{"id":"https://openalex.org/W4385767699","doi":"https://doi.org/10.24963/ijcai.2023/149","title":"ViT-P3DE\u2217: Vision Transformer Based Multi-Camera Instance Association with Pseudo 3D Position Embeddings","display_name":"ViT-P3DE\u2217: Vision Transformer Based Multi-Camera Instance Association with Pseudo 3D Position Embeddings","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767699","doi":"https://doi.org/10.24963/ijcai.2023/149"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/149","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/149","pdf_url":"https://www.ijcai.org/proceedings/2023/0149.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0149.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102025104","display_name":"Minseok Seo","orcid":"https://orcid.org/0000-0003-3648-5575"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minseok Seo","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University","Inter-University Semiconductor Research Center (ISRC)","Inter-University Semiconductor Research Center (ISRC) Department of Electrical and Computer Engineering, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Inter-University Semiconductor Research Center (ISRC)","institution_ids":[]},{"raw_affiliation_string":"Inter-University Semiconductor Research Center (ISRC) Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024723558","display_name":"Hyuk\u2010Jae Lee","orcid":"https://orcid.org/0000-0001-6811-9647"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyuk-Jae Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University","Inter-University Semiconductor Research Center (ISRC)","Inter-University Semiconductor Research Center (ISRC) Department of Electrical and Computer Engineering, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Inter-University Semiconductor Research Center (ISRC)","institution_ids":[]},{"raw_affiliation_string":"Inter-University Semiconductor Research Center (ISRC) Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014900695","display_name":"Xuan Truong Nguyen","orcid":"https://orcid.org/0000-0002-7527-6971"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Xuan Truong Nguyen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University","Inter-University Semiconductor Research Center (ISRC)","Inter-University Semiconductor Research Center (ISRC) Department of Electrical and Computer Engineering, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Inter-University Semiconductor Research Center (ISRC)","institution_ids":[]},{"raw_affiliation_string":"Inter-University Semiconductor Research Center (ISRC) Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024723558"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1340","last_page":"1350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/computer-science","display_name":"Computer science","score":0.721657395362854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7090466618537903},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6664407849311829},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6281741857528687},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5903947949409485},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47577181458473206},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4655856192111969},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4412387013435364},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4297787547111511},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.42659032344818115},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4157909154891968},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4094218611717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.721657395362854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7090466618537903},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6664407849311829},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6281741857528687},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5903947949409485},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47577181458473206},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4655856192111969},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4412387013435364},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4297787547111511},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.42659032344818115},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4157909154891968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4094218611717224},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/149","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/149","pdf_url":"https://www.ijcai.org/proceedings/2023/0149.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/149","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/149","pdf_url":"https://www.ijcai.org/proceedings/2023/0149.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G6260389816","display_name":null,"funder_award_id":"IITP-2023-2020-0-01461","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8040526782","display_name":null,"funder_award_id":"IITP-2023-2020-0-01461","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767699.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W176069360","https://openalex.org/W1522301498","https://openalex.org/W1869500417","https://openalex.org/W1929856797","https://openalex.org/W1955055330","https://openalex.org/W2058536148","https://openalex.org/W2194775991","https://openalex.org/W2746791238","https://openalex.org/W2799108620","https://openalex.org/W2962858109","https://openalex.org/W2991133498","https://openalex.org/W3091905774","https://openalex.org/W3094502228","https://openalex.org/W3099206234","https://openalex.org/W3109747200","https://openalex.org/W3118212025","https://openalex.org/W3138516171","https://openalex.org/W3139434170","https://openalex.org/W3164024107","https://openalex.org/W3170874841","https://openalex.org/W4214891830","https://openalex.org/W4239072543","https://openalex.org/W4287022992","https://openalex.org/W4287330514","https://openalex.org/W4310659231","https://openalex.org/W4353103813","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147"],"abstract_inverted_index":{"Multi-camera":[0],"instance":[1],"association,":[2],"which":[3,93],"identifies":[4],"identical":[5],"objects":[6,9],"among":[7],"multiple":[8],"in":[10,88,113,133],"multi-view":[11],"images,":[12],"is":[13,94],"challenging":[14],"due":[15],"to":[16,66,127,161],"several":[17],"harsh":[18,37,98,193],"constraints.":[19,38,99,194],"To":[20,100],"tackle":[21],"this":[22],"problem,":[23],"most":[24],"studies":[25],"have":[26],"employed":[27],"CNNs":[28],"as":[29,156],"feature":[30,53,69],"extractors":[31],"but":[32],"often":[33],"fail":[34],"under":[35],"such":[36],"Inspired":[39],"by":[40],"Vision":[41],"Transformer":[42],"(ViT),":[43],"we":[44,72,103,139],"first":[45],"develop":[46],"a":[47,122,134,157],"pure":[48],"ViT-based":[49],"framework":[50,123],"for":[51],"robust":[52,68],"extraction":[54],"through":[55],"self-attention":[56],"and":[57,108,153,176,183],"residual":[58],"connection.":[59],"We":[60,119],"then":[61,120],"propose":[62],"two":[63,167],"novel":[64],"methods":[65],"achieve":[67,180],"learning.":[70],"First,":[71],"introduce":[73],"learnable":[74],"pseudo":[75],"3D":[76,83,131],"position":[77,112,132],"embeddings":[78],"(P3DEs)":[79],"that":[80,124,173],"represent":[81,128],"the":[82,89,97,105,109,114,163],"location":[84],"of":[85,96],"an":[86,129,151],"object":[87,152],"world":[90],"coordinate":[91],"system,":[92],"independent":[95],"generate":[101],"P3DEs,":[102],"encode":[104],"camera":[106],"ID":[107],"object's":[110,130],"2D":[111],"image":[115],"using":[116],"embedding":[117],"tables.":[118],"build":[121],"trains":[125],"P3DEs":[126],"weakly":[135],"supervised":[136],"manner.":[137],"Second,":[138],"also":[140],"utilize":[141],"joint":[142],"patch":[143,147,160],"generation":[144],"(JPG).":[145],"During":[146],"generation,":[148],"JPG":[149,179],"considers":[150],"its":[154],"surroundings":[155],"single":[158],"input":[159],"reinforce":[162],"relationship":[164],"information":[165],"between":[166],"features.":[168],"Ultimately,":[169],"experimental":[170],"results":[171],"demonstrate":[172],"both":[174],"ViT-P3DE":[175,177],"with":[178,191],"state-of-the-art":[181],"performance":[182],"significantly":[184],"outperform":[185],"existing":[186],"works,":[187],"especially":[188],"when":[189],"dealing":[190],"extremely":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}