{"id":"https://openalex.org/W7136288508","doi":"https://doi.org/10.1109/itsc60802.2025.11423067","title":"Beyond Pixels: Vision-Language Models for Enhanced Street Environment Perception","display_name":"Beyond Pixels: Vision-Language Models for Enhanced Street Environment Perception","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W7136288508","doi":"https://doi.org/10.1109/itsc60802.2025.11423067"},"language":null,"primary_location":{"id":"doi:10.1109/itsc60802.2025.11423067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","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/A5129444310","display_name":"Wenyu Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenyu Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129507922","display_name":"Chonghao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chonghao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129554628","display_name":"Hao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129450815","display_name":"Xiao Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129465515","display_name":"Jinyi Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyi Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129580136","display_name":"Jialei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialei Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129478984","display_name":"Shuwen Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuwen Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"317","last_page":"322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.617900013923645,"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":0.617900013923645,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.054999999701976776,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.039000000804662704,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5320000052452087},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.36890000104904175},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3131999969482422},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.26429998874664307}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41499999165534973},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3587000072002411},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.26100000739097595},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc60802.2025.11423067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.5965271592140198,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1860531110","https://openalex.org/W1968147892","https://openalex.org/W2007027649","https://openalex.org/W2027808287","https://openalex.org/W2031043921","https://openalex.org/W2153975459","https://openalex.org/W2194775991","https://openalex.org/W2324134362","https://openalex.org/W2478090196","https://openalex.org/W2890231632","https://openalex.org/W2895762794","https://openalex.org/W2962764844","https://openalex.org/W4214763453","https://openalex.org/W4283590008","https://openalex.org/W4378575337","https://openalex.org/W4382138521","https://openalex.org/W4385245566","https://openalex.org/W4399529811","https://openalex.org/W4402716288","https://openalex.org/W7133231679"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,10,25,59,75,82,88,93,105],"continuous":[2],"development":[3],"of":[4,16,30,48,65,77,84,107,113],"smart":[5],"cities":[6],"and":[7,27,50,61,121,151,171],"human-oriented":[8],"transportation,":[9],"streets,":[11],"as":[12,43],"a":[13,21],"key":[14],"component":[15],"urban":[17,28,177],"public":[18],"space,":[19],"have":[20],"significant":[22],"impact":[23],"on":[24,37],"behavior":[26],"vitality":[29],"residents.":[31],"Traditional":[32],"street":[33,66,114,134],"perception":[34,63,68,136,149,166],"methods":[35],"based":[36],"semantic":[38],"segmentation":[39],"face":[40],"challenges":[41],"such":[42],"limited":[44],"semantics,":[45],"insufficient":[46],"understanding":[47],"relationships,":[49],"poor":[51],"task":[52],"adaptability":[53],"in":[54,110,176],"open-world":[55],"environments.":[56],"Therefore,":[57],"enhancing":[58,148],"accuracy":[60,150],"fine-grained":[62,133],"capabilities":[64],"environment":[67],"is":[69],"particularly":[70],"important.":[71],"This":[72],"study":[73],"proposes":[74],"introduction":[76],"Vision-Language":[78,108,128,157],"Models":[79,109,129,158],"to":[80,103,141],"overcome":[81],"limitations":[83],"traditional":[85],"frameworks.":[86],"Using":[87],"Qwen2.5-VL-72B-Instruct":[89],"model":[90],"combined":[91],"with":[92],"MIT":[94],"Place":[95],"Pulse":[96],"2.0":[97],"Dataset,":[98],"experiments":[99],"were":[100],"carried":[101],"out":[102],"verify":[104],"superiority":[106],"six":[111],"dimensions":[112],"perception:":[115],"safe,":[116],"lively,":[117],"clean,":[118],"wealthy,":[119],"depressing":[120],"beautiful.":[122],"The":[123],"research":[124],"results":[125],"indicate":[126],"that":[127],"not":[130],"only":[131],"enables":[132],"space":[135,178],"but":[137],"also":[138],"flexibly":[139],"adapts":[140],"various":[142],"tasks":[143],"through":[144,160],"prompt-based":[145],"approaches,":[146],"further":[147],"personalization.":[152],"Future":[153],"work":[154],"can":[155],"optimize":[156],"performance":[159],"low-parameter":[161],"fine-tuning":[162],"(e.g.,":[163],"LoRA),":[164],"improve":[165],"speed,":[167],"reduce":[168],"computational":[169],"consumption,":[170],"thus":[172],"promote":[173],"its":[174],"application":[175],"perception.":[179]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-17T00:00:00"}