{"id":"https://openalex.org/W4413785393","doi":"https://doi.org/10.1109/tpami.2025.3603181","title":"Efficient High-Order Spatial Interactions for Visual Perception","display_name":"Efficient High-Order Spatial Interactions for Visual Perception","publication_year":2025,"publication_date":"2025-08-28","ids":{"openalex":"https://openalex.org/W4413785393","doi":"https://doi.org/10.1109/tpami.2025.3603181","pmid":"https://pubmed.ncbi.nlm.nih.gov/40875425"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3603181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3603181","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5013372143","display_name":"Zuyan Liu","orcid":"https://orcid.org/0009-0002-6943-3085"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zuyan Liu","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106276801","display_name":"Yongming Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongming Rao","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060902476","display_name":"Wenliang Zhao","orcid":"https://orcid.org/0000-0002-0920-1576"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenliang Zhao","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620306","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0001-7701-234X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460385","display_name":"Jiwen Lu","orcid":"https://orcid.org/0000-0002-6121-5529"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwen Lu","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), State Key Lab of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), the State Key Lab of Intelligent Technologies and Systems, and the Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013372143"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82922172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"48","issue":"1","first_page":"33","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9894000291824341,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9894000291824341,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11408","display_name":"Advanced Optical Imaging Technologies","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/computer-science","display_name":"Computer science","score":0.6617996692657471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6129981279373169},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49294233322143555},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47742876410484314},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3619248569011688},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16472983360290527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6617996692657471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129981279373169},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49294233322143555},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47742876410484314},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3619248569011688},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16472983360290527},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3603181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3603181","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40875425","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40875425","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2438210826","display_name":null,"funder_award_id":"62321005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3510215249","display_name":null,"funder_award_id":"62125603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5196092873","display_name":null,"funder_award_id":"L247009","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G7641150618","display_name":null,"funder_award_id":"62441616","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8443129088","display_name":null,"funder_award_id":"62336004","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"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2147800946","https://openalex.org/W2194775991","https://openalex.org/W2460657278","https://openalex.org/W2565639579","https://openalex.org/W2594519801","https://openalex.org/W2737258237","https://openalex.org/W2752782242","https://openalex.org/W2884822772","https://openalex.org/W2963150697","https://openalex.org/W2963849369","https://openalex.org/W2964137095","https://openalex.org/W2964241181","https://openalex.org/W2979750740","https://openalex.org/W2990613095","https://openalex.org/W3012494314","https://openalex.org/W3034421924","https://openalex.org/W3035560525","https://openalex.org/W3037492894","https://openalex.org/W3094502228","https://openalex.org/W3097217077","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3137278571","https://openalex.org/W3138516171","https://openalex.org/W3153131045","https://openalex.org/W3171215128","https://openalex.org/W3172801447","https://openalex.org/W3177096435","https://openalex.org/W3196107618","https://openalex.org/W4214493665","https://openalex.org/W4214614183","https://openalex.org/W4226106508","https://openalex.org/W4226224676","https://openalex.org/W4226334005","https://openalex.org/W4246193833","https://openalex.org/W4312349930","https://openalex.org/W4312443924","https://openalex.org/W4312658081","https://openalex.org/W4312805142","https://openalex.org/W4312815172","https://openalex.org/W4312820606","https://openalex.org/W4312847199","https://openalex.org/W4313007769","https://openalex.org/W4385245566","https://openalex.org/W4385346076"],"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":{"Recent":[0],"progress":[1],"in":[2,8,90,258],"vision":[3,33,111,128,323],"Transformers":[4,112,182,324],"exhibits":[5],"great":[6],"success":[7],"various":[9,81,110,131],"tasks":[10,257,293],"driven":[11],"by":[12,185],"the":[13,28,32,53,87,118,240,319],"new":[14,70,124,310],"spatial":[15,40,61,305],"modeling":[16,315],"mechanism":[17],"based":[18],"on":[19,117,169,252,280,289,294],"dot-product":[20],"self-attention.":[21],"In":[22,263],"this":[23],"paper,":[24],"we":[25,121,156,165,213,236],"show":[26,215],"that":[27,58,301,316],"key":[29],"ingredients":[30],"behind":[31],"Transformers,":[34],"namely":[35],"input-adaptive,":[36],"long-range":[37],"and":[38,66,75,85,113,134,138,148,175,183,193,205,223,260,273,284,325],"high-order":[39,60,243,304],"interactions,":[41],"can":[42,102,217,307],"also":[43,197,214],"be":[44,218,308],"efficiently":[45],"implemented":[46],"with":[47,63,80,189,229,276,303],"a":[48,105,123,160,186,309],"convolution-based":[49,114],"framework.":[50],"We":[51],"present":[52],"Recursive":[54],"Gated":[55],"Convolution":[56],"(${\\mathit{g}}^{\\mathit{n}}$gnConv)":[57],"performs":[59],"interactions":[62,89,244,306],"gated":[64],"convolutions":[65],"recursive":[67],"designs.":[68],"The":[69],"operation":[71,312],"is":[72,78],"highly":[73],"flexible":[74],"customizable,":[76],"which":[77],"compatible":[79],"variants":[82],"of":[83,126,242,321],"convolution":[84],"extends":[86],"two-order":[88],"self-attention":[91],"to":[92,108,201,220],"arbitrary":[93],"orders":[94],"without":[95],"introducing":[96],"significant":[97,187],"extra":[98],"computation.":[99,231],"${\\mathit{g}}^{\\mathit{n}}$gn":[100],"Conv":[101],"serve":[103],"as":[104,159],"plug-and-play":[106],"module":[107],"improve":[109,225],"models.":[115],"Based":[116],"proposed":[119,267],"operation,":[120],"construct":[122],"family":[125],"generic":[127],"backbones":[129],"for":[130,140,144,150,245,313],"visual":[132,162,314],"modalities":[133],"tasks,":[135],"including":[136],"HorNet":[137,158,179,196],"HorFPN":[139],"image":[141,154,211],"recognition,":[142,155],"Hor3D":[143],"point":[145,233,247],"cloud":[146,234,248],"analysis,":[147,235],"HorCLIP":[149,268],"vision-language":[151,264,290],"modeling.":[152],"For":[153,232],"propose":[157],"stronger":[161],"encoder,":[163],"where":[164],"conduct":[166],"extensive":[167],"experiments":[168,251],"ImageNet":[170,281],"classification,":[171],"COCO":[172,295],"object":[173],"detection,":[174],"ADE20K":[176],"semantic":[177,255],"segmentation.":[178],"outperforms":[180],"Swin":[181],"ConvNeXt":[184,274],"margin":[188],"similar":[190],"overall":[191],"architecture":[192],"training":[194,203,278],"configurations.":[195],"shows":[198,285],"favorable":[199],"scalability":[200],"more":[202],"data":[204,249],"larger":[206],"model":[207],"sizes.":[208],"Apart":[209],"from":[210],"encoders,":[212],"${\\mathit{g}}^{\\mathit{n}}$gnConv":[216,302],"applied":[219],"task-specific":[221],"decoders":[222],"consistently":[224],"dense":[226,291],"prediction":[227],"performance":[228,288],"less":[230],"design":[237],"Hor3D,":[238],"demonstrating":[239],"efficacy":[241],"unstructured":[246],"through":[250],"challenging":[253],"3D":[254],"segmentation":[256],"S3DIS":[259],"ScanNet":[261],"V2.":[262],"modeling,":[265],"our":[266],"surpasses":[269],"mainstream":[270],"Vision":[271],"Transformer":[272],"architectures":[275],"shorter":[277],"schedules":[279],"zero-shot":[282],"classification":[283],"remarkably":[286],"higher":[287],"representation":[292],"Panoptic":[296],"datasets.":[297],"Our":[298],"results":[299],"demonstrate":[300],"basic":[311],"effectively":[317],"combines":[318],"merits":[320],"both":[322],"CNNs.":[326]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}