{"id":"https://openalex.org/W4392904667","doi":"https://doi.org/10.1109/icassp48485.2024.10446293","title":"Vision Transformer with 2D Explicit Position Encoding","display_name":"Vision Transformer with 2D Explicit Position Encoding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904667","doi":"https://doi.org/10.1109/icassp48485.2024.10446293"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100340449","display_name":"Yujie Li","orcid":"https://orcid.org/0000-0002-5801-4937"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujie Li","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656555","display_name":"Zihang Ma","orcid":"https://orcid.org/0009-0000-6021-7605"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihang Ma","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488030","display_name":"Xinghe Wang","orcid":"https://orcid.org/0009-0000-3255-6626"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghe Wang","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613594","display_name":"Yifu Wang","orcid":"https://orcid.org/0000-0001-5937-2261"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifu Wang","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030439103","display_name":"Benying Tan","orcid":"https://orcid.org/0000-0002-9121-8499"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benying Tan","raw_affiliation_strings":["Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,School of Artificial Intelligence,Guilin,China","institution_ids":["https://openalex.org/I5343935"]},{"raw_affiliation_string":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100340449"],"corresponding_institution_ids":["https://openalex.org/I5343935"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46902049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7690","last_page":"7694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/interpretability","display_name":"Interpretability","score":0.8157730102539062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853045463562012},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7729175686836243},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5753876566886902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5285849571228027},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3924850821495056},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08738455176353455}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8157730102539062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853045463562012},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7729175686836243},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5753876566886902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5285849571228027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3924850821495056},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08738455176353455},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2108598243","https://openalex.org/W2747329762","https://openalex.org/W2899663614","https://openalex.org/W2962858109","https://openalex.org/W3138516171","https://openalex.org/W3188427387","https://openalex.org/W3203701986","https://openalex.org/W4312340826","https://openalex.org/W4312349930","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6714181750","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6792695861"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recently,":[0],"the":[1,24,42,61,92,98,117,121],"Vision":[2],"Transformer":[3],"(ViT)":[4],"has":[5],"achieved":[6],"outstanding":[7],"performance":[8],"in":[9,91],"various":[10,107],"computer":[11],"vision":[12],"tasks.":[13],"Positional":[14],"encoding":[15,74,102,129,137],"is":[16,35],"an":[17,53],"indispensable":[18],"component":[19],"of":[20,28,45,95,123,143],"ViT":[21],"for":[22,56],"handling":[23],"inherent":[25],"structural":[26],"information":[27],"images.":[29],"However,":[30],"attaching":[31],"position":[32,136],"encodings":[33],"manually":[34],"a":[36,70,87,140],"time-consuming":[37],"process":[38],"that":[39,76],"slows":[40],"down":[41],"training":[43,81],"speed":[44],"ViT.":[46],"To":[47],"address":[48],"this":[49],"issue,":[50],"we":[51],"propose":[52],"explicit":[54,72,100,127,133],"approach":[55,85],"positional":[57,73,101,128],"encoding,":[58],"distinct":[59],"from":[60],"original":[62],"ViT\u2019s":[63],"implicit":[64],"design.":[65],"Our":[66],"new":[67],"implementation":[68],"uses":[69],"2D-based":[71],"method":[75],"accelerates":[77],"convergence":[78],"and":[79,110],"improves":[80],"efficiency.":[82],"The":[83,113,131],"proposed":[84,125,132],"yields":[86],"remarkable":[88],"improvement,":[89],"especially":[90],"initial":[93],"stages":[94],"training,":[96],"where":[97],"2D":[99,126,134],"offers":[103],"improved":[104],"compatibility":[105],"with":[106],"input":[108],"lengths":[109],"enhanced":[111],"interpretability.":[112],"experimental":[114],"results":[115],"on":[116],"ImageNet":[118],"dataset":[119],"confirm":[120],"effectiveness":[122],"our":[124],"approach.":[130],"coordinate":[135],"can":[138],"achieve":[139],"maximum":[141],"improvement":[142],"up":[144],"to":[145],"437%.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
