{"id":"https://openalex.org/W7138001113","doi":"https://doi.org/10.1609/aaai.v40i10.37739","title":"Learning Spatial Decay for Vision Transformers","display_name":"Learning Spatial Decay for Vision Transformers","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138001113","doi":"https://doi.org/10.1609/aaai.v40i10.37739"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37739","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37739/41701","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37739/41701","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089981289","display_name":"Yuxin Mao","orcid":"https://orcid.org/0000-0001-8332-2467"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Mao","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, and Shaanxi Key Laboratory of Information Acquisition and Processing, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, and Shaanxi Key Laboratory of Information Acquisition and Processing, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129673931","display_name":"Zhen Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Zhen Qin","raw_affiliation_strings":["TapTap"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TapTap","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047303316","display_name":"Jinxing Zhou","orcid":"https://orcid.org/0000-0001-6402-7593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinxing Zhou","raw_affiliation_strings":["OpenNLPLab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenNLPLab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129708966","display_name":"Bin Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Fan","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, and Shaanxi Key Laboratory of Information Acquisition and Processing, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, and Shaanxi Key Laboratory of Information Acquisition and Processing, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129740627","display_name":"Jing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, and Shaanxi Key Laboratory of Information Acquisition and Processing, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, and Shaanxi Key Laboratory of Information Acquisition and Processing, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621365","display_name":"Yiran Zhong","orcid":"https://orcid.org/0000-0003-1404-3610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiran Zhong","raw_affiliation_strings":["OpenNLPLab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenNLPLab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129641647","display_name":"Yuchao Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchao Dai","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, and Shaanxi Key Laboratory of Information Acquisition and Processing, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, and Shaanxi Key Laboratory of Information Acquisition and Processing, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23789174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"7945","last_page":"7953"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3750999867916107,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3750999867916107,"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":0.3684999942779541,"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"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0617000013589859,"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/adaptability","display_name":"Adaptability","score":0.5891000032424927},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5065000057220459},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4465000033378601},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.39590001106262207},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3711000084877014},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3325999975204468},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.3149999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607999801635742},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565000176429749},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4465000033378601},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.29739999771118164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C158709400","wikidata":"https://www.wikidata.org/wiki/Q3578586","display_name":"Spatial ecology","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2781179811","wikidata":"https://www.wikidata.org/wiki/Q28134081","display_name":"Spatial configuration","level":3,"score":0.2660999894142151}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37739","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37739/41701","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37739","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37739","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37739/41701","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3766433509","display_name":null,"funder_award_id":"62271410","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6545572955","display_name":null,"funder_award_id":"12150007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138001113.pdf","grobid_xml":"https://content.openalex.org/works/W7138001113.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Transformers":[1],"(ViTs)":[2],"have":[3],"revolutionized":[4],"computer":[5],"vision,":[6],"yet":[7],"their":[8],"self-attention":[9],"mechanism":[10,95],"lacks":[11],"explicit":[12],"spatial":[13,27,77,109,117,137,161,169],"inductive":[14],"biases,":[15],"leading":[16],"to":[17,45,79,107],"suboptimal":[18],"performance":[19],"on":[20,30,112,145],"spatially-structured":[21],"tasks.":[22],"Existing":[23],"approaches":[24],"introduce":[25,84],"data-independent":[26],"decay":[28,78,100,162],"based":[29,111],"fixed":[31],"distance":[32],"metrics,":[33],"applying":[34],"uniform":[35],"attention":[36,110,170],"weighting":[37],"regardless":[38],"of":[39,75,124],"image":[40],"content":[41,114,141],"and":[42,116,148],"limiting":[43],"adaptability":[44],"diverse":[46],"visual":[47],"scenarios.":[48],"Inspired":[49],"by":[50],"recent":[51],"advances":[52],"in":[53,171],"large":[54],"language":[55],"models":[56],"where":[57],"content-aware":[58],"gating":[59],"mechanisms":[60],"(e.g.,":[61],"GLA,":[62],"HGRN2,":[63],"FOX)":[64],"significantly":[65],"outperform":[66],"static":[67],"alternatives,":[68],"we":[69],"present":[70],"the":[71,121],"first":[72],"successful":[73],"adaptation":[74,126],"data-dependent":[76,99,160],"2D":[80],"vision":[81,172],"transformers.":[82,173],"We":[83,119],"Spatial":[85],"Decay":[86],"Transformer":[87],"(SDT),":[88],"featuring":[89],"a":[90,128,164],"novel":[91],"Context-Aware":[92],"Gating":[93],"(CAG)":[94],"that":[96,133],"generates":[97],"dynamic,":[98],"for":[101,167],"patch":[102],"interactions.":[103],"Our":[104,157],"approach":[105],"learns":[106],"modulate":[108],"both":[113],"relevance":[115],"proximity.":[118],"address":[120],"fundamental":[122],"challenge":[123],"1D-to-2D":[125],"through":[127],"unified":[129],"spatial-content":[130],"fusion":[131],"framework":[132],"integrates":[134],"manhattan":[135],"distance-based":[136],"priors":[138],"with":[139],"learned":[140],"representations.":[142],"Extensive":[143],"experiments":[144],"ImageNet-1K":[146],"classification":[147],"generation":[149],"tasks":[150],"demonstrate":[151],"consistent":[152],"improvements":[153],"over":[154],"strong":[155],"baselines.":[156],"work":[158],"establishes":[159],"as":[163],"new":[165],"paradigm":[166],"enhancing":[168]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}