{"id":"https://openalex.org/W4415540249","doi":"https://doi.org/10.1145/3746027.3755145","title":"Vision Transformer with Sparse Scan Prior","display_name":"Vision Transformer with Sparse Scan Prior","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540249","doi":"https://doi.org/10.1145/3746027.3755145"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755145","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755145","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030116794","display_name":"Yuguang Zhang","orcid":"https://orcid.org/0009-0003-4812-7625"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuguang Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China, MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China, and China Electronics Standardization Insitute, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China, MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China, and China Electronics Standardization Insitute, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058212022","display_name":"Qihang Fan","orcid":"https://orcid.org/0000-0002-6115-5503"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihang Fan","raw_affiliation_strings":["MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005195235","display_name":"Huaibo Huang","orcid":"https://orcid.org/0000-0001-5866-2283"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaibo Huang","raw_affiliation_strings":["MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030116794"],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.6973,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77096084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3664","last_page":"3672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9907000064849854,"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"}},{"id":"https://openalex.org/T11569","display_name":"Optical Coherence Tomography Applications","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/robustness","display_name":"Robustness (evolution)","score":0.6488000154495239},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6097999811172485},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.3995000123977661},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.39879998564720154},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3763999938964844},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3441999852657318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096999883651733},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6488000154495239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6351000070571899},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6097999811172485},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5263000130653381},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755145","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755145","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8295388262","display_name":null,"funder_award_id":"20230484276","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1887706683","https://openalex.org/W2000674472","https://openalex.org/W2007163867","https://openalex.org/W2037908367","https://openalex.org/W2116360511","https://openalex.org/W2331143823","https://openalex.org/W2737258237","https://openalex.org/W2884822772","https://openalex.org/W2910628332","https://openalex.org/W3037492894","https://openalex.org/W3131500599","https://openalex.org/W3151130473","https://openalex.org/W3177096435","https://openalex.org/W4312628331","https://openalex.org/W4312881242","https://openalex.org/W4312986923","https://openalex.org/W4313007769","https://openalex.org/W4386075524","https://openalex.org/W4386075553","https://openalex.org/W4386076222","https://openalex.org/W4388145401"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Transformers":[3],"have":[4],"achieved":[5],"remarkable":[6],"progress":[7],"in":[8,22,145],"computer":[9],"vision":[10,97],"tasks.":[11,122],"However,":[12],"their":[13],"global":[14,75],"modeling":[15,76],"often":[16],"comes":[17],"with":[18,139],"substantial":[19],"computational":[20,94],"overhead,":[21],"stark":[23],"contrast":[24],"to":[25,64],"the":[26,34,67,86,93,104,113],"human":[27,35,87],"eye's":[28,36,88],"efficient":[29],"information":[30,69],"processing.":[31],"Inspired":[32],"by":[33],"sparse":[37],"scanning":[38],"mechanism,":[39],"we":[40,102],"propose":[41],"a":[42,51,119],"Sparse":[43,105],"Scan":[44,106],"Self-Attention":[45],"mechanism":[46,49],"(S3A).":[47],"This":[48,83],"predefines":[50],"series":[52],"of":[53,55,96,116,121,137],"Anchors":[54],"Interest":[56],"for":[57],"each":[58],"token":[59],"and":[60,77,90,154],"employs":[61],"local":[62,81],"attention":[63],"efficiently":[65],"model":[66],"spatial":[68],"around":[70],"these":[71],"anchors,":[72],"avoiding":[73],"redundant":[74],"excessive":[78],"focus":[79],"on":[80,100,124],"information.":[82],"approach":[84],"mirrors":[85],"functionality":[89],"significantly":[91],"reduces":[92],"load":[95],"models.":[98],"Building":[99],"S3A,":[101],"introduce":[103],"Vision":[107],"Transformer":[108],"(SSViT).":[109],"Extensive":[110],"experiments":[111],"demonstrate":[112],"outstanding":[114],"performance":[115],"SSViT":[117,133,142],"across":[118,162],"variety":[120],"Specifically,":[123],"ImageNet":[125],"classification,":[126],"without":[127],"additional":[128],"supervision":[129],"or":[130],"training":[131],"data,":[132],"achieves":[134],"top-1":[135],"accuracies":[136],"84.4%/85.7%":[138],"4.4G/18.2G":[140],"FLOPs.":[141],"also":[143],"excels":[144],"downstream":[146],"tasks":[147],"such":[148],"as":[149],"object":[150],"detection,":[151],"instance":[152],"segmentation,":[153],"semantic":[155],"segmentation.":[156],"Its":[157],"robustness":[158],"is":[159],"further":[160],"validated":[161],"diverse":[163],"datasets.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}