{"id":"https://openalex.org/W4385488723","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191714","title":"Scene Understanding for Autonomous Driving Using Visual Question Answering","display_name":"Scene Understanding for Autonomous Driving Using Visual Question Answering","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488723","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191714"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5092582466","display_name":"Adrien Wantiez","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adrien Wantiez","raw_affiliation_strings":["Technical University of Munich,Munich,Germany","Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027090002","display_name":"Tianming Qiu","orcid":"https://orcid.org/0000-0003-1089-4717"},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tianming Qiu","raw_affiliation_strings":["fortiss GmbH,Munich,Germany","fortiss GmbH, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"fortiss GmbH,Munich,Germany","institution_ids":["https://openalex.org/I4210134795"]},{"raw_affiliation_string":"fortiss GmbH, Munich, Germany","institution_ids":["https://openalex.org/I4210134795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062517375","display_name":"Stefan Matthes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Matthes","raw_affiliation_strings":["fortiss GmbH,Munich,Germany","fortiss GmbH, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"fortiss GmbH,Munich,Germany","institution_ids":["https://openalex.org/I4210134795"]},{"raw_affiliation_string":"fortiss GmbH, Munich, Germany","institution_ids":["https://openalex.org/I4210134795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101759953","display_name":"Hao Shen","orcid":"https://orcid.org/0000-0003-0091-4155"},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hao Shen","raw_affiliation_strings":["fortiss GmbH,Munich,Germany","fortiss GmbH, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"fortiss GmbH,Munich,Germany","institution_ids":["https://openalex.org/I4210134795"]},{"raw_affiliation_string":"fortiss GmbH, Munich, Germany","institution_ids":["https://openalex.org/I4210134795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4855,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71759736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9940999746322632,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8603639602661133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367541790008545},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.7139861583709717},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7050321102142334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5906623005867004},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5604753494262695},{"id":"https://openalex.org/keywords/argument","display_name":"Argument (complex analysis)","score":0.5290438532829285},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5168285965919495},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5100205540657043},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45391517877578735},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3848660886287689},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37035393714904785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3553061783313751},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07636496424674988}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8603639602661133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367541790008545},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.7139861583709717},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7050321102142334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906623005867004},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5604753494262695},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.5290438532829285},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5168285965919495},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5100205540657043},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45391517877578735},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3848660886287689},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37035393714904785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3553061783313751},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07636496424674988},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323803","display_name":"Bundesministerium f\u00fcr Wirtschaft und Energie","ror":"https://ror.org/02vgg2808"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W1923162067","https://openalex.org/W1933349210","https://openalex.org/W2161002933","https://openalex.org/W2186283982","https://openalex.org/W2560730294","https://openalex.org/W2748815144","https://openalex.org/W2807331483","https://openalex.org/W2885138528","https://openalex.org/W2890443367","https://openalex.org/W2896457183","https://openalex.org/W2948947170","https://openalex.org/W2962896653","https://openalex.org/W2963150697","https://openalex.org/W2963890019","https://openalex.org/W2970231061","https://openalex.org/W2971278627","https://openalex.org/W2972324944","https://openalex.org/W3035292170","https://openalex.org/W3046756688","https://openalex.org/W3091678670","https://openalex.org/W3109643012","https://openalex.org/W3171841353","https://openalex.org/W4212951146","https://openalex.org/W4298392976","https://openalex.org/W4385245566","https://openalex.org/W4386065742","https://openalex.org/W6637131181","https://openalex.org/W6640071036","https://openalex.org/W6682086655","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763000687","https://openalex.org/W6763480078","https://openalex.org/W6846777640"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4381058564","https://openalex.org/W4283822356","https://openalex.org/W1950940422","https://openalex.org/W2964413124","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W2147282173"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,33,48,63,77,82,115,120,124,131,134,145,149,153,157,169],"feasibility":[4],"of":[5,29,37,50,62,89,97,136,142,161,171],"dot-products":[6,126],"present":[7,73],"in":[8,133],"self-attention":[9,125],"mechanisms":[10],"as":[11],"an":[12,164],"explainability":[13],"technique":[14],"for":[15,47,76,144,152,168],"autonomous":[16,175],"driving.":[17,176],"A":[18],"Visual":[19],"Question":[20],"Answering":[21],"(VQA)":[22],"framework":[23],"is":[24,166],"implemented":[25],"with":[26,86],"three":[27],"types":[28],"questions":[30,132],"pertaining":[31],"to":[32,130,174],"presence":[34],"or":[35],"absence":[36],"road":[38],"signs":[39],"and":[40,52,58,91,94,99,110,148,159],"traffic":[41],"lights.":[42],"The":[43,140],"models":[44],"are":[45],"evaluated":[46],"encoding":[49],"uni-":[51],"multimodal":[53],"encodings:":[54],"a":[55,59,137],"standard":[56],"version":[57,61],"modified":[60],"Learning":[64],"Cross-Modality":[65],"Encoder":[66],"Representations":[67],"from":[68],"Transformers":[69],"(LXMERT)":[70],"framework.":[71],"We":[72],"numerical":[74],"results":[75],"two":[78],"model":[79,121],"architectures":[80],"on":[81,114],"question":[83],"answering":[84],"task,":[85],"overall":[87,95],"accuracies":[88],"79.7%":[90],"78.5%":[92],"respectively,":[93],"F1-scores":[96],"0.749":[98],"0.693":[100],"respectively.":[101],"Moreover,":[102],"we":[103],"show":[104],"that":[105,123],"these":[106],"questions,":[107],"despite":[108],"containing":[109],"asking":[111],"no":[112],"information":[113],"objects'":[116],"positions,":[117],"indirectly":[118],"tune":[119],"such":[122],"provide":[127],"scenic":[128],"understanding":[129],"form":[135],"visual":[138,154],"map.":[139],"choice":[141],"pooling":[143],"model's":[146],"output":[147],"plotting":[150],"parameters":[151],"maps":[155],"influence":[156],"reliability":[158],"accuracy":[160],"visualization.":[162],"Finally,":[163],"argument":[165],"made":[167],"benefit":[170],"this":[172],"approach":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}