{"id":"https://openalex.org/W3196099359","doi":"https://doi.org/10.23919/mva51890.2021.9511366","title":"Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU","display_name":"Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU","publication_year":2021,"publication_date":"2021-07-25","ids":{"openalex":"https://openalex.org/W3196099359","doi":"https://doi.org/10.23919/mva51890.2021.9511366","mag":"3196099359"},"language":"en","primary_location":{"id":"doi:10.23919/mva51890.2021.9511366","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva51890.2021.9511366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Machine Vision and Applications (MVA)","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/A5078056050","display_name":"Napat Wanchaitanawong","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Napat Wanchaitanawong","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040292386","display_name":"Masayuki Tanaka","orcid":"https://orcid.org/0000-0002-5756-1904"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Tanaka","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010157078","display_name":"Takashi Shibata","orcid":"https://orcid.org/0000-0001-8072-3847"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Shibata","raw_affiliation_strings":["NTT Corporation, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024453747","display_name":"Masatoshi Okutomi","orcid":"https://orcid.org/0000-0001-5787-0742"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatoshi Okutomi","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9983000159263611,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9977999925613403,"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/modal","display_name":"Modal","score":0.8532660603523254},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7652462720870972},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7570347785949707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7479594945907593},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.6786292195320129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5740373134613037},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.49840307235717773},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4870017170906067},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3986976742744446},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3704008460044861},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3586443364620209},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34958523511886597},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18271586298942566},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13400021195411682}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8532660603523254},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7652462720870972},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7570347785949707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479594945907593},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.6786292195320129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740373134613037},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.49840307235717773},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4870017170906067},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3986976742744446},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3704008460044861},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3586443364620209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34958523511886597},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18271586298942566},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13400021195411682},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mva51890.2021.9511366","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva51890.2021.9511366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W345900524","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1910108985","https://openalex.org/W1926022583","https://openalex.org/W2031454541","https://openalex.org/W2108598243","https://openalex.org/W2116702374","https://openalex.org/W2125556102","https://openalex.org/W2163605009","https://openalex.org/W2415234561","https://openalex.org/W2497039038","https://openalex.org/W2549063375","https://openalex.org/W2608096492","https://openalex.org/W2608295741","https://openalex.org/W2610365247","https://openalex.org/W2613599172","https://openalex.org/W2613718673","https://openalex.org/W2741160171","https://openalex.org/W2741620214","https://openalex.org/W2776732561","https://openalex.org/W2789621390","https://openalex.org/W2792925809","https://openalex.org/W2883363148","https://openalex.org/W2885652903","https://openalex.org/W2887564556","https://openalex.org/W2902314041","https://openalex.org/W2929607865","https://openalex.org/W2951242024","https://openalex.org/W2962835968","https://openalex.org/W2963150697","https://openalex.org/W2963188557","https://openalex.org/W2963315052","https://openalex.org/W2963579094","https://openalex.org/W2964027659","https://openalex.org/W2987131085","https://openalex.org/W3116967329","https://openalex.org/W3118570274","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6640132086","https://openalex.org/W6684191040","https://openalex.org/W6736851953","https://openalex.org/W6753836424","https://openalex.org/W6756834165","https://openalex.org/W6781859543","https://openalex.org/W6787615902"],"related_works":["https://openalex.org/W2392812199","https://openalex.org/W4200176076","https://openalex.org/W598185802","https://openalex.org/W2355516524","https://openalex.org/W2361471170","https://openalex.org/W2025616642","https://openalex.org/W1954972543","https://openalex.org/W2954738200","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"The":[0,24,105],"combined":[1],"use":[2,30],"of":[3,62,87,167],"multiple":[4],"modalities":[5,22],"enables":[6],"accurate":[7],"pedestrian":[8],"detection":[9,79],"under":[10],"poor":[11],"lighting":[12],"conditions":[13],"by":[14],"using":[15],"the":[16,28,42,60,63,70,85,130,150,158,168],"high":[17],"visibility":[18],"areas":[19],"from":[20],"these":[21],"together.":[23],"vital":[25],"assumption":[26,49],"for":[27,115,128,152,171],"combination":[29],"is":[31,34,89,100,162],"that":[32,99,148,157,166],"there":[33],"no":[35],"or":[36],"only":[37],"a":[38,75,96,140],"weak":[39],"misalignment":[40,88,175],"between":[41,69],"two":[43,71],"modalities.":[44,136,154],"In":[45,91],"general,":[46],"however,":[47],"this":[48,57,92],"often":[50],"breaks":[51],"in":[52,74,78,82],"actual":[53,177],"situations.":[54],"Due":[55],"to":[56],"assumption's":[58],"breakdown,":[59],"position":[61],"bounding":[64,125],"boxes":[65],"does":[66],"not":[67],"match":[68],"modalities,":[72],"resulting":[73],"significant":[76],"decrease":[77],"accuracy,":[80],"especially":[81],"regions":[83],"where":[84],"amount":[86],"large.":[90],"paper,":[93],"we":[94,123],"propose":[95,139],"multimodal":[97],"Faster-RCNN":[98],"robust":[101],"against":[102],"large":[103,121,174],"misalignment.":[104],"keys":[106],"are":[107],"1)":[108],"modal-wise":[109],"regression":[110,127],"and":[111,132],"2)":[112],"multi-modal":[113],"IoU":[114,151],"mini-batch":[116,146],"sampling.":[117],"To":[118],"deal":[119],"with":[120,134,173],"misalignment,":[122],"perform":[124],"box":[126],"both":[129,135,153],"RPN":[131],"detection-head":[133],"We":[137,155],"also":[138],"new":[141],"sampling":[142],"strategy":[143],"called":[144],"\u201cmulti-modal":[145],"sampling\u201d":[147],"integrates":[149],"demonstrate":[156],"proposed":[159],"method's":[160],"performance":[161],"much":[163],"better":[164],"than":[165],"state-of-the-art":[169],"methods":[170],"data":[172],"through":[176],"image":[178],"experiments.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}