013explanation":[85],"pairs":[86],"are":[87,143],"then":[88],"distilled":[89],"into":[90],"compact":[92],"MLLM,":[93],"which":[94],"jointly":[95],"learns":[96],"predict":[98],"intentions":[99],"corresponding":[101],"explanations.":[102],"We":[103,170],"incorporating":[106],"during":[108],"training":[109],"leads":[110],"substantial":[112],"gains":[113],"over":[114],"models":[115],"trained":[116],"solely":[117],"labels,":[119],"distilling":[121],"instills":[123],"reasoning":[124],"capabilities":[125],"by":[126],"enabling":[127],"the":[128],"model":[129],"understand":[131],"not":[132],"only":[133],"what":[134],"decisions":[135,142],"make":[137],"but":[138],"also":[139,171],"why":[140],"those":[141],"made.":[144],"Comprehensive":[145],"experiments":[146],"across":[147],"structured":[148],"(Brain4Cars,":[149],"AIDE)":[150],"unstructured":[152],"(DAAD)":[153],"datasets":[154],"demonstrate":[155],"our":[157,181],"approach":[158],"achieves":[159],"state-of-the-art":[160],"results":[161],"DIP":[163],"task,":[164],"outperforming":[165],"baselines.":[169],"present":[172],"ablation":[173],"studies":[174],"evaluate":[176],"key":[177],"design":[178],"choices":[179],"framework.":[182],"This":[183],"work":[184],"sets":[185],"direction":[187],"more":[189],"explainable":[190],"generalizable":[192],"prediction":[194],"autonomous":[196],"driving":[197],"systems.":[198],"Project":[199],"webpage:":[200],"https://avijit9.github.io/DriveXplain/":[201]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}