{"id":"https://openalex.org/W4416750512","doi":"https://doi.org/10.1109/iros60139.2025.11245662","title":"DriveBLIP2: Attention-Guided Explanation Generation for Complex Driving Scenarios","display_name":"DriveBLIP2: Attention-Guided Explanation Generation for Complex Driving Scenarios","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750512","doi":"https://doi.org/10.1109/iros60139.2025.11245662"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5000468775","display_name":"Shihong Ling","orcid":"https://orcid.org/0009-0008-1414-2436"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shihong Ling","raw_affiliation_strings":["University of Pittsburgh,School of Computing and Information,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,School of Computing and Information,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Wan","raw_affiliation_strings":["University of Pittsburgh,School of Computing and Information,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,School of Computing and Information,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaowei Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaowei Jia","raw_affiliation_strings":["University of Pittsburgh,School of Computing and Information,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,School of Computing and Information,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027093356","display_name":"Na Du","orcid":"https://orcid.org/0000-0002-4383-2451"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Na Du","raw_affiliation_strings":["University of Pittsburgh,School of Computing and Information,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,School of Computing and Information,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20662","last_page":"20668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7348999977111816,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7348999977111816,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15279999375343323,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.025200000032782555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6732000112533569},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6498000025749207},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5979999899864197},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5419999957084656},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42260000109672546}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6732000112533569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65420001745224},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6498000025749207},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4375},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.41519999504089355},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2506483933","https://openalex.org/W2945976633","https://openalex.org/W2946112597","https://openalex.org/W2963341956","https://openalex.org/W2970603850","https://openalex.org/W4319300501","https://openalex.org/W4389519587","https://openalex.org/W4401386967","https://openalex.org/W4401414574","https://openalex.org/W4401416408","https://openalex.org/W4402671847","https://openalex.org/W4408696909"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3],"new":[4],"framework,":[5],"Drive-Blip2,":[6],"built":[7],"upon":[8],"the":[9,49,81,88,103,112,138],"BLIP2-OPT":[10],"architecture,":[11],"to":[12,67,72,84,100,132],"generate":[13],"accurate":[14],"and":[15,95,128],"contextually":[16],"relevant":[17,71,96],"explanations":[18],"for":[19,147],"emerging":[20],"driving":[21,73],"scenarios.":[22],"While":[23],"existing":[24],"vision-language":[25,145],"models":[26,146],"perform":[27],"well":[28],"in":[29,35,41,107,118,144,150],"general":[30],"tasks,":[31],"they":[32],"encounter":[33],"difficulties":[34],"understanding":[36],"complex,":[37],"multi-object":[38],"environments,":[39],"particularly":[40],"real-time":[42,151],"applications":[43],"such":[44],"as":[45,121],"autonomous":[46,152],"driving,":[47],"where":[48],"rapid":[50],"identification":[51],"of":[52,140],"key":[53,86],"objects":[54,70],"is":[55,65],"crucial.":[56],"To":[57],"address":[58],"this":[59],"limitation,":[60],"an":[61],"Attention":[62],"Map":[63],"Generator":[64],"proposed":[66],"highlight":[68],"significant":[69,116],"decisions":[74],"within":[75],"critical":[76,108],"video":[77],"frames.":[78],"By":[79],"directing":[80],"model\u2019s":[82],"focus":[83],"these":[85],"regions,":[87],"generated":[89],"attention":[90,142],"map":[91],"helps":[92],"produce":[93],"clear":[94],"explanations,":[97],"enabling":[98],"drivers":[99],"better":[101],"understand":[102],"vehicle\u2019s":[104],"decision-making":[105],"process":[106],"situations.":[109],"Evaluations":[110],"on":[111],"DRAMA":[113],"dataset":[114],"reveal":[115],"improvements":[117],"explanation":[119],"quality,":[120],"indicated":[122],"by":[123],"higher":[124],"BLEU,":[125],"ROUGE,":[126],"CIDEr,":[127],"SPICE":[129],"scores":[130],"compared":[131],"baseline":[133],"models.":[134],"These":[135],"findings":[136],"underscore":[137],"potential":[139],"targeted":[141],"mechanisms":[143],"enhancing":[148],"explainability":[149],"driving.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}