{"id":"https://openalex.org/W4414055002","doi":"https://doi.org/10.1109/hsi66212.2025.11142399","title":"Efficient Multi-Scale Spatial Interactions for Visual Recognition Tasks","display_name":"Efficient Multi-Scale Spatial Interactions for Visual Recognition Tasks","publication_year":2025,"publication_date":"2025-07-16","ids":{"openalex":"https://openalex.org/W4414055002","doi":"https://doi.org/10.1109/hsi66212.2025.11142399"},"language":"en","primary_location":{"id":"doi:10.1109/hsi66212.2025.11142399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hsi66212.2025.11142399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 17th International Conference on Human System Interaction (HSI)","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/A5057436905","display_name":"Xuan-Thuy Vo","orcid":"https://orcid.org/0000-0002-7411-0697"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Xuan-Thuy Vo","raw_affiliation_strings":["University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079734356","display_name":"Duy-Linh Nguyen","orcid":"https://orcid.org/0000-0001-6184-4133"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Duy-Linh Nguyen","raw_affiliation_strings":["University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010613480","display_name":"Adri Priadana","orcid":"https://orcid.org/0000-0002-1553-7631"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Adri Priadana","raw_affiliation_strings":["University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010132145","display_name":"Jehwan Choi","orcid":"https://orcid.org/0009-0005-8494-2170"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jehwan Choi","raw_affiliation_strings":["University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044448641","display_name":"Kang-Hyun Jo","orcid":"https://orcid.org/0000-0002-4937-7082"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kang-Hyun Jo","raw_affiliation_strings":["University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057436905"],"corresponding_institution_ids":["https://openalex.org/I40542001"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25428725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"09"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10888","display_name":"Augmented Reality Applications","score":0.9771999716758728,"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":0.9725000262260437,"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/generalization","display_name":"Generalization","score":0.5942000150680542},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5774000287055969},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5138000249862671},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49970000982284546},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4449999928474426},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4442000091075897},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4336000084877014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4253000020980835},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4108000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755299985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5964000225067139},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5942000150680542},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5774000287055969},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5138000249862671},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4442000091075897},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4108000099658966},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37860000133514404},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31360000371932983},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hsi66212.2025.11142399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hsi66212.2025.11142399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 17th International Conference on Human System Interaction (HSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2618530766","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963351448","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3175515048","https://openalex.org/W3179869055","https://openalex.org/W4214636423","https://openalex.org/W4246193833","https://openalex.org/W4312443924","https://openalex.org/W4312742569","https://openalex.org/W4312820606","https://openalex.org/W4313170858","https://openalex.org/W4323338516","https://openalex.org/W4323914173","https://openalex.org/W4376607931","https://openalex.org/W4378647849","https://openalex.org/W4385346076","https://openalex.org/W4386076222"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Convolution":[0],"operation":[1,10,46,105],"has":[2,47,77],"local":[3,113],"connectivity":[4],"and":[5,20,32,60,87,127,143,155,161,190],"translation":[6],"equivalence":[7],"while":[8],"self-attention":[9,21,37,45,103,130],"captures":[11],"long-range":[12,88],"spatial":[13,89,110],"dependencies.":[14],"Adopting":[15],"the":[16,92,95,120,159,165,169],"merits":[17],"of":[18,72,94,119,141,164],"convolution":[19],"operations":[22],"in":[23,28],"hierarchical":[24],"networks":[25],"can":[26],"result":[27],"better":[29],"visual":[30],"representation":[31],"generalization":[33,162],"performance.":[34],"However,":[35],"integrating":[36],"layers":[38],"into":[39],"earlier":[40],"stages":[41],"is":[42,106,179],"inefficient":[43],"because":[44],"quadratic":[48],"complexity":[49],"with":[50,186],"token":[51],"lengths.":[52],"In":[53],"this":[54,58],"work,":[55],"we":[56],"tackle":[57],"issue":[59],"propose":[61],"an":[62],"Efficient":[63],"Multi-scale":[64],"Spatial":[65],"interaction":[66],"Network":[67],"(EMSNet)":[68],"that":[69],"takes":[70],"advantage":[71],"hybrid":[73],"networks.":[74],"The":[75,99,116],"EMSNet":[76],"key":[78],"insights:":[79],"(1)":[80],"Each":[81],"stage":[82],"efficiently":[83],"models":[84],"both":[85],"short-range":[86],"interactions":[90,111],"via":[91,134],"design":[93],"multi-scale":[96],"tokens;":[97],"(2)":[98],"novel":[100],"convolution-based":[101],"multi-head":[102,129],"(C-MHSA)":[104],"introduced":[107],"to":[108],"learn":[109],"inside":[112],"regions;":[114],"(3)":[115],"efficient":[117],"combination":[118],"depthwise":[121,124],"convolution,":[122,125],"coordinate":[123],"C-MHSA,":[126],"global":[128],"(G-MHSA)":[131],"are":[132],"performed":[133],"channel":[135],"splitting":[136],"strategy,":[137],"extracting":[138],"wide":[139],"ranges":[140],"frequencies":[142],"multi-order":[144],"interactions.":[145],"Extensive":[146],"experiments":[147],"on":[148,176],"ImageNet-1K":[149,177],"image":[150],"classification,":[151],"MS-COCO":[152],"object":[153],"detection,":[154],"segmentation":[156],"tasks":[157],"verify":[158],"effectiveness":[160],"ability":[163],"EMSNet.":[166],"For":[167],"instance,":[168],"EMS":[170],"Net-XTiny":[171],"gets":[172],"77.1%":[173],"Top-1":[174],"accuracy":[175],"which":[178],"much":[180],"greater":[181],"than":[182],"PVTvl-Tiny":[183],"by":[184],"2%":[185],"only":[187],"22%":[188],"parameters":[189],"37%":[191],"GFLOPs.":[192]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}