{"id":"https://openalex.org/W4402915572","doi":"https://doi.org/10.1109/icip51287.2024.10647358","title":"Scene Generalized Multi-View Pedestrian Detection with Rotation-Based Augmentation and Regularization","display_name":"Scene Generalized Multi-View Pedestrian Detection with Rotation-Based Augmentation and Regularization","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915572","doi":"https://doi.org/10.1109/icip51287.2024.10647358"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","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/A5027868267","display_name":"Satoshi Suzuki","orcid":"https://orcid.org/0000-0001-5343-4660"},"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":true,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050560752","display_name":"Shotaro Tora","orcid":null},"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":"Shotaro Tora","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"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":"Ryo Masumura","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027868267"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.4922,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6499176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"596","last_page":"602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9894000291824341,"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/T13282","display_name":"Automated Road and Building Extraction","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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-detection","display_name":"Pedestrian detection","score":0.6925473213195801},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.6766998171806335},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6466472148895264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6180809736251831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5761095285415649},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4937046468257904},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.4713665246963501},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3406762480735779},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11337310075759888}],"concepts":[{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.6925473213195801},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.6766998171806335},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6466472148895264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6180809736251831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5761095285415649},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4937046468257904},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.4713665246963501},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3406762480735779},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11337310075759888},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1650122911","https://openalex.org/W2108598243","https://openalex.org/W2158634074","https://openalex.org/W2194775991","https://openalex.org/W2475287302","https://openalex.org/W2583638424","https://openalex.org/W2588287671","https://openalex.org/W2799108620","https://openalex.org/W2962850098","https://openalex.org/W2962850830","https://openalex.org/W2963859909","https://openalex.org/W3107147550","https://openalex.org/W3202890594","https://openalex.org/W3207737630","https://openalex.org/W4312417027","https://openalex.org/W4319300102","https://openalex.org/W4319336168","https://openalex.org/W4394625853","https://openalex.org/W6749845547"],"related_works":["https://openalex.org/W2392100589","https://openalex.org/W2512789322","https://openalex.org/W2101960027","https://openalex.org/W2197846993","https://openalex.org/W49697837","https://openalex.org/W2586575957","https://openalex.org/W3122828758","https://openalex.org/W2170799233","https://openalex.org/W2972620127","https://openalex.org/W2981141433"],"abstract_inverted_index":{"Multi-view":[0],"pedestrian":[1,104],"detection":[2,136],"aims":[3],"to":[4,51,53,65,82,84,119,132,147,165],"predict":[5],"a":[6,46,95,125],"bird\u2019s":[7],"eye":[8],"view":[9],"(BEV)":[10],"occupancy":[11],"map":[12],"using":[13],"multiple":[14,59],"camera":[15,39],"views.":[16],"While":[17],"existing":[18,159],"deep":[19],"learning-based":[20],"methods":[21,160],"have":[22],"shown":[23],"progress,":[24],"they":[25,48],"are":[26,49],"typically":[27],"trained":[28],"and":[29,41,99,144],"tested":[30],"on":[31,76],"the":[32,37,74,85,116,121,135,139],"same":[33,38],"scene,":[34],"which":[35],"has":[36,61],"layout":[40],"number":[42],"of":[43,109,141,163],"cameras.":[44],"As":[45],"result,":[47],"difficult":[50],"generalize":[52],"new":[54,77,126,142,166],"scenes.":[55,88,167],"A":[56],"dataset":[57],"containing":[58],"scenes":[60,78,143,149],"recently":[62],"been":[63],"proposed":[64],"overcome":[66],"this":[67,72,91],"limitation,":[68],"but":[69],"even":[70],"with":[71,138],"dataset,":[73],"performance":[75],"remains":[79],"poor":[80],"due":[81],"overfitting":[83,146],"limited":[86],"training":[87],"To":[89],"address":[90],"problem,":[92],"we":[93],"propose":[94],"novel":[96],"data":[97],"augmentation":[98],"regularization":[100],"method":[101,111,131,157],"for":[102],"multi-view":[103],"detection.":[105],"The":[106],"unique":[107],"point":[108],"our":[110,130,156],"is":[112],"that":[113,155],"it":[114],"rotates":[115],"BEV":[117],"features":[118,122],"generate":[120],"originating":[123],"from":[124],"scene.":[127],"This":[128],"enables":[129],"effectively":[133],"train":[134],"model":[137],"knowledge":[140],"prevent":[145],"specific":[148],"through":[150],"regularization.":[151],"Experimental":[152],"results":[153],"show":[154],"outperforms":[158],"in":[161],"terms":[162],"generalization":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}