{"id":"https://openalex.org/W4408355887","doi":"https://doi.org/10.1109/icassp49660.2025.10889912","title":"VP-YOLO: Robust Vehicle-Pedestrian Detection in Challenging Traffic Scenarios via A Human Visual Perception-Inspired Network","display_name":"VP-YOLO: Robust Vehicle-Pedestrian Detection in Challenging Traffic Scenarios via A Human Visual Perception-Inspired Network","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355887","doi":"https://doi.org/10.1109/icassp49660.2025.10889912"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100330670","display_name":"Wenbo Liu","orcid":"https://orcid.org/0000-0001-5058-8672"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Liu","raw_affiliation_strings":["Southwest Jiaotong University,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,Chengdu,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031400194","display_name":"Tao Deng","orcid":"https://orcid.org/0000-0001-5094-5879"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Deng","raw_affiliation_strings":["Southwest Jiaotong University,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,Chengdu,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101554660","display_name":"Fei Yan","orcid":"https://orcid.org/0000-0001-5177-4493"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yan","raw_affiliation_strings":["Southwest Jiaotong University,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,Chengdu,China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4800084"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9979000091552734,"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":0.9965000152587891,"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/pedestrian","display_name":"Pedestrian","score":0.7434026002883911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7337095737457275},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6188812255859375},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.6024051904678345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5408127903938293},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5363131165504456},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34725886583328247},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.14442825317382812},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13437360525131226},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09196346998214722},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06444790959358215}],"concepts":[{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.7434026002883911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337095737457275},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6188812255859375},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.6024051904678345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5408127903938293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5363131165504456},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34725886583328247},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.14442825317382812},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13437360525131226},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09196346998214722},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06444790959358215}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2138040059","https://openalex.org/W2150066425","https://openalex.org/W2340897893","https://openalex.org/W2795812085","https://openalex.org/W2912512021","https://openalex.org/W3034403122","https://openalex.org/W3206023204","https://openalex.org/W3210586215","https://openalex.org/W4287882618","https://openalex.org/W4313591362","https://openalex.org/W4317796687","https://openalex.org/W4386071462","https://openalex.org/W4386076325","https://openalex.org/W4388543960","https://openalex.org/W4403770406","https://openalex.org/W6620707391","https://openalex.org/W6750227808","https://openalex.org/W6798838024","https://openalex.org/W6802960164","https://openalex.org/W6846002001","https://openalex.org/W6849995042","https://openalex.org/W6868582632"],"related_works":["https://openalex.org/W2392100589","https://openalex.org/W2512789322","https://openalex.org/W3122828758","https://openalex.org/W2101960027","https://openalex.org/W4205958986","https://openalex.org/W2197846993","https://openalex.org/W49697837","https://openalex.org/W2586575957","https://openalex.org/W2972620127","https://openalex.org/W2981141433"],"abstract_inverted_index":{"Intelligent":[0],"vehicles":[1,19,34],"need":[2],"to":[3,41,101,107,162],"provide":[4],"rational":[5],"driving":[6,10,14,39],"strategies":[7],"for":[8,37],"assisted":[9],"systems":[11,40],"based":[12],"on":[13,95,180],"scenarios.":[15,201],"Since":[16],"pedestrians":[17,32],"and":[18,29,33,51,60,68,91,93,132,136,141,170,184,187],"are":[20,35],"the":[21,103,146,167,172,181,188],"main":[22],"players":[23],"in":[24,45,65,166,198],"these":[25,108],"scenarios,":[26],"accurate":[27],"detection":[28,53],"localization":[30],"of":[31],"crucial":[36],"intelligent":[38],"make":[42,102],"reliable":[43],"decisions":[44],"dynamic":[46,59],"environments.":[47],"However,":[48],"existing":[49],"pedestrian":[50],"vehicle":[52],"models":[54],"often":[55],"lack":[56],"robustness":[57],"under":[58],"complex":[61,82],"traffic":[62,83],"conditions,":[63],"resulting":[64],"missed":[66],"detections":[67],"false":[69],"alarms,":[70],"which":[71],"pose":[72],"significant":[73],"safety":[74],"risks.":[75],"To":[76],"address":[77],"this":[78,111],"problem,":[79],"we":[80,119,155],"categorize":[81],"scenarios":[84],"into":[85],"three":[86],"typical":[87],"challenges:":[88],"long-distance,":[89],"truncation,":[90],"occlusion,":[92],"focus":[94],"designing":[96],"a":[97,121,157],"novel":[98],"enhancement":[99,112],"stage":[100],"model":[104],"more":[105],"robust":[106],"challenges.":[109],"In":[110],"stage,":[113],"inspired":[114],"by":[115,150],"human":[116],"visual":[117],"perception,":[118],"design":[120],"Visual":[122],"Attention":[123],"Module":[124,160],"(VAM).":[125],"This":[126],"module":[127],"can":[128],"gather":[129],"high-quality":[130],"horizontal":[131,140],"vertical":[133,142],"spatial":[134,143],"features":[135],"efficiently":[137],"interact":[138],"between":[139],"features,":[144],"enhancing":[145],"model\u2019s":[147,173],"perceptual":[148],"ability":[149],"mimicking":[151],"optic":[152],"chiasm.":[153],"Additionally,":[154],"use":[156],"Feature":[158],"Reconstruction":[159],"(FRM)":[161],"reduce":[163],"redundant":[164],"information":[165],"feature":[168],"maps":[169],"enhance":[171],"inference":[174],"ability.":[175],"We":[176],"conduct":[177],"comprehensive":[178],"experiments":[179],"KITTI":[182],"benchmark":[183],"Cityscapes":[185],"dataset,":[186],"experimental":[189],"results":[190],"demonstrate":[191],"that":[192],"our":[193],"algorithm":[194],"achieves":[195],"state-of-the-art":[196],"performance":[197],"various":[199],"challenging":[200]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}