{"id":"https://openalex.org/W4389988933","doi":"https://doi.org/10.1109/ictai59109.2023.00125","title":"Vision Transformer with Interactive Windows based on Patch Sequence Reconstruction","display_name":"Vision Transformer with Interactive Windows based on Patch Sequence Reconstruction","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4389988933","doi":"https://doi.org/10.1109/ictai59109.2023.00125"},"language":"en","primary_location":{"id":"doi:10.1109/ictai59109.2023.00125","doi":"https://doi.org/10.1109/ictai59109.2023.00125","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai59109.2023.00125","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5045504745","display_name":"Yuantian Xia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuantian Xia","raw_affiliation_strings":["China Agricultural University,College of Information and Electrical Engineering,Beijing,China","College of Information and Electrical Engineering, China Agricultural University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Agricultural University,College of Information and Electrical Engineering,Beijing,China","institution_ids":["https://openalex.org/I52158045"]},{"raw_affiliation_string":"College of Information and Electrical Engineering, China Agricultural University, Beijing, China","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000261788","display_name":"Xupeng Kou","orcid":"https://orcid.org/0000-0002-3246-6820","observed_orcids":["https://orcid.org/0000-0002-3246-6820"]},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xupeng Kou","raw_affiliation_strings":["China Agricultural University,College of Information and Electrical Engineering,Beijing,China","College of Information and Electrical Engineering, China Agricultural University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Agricultural University,College of Information and Electrical Engineering,Beijing,China","institution_ids":["https://openalex.org/I52158045"]},{"raw_affiliation_string":"College of Information and Electrical Engineering, China Agricultural University, Beijing, China","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091144053","display_name":"Shuhan Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhan Lu","raw_affiliation_strings":["University of Michigan,School of Information,Ann Arbor,USA","School of Information, University of Michigan, Ann Arbor, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,School of Information,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"School of Information, University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039601192","display_name":"Longhe Wang","orcid":"https://orcid.org/0000-0001-9176-8063","observed_orcids":["https://orcid.org/0000-0001-9176-8063"]},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longhe Wang","raw_affiliation_strings":["China Agricultural University,National Research Facility for Phenotypic and Genotypic Analysis of Model Animals,Beijing,China","National Research Facility for Phenotypic and Genotypic Analysis of Model Animals, China Agricultural University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Agricultural University,National Research Facility for Phenotypic and Genotypic Analysis of Model Animals,Beijing,China","institution_ids":["https://openalex.org/I52158045"]},{"raw_affiliation_string":"National Research Facility for Phenotypic and Genotypic Analysis of Model Animals, China Agricultural University, Beijing, China","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101483416","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-2247-3533","observed_orcids":["https://orcid.org/0000-0002-2247-3533"]},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["China Agricultural University,College of Information and Electrical Engineering,Beijing,China","College of Information and Electrical Engineering, China Agricultural University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Agricultural University,College of Information and Electrical Engineering,Beijing,China","institution_ids":["https://openalex.org/I52158045"]},{"raw_affiliation_string":"College of Information and Electrical Engineering, China Agricultural University, Beijing, China","institution_ids":["https://openalex.org/I52158045"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"821","last_page":"828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9937000274658203,"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":0.9937000274658203,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0027000000700354576,"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":0.0017999999690800905,"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/vision-transformer","display_name":"vision transformer","score":0.9430000185966492},{"id":"https://openalex.org/keywords/multiscale-features","display_name":"multi-scale features","score":0.968999981880188},{"id":"https://openalex.org/keywords/translation-invariance","display_name":"translation invariance","score":0.9829999804496765},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.9629999995231628},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.8450000286102295},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.9909999966621399},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.7649999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842268943786621},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7157180309295654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537058711051941},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5224272608757019},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4742673635482788},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4346114993095398},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.43000197410583496},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10547429323196411},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09202221035957336},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/ictai59109.2023.00125","doi":"https://doi.org/10.1109/ictai59109.2023.00125","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai59109.2023.00125","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2560674852","https://openalex.org/W2601564443","https://openalex.org/W2626778328","https://openalex.org/W2942489928","https://openalex.org/W2946948417","https://openalex.org/W2949718784","https://openalex.org/W2950141105","https://openalex.org/W2962851485","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963446712","https://openalex.org/W2963849369","https://openalex.org/W2964080601","https://openalex.org/W2964241181","https://openalex.org/W2966926453","https://openalex.org/W2982220924","https://openalex.org/W3014641072","https://openalex.org/W3015146382","https://openalex.org/W3016265891","https://openalex.org/W3016719260","https://openalex.org/W3018757597","https://openalex.org/W3030520226","https://openalex.org/W3034971973","https://openalex.org/W3035087309","https://openalex.org/W3035396860","https://openalex.org/W3100020884","https://openalex.org/W3101246443","https://openalex.org/W3107634219","https://openalex.org/W3111156583","https://openalex.org/W3116489684","https://openalex.org/W3122484828","https://openalex.org/W3130071011","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3170874841","https://openalex.org/W3172752666","https://openalex.org/W3175630421","https://openalex.org/W6777046832","https://openalex.org/W6780959388","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W3187216907","https://openalex.org/W4313007769","https://openalex.org/W3119786062","https://openalex.org/W3161838454","https://openalex.org/W3168101492","https://openalex.org/W3138516171","https://openalex.org/W4395064982","https://openalex.org/W4312793815","https://openalex.org/W4385805202","https://openalex.org/W3151130473"],"abstract_inverted_index":{"To":[0],"further":[1],"enhance":[2],"the":[3,39,49,52,75,88,103,111,118,122],"performance":[4],"of":[5,42,54,77,107,115,126],"Transformer-based":[6],"models":[7],"in":[8],"vision":[9],"task,":[10],"this":[11],"paper":[12],"proposes":[13],"an":[14],"algorithm":[15],"named":[16],"interactive":[17],"windows":[18],"based":[19],"on":[20,34,87,109,117],"patch":[21,27],"sequence.":[22],"Firstly,":[23],"we":[24,67,84],"introduce":[25],"a":[26,69],"internal":[28,40],"modeling":[29],"method":[30],"that":[31,98],"relies":[32],"solely":[33],"convolutional":[35],"operations":[36],"to":[37],"model":[38,50,101],"features":[41,79],"each":[43],"patch.":[44],"This":[45],"not":[46],"only":[47],"endows":[48],"with":[51],"capability":[53],"multi-scale":[55],"feature":[56],"representation":[57],"but":[58],"also":[59],"adds":[60],"translational":[61],"invariance":[62],"and":[63,90,121],"inductive":[64],"bias.":[65],"Secondly,":[66],"propose":[68],"sequence":[70],"reconstruction":[71],"transformer":[72],"block,":[73],"enabling":[74],"interaction":[76],"attention":[78],"between":[80],"different":[81],"windows.":[82],"Finally,":[83],"conduct":[85],"experiments":[86],"ImageNet-1K":[89],"COCO":[91,119],"2017":[92],"datasets.":[93],"The":[94],"experimental":[95],"results":[96],"demonstrate":[97],"our":[99],"improved":[100],"achieves":[102],"best":[104,112,123],"classification":[105],"accuracy":[106,114,125],"87.3%":[108],"ImageNet-1K,":[110],"detection":[113],"59.6%":[116],"dataset,":[120],"segmentation":[124],"51.9%.":[127]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2023-12-21T00:00:00"}