{"id":"https://openalex.org/W7131117128","doi":"https://doi.org/10.1109/iccvw69036.2025.00559","title":"TrafficInternVL: Spatially-Guided Fine-Tuning with Caption Refinement for Fine-Grained Traffic Safety Captioning and Visual Question Answering","display_name":"TrafficInternVL: Spatially-Guided Fine-Tuning with Caption Refinement for Fine-Grained Traffic Safety Captioning and Visual Question Answering","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131117128","doi":"https://doi.org/10.1109/iccvw69036.2025.00559"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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/A5049209997","display_name":"Sasin Phimsiri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sasin Phimsiri","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126636345","display_name":"Sarut Sunpawatr","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarut Sunpawatr","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099127064","display_name":"Riu Cherdchusakulchai","orcid":"https://orcid.org/0009-0008-7779-970X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Riu Cherdchusakulchai","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003927462","display_name":"Pornprom Kiawjak","orcid":null},"institutions":[{"id":"https://openalex.org/I91538806","display_name":"King Mongkut's Institute of Technology Ladkrabang","ror":"https://ror.org/055mf0v62","country_code":"TH","type":"education","lineage":["https://openalex.org/I91538806"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Pornprom Kiawjak","raw_affiliation_strings":["King Mongkut&#x0027;s Institute of Technology Ladkrabang"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Mongkut&#x0027;s Institute of Technology Ladkrabang","institution_ids":["https://openalex.org/I91538806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126612097","display_name":"Teepakorn Tosawadi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teepakorn Tosawadi","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024159147","display_name":"Suchat Tungjitnob","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suchat Tungjitnob","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074008883","display_name":"Visarut Trairattanapa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visarut Trairattanapa","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046907434","display_name":"Supawit Vatathanavaro","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Supawit Vatathanavaro","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083643995","display_name":"Wasu Kudisthalert","orcid":"https://orcid.org/0000-0003-3638-6673"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wasu Kudisthalert","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126619440","display_name":"Chaitat Utintu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitat Utintu","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126586569","display_name":"Worawit Saetan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Worawit Saetan","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126606839","display_name":"Nathamon Kongsawat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathamon Kongsawat","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107515575","display_name":"Phawat Borisuitsawat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phawat Borisuitsawat","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092785739","display_name":"Kasisdis Mahakijdechachai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kasisdis Mahakijdechachai","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126628910","display_name":"Nitipan Su-Inn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitipan Su-Inn","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001740152","display_name":"Ek Thamwiwatthana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ek Thamwiwatthana","raw_affiliation_strings":["AI and Robotics Ventures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Robotics Ventures","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035212955","display_name":"Vasin Suttichaya","orcid":null},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Vasin Suttichaya","raw_affiliation_strings":["Mahidol University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mahidol University","institution_ids":["https://openalex.org/I25399158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87967653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5358","last_page":"5365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9812999963760376,"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":0.9812999963760376,"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/T10028","display_name":"Topic Modeling","score":0.002199999988079071,"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/T11439","display_name":"Video Analysis and Summarization","score":0.0020000000949949026,"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/closed-captioning","display_name":"Closed captioning","score":0.858299970626831},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7839999794960022},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6068000197410583},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5532000064849854},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5144000053405762},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.384799987077713},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.37720000743865967}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.858299970626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892000079154968},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7839999794960022},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6068000197410583},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5414000153541565},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3833000063896179},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C2985695025","wikidata":"https://www.wikidata.org/wiki/Q4323994","display_name":"Road traffic","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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":16,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W3166608351","https://openalex.org/W4386066385","https://openalex.org/W4386088285","https://openalex.org/W4389519587","https://openalex.org/W4390662480","https://openalex.org/W4390873290","https://openalex.org/W4402671548","https://openalex.org/W4402713111","https://openalex.org/W4402727014","https://openalex.org/W4402904107","https://openalex.org/W4402916219","https://openalex.org/W4402916900","https://openalex.org/W4402917033","https://openalex.org/W7131078821"],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"traffic":[1,21],"understanding":[2],"requires":[3],"both":[4],"detailed":[5],"visual":[6,52],"descriptions":[7],"and":[8,24,44,57,75,95,104],"precise":[9],"answers":[10],"to":[11],"safety-critical":[12],"questions.":[13],"We":[14],"present":[15],"TrafficInternVl,":[16],"a":[17,85,96],"framework":[18],"for":[19,28,79],"fine-grained":[20],"safety":[22],"description":[23],"question":[25],"answering,":[26],"developed":[27],"AI":[29],"City":[30],"Challenge":[31],"2025":[32],"Track":[33],"2.":[34],"Our":[35,82],"approach":[36],"is":[37],"based":[38],"on":[39],"the":[40],"InternVL3-38B":[41],"vision-language":[42],"model":[43,73,83],"integrates":[45],"four":[46],"key":[47],"components:":[48],"(1)":[49],"spatially":[50],"guided":[51],"prompting":[53],"via":[54],"bounding-box-based":[55],"cropping":[56],"rendering;":[58],"(2)":[59],"Adaptive":[60],"view":[61],"selection":[62],"protocols;":[63],"(3)":[64],"low-rank":[65],"adaptation":[66],"(LoRA)":[67],"fine-tuning,":[68],"updating":[69],"only":[70],"1%":[71],"of":[72,88,99],"parameters;":[74],"(4)":[76],"caption":[77],"refinement":[78],"intra-scene":[80],"consistency.":[81],"achieves":[84],"Caption":[86],"Score":[87],"32.75":[89],"(BLEU-4,":[90],"METEOR,":[91],"ROUGE-L,":[92],"CIDEr":[93],"averaged)":[94],"VQA":[97],"accuracy":[98],"83.08":[100],"%.":[101],"Code,":[102],"prompts,":[103],"LoRA":[105],"weights":[106],"are":[107],"released":[108],"at":[109],"https://github.com/ARV-MLCORE/TrafficInternVL":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-24T00:00:00"}
