{"id":"https://openalex.org/W4403791504","doi":"https://doi.org/10.1145/3664647.3680809","title":"Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation","display_name":"Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791504","doi":"https://doi.org/10.1145/3664647.3680809"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101823420","display_name":"Jin Sun","orcid":"https://orcid.org/0000-0002-5860-059X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jin Sun","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069008709","display_name":"Xiaoshuang Shi","orcid":"https://orcid.org/0000-0003-4934-0850"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"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":"Xiaoshuang Shi","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Tsinghua University, Chengdu, SiChuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Tsinghua University, Chengdu, SiChuan, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110818372","display_name":"Zhiyuan Wang","orcid":"https://orcid.org/0009-0009-3835-4596"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Wang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102775611","display_name":"Kaidi Xu","orcid":"https://orcid.org/0000-0003-4437-0671"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaidi Xu","raw_affiliation_strings":["Department of Computer Science, Drexel University, Philadelphia, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Drexel University, Philadelphia, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China &amp; Tongji University, Chengdu, SiChuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China &amp; Tongji University, Chengdu, SiChuan, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037340898","display_name":"Xiaofeng Zhu","orcid":"https://orcid.org/0000-0001-6840-0578"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101823420"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16688583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7123","last_page":"7132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9952999949455261,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9952999949455261,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9896000027656555,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/concatenation","display_name":"Concatenation (mathematics)","score":0.8521038293838501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5829191207885742},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5389725565910339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34566113352775574},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34127265214920044},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.20398196578025818},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14094042778015137},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0947231650352478}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8521038293838501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5829191207885742},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5389725565910339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34566113352775574},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34127265214920044},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.20398196578025818},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14094042778015137},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0947231650352478},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1594551768","https://openalex.org/W2112796928","https://openalex.org/W2116360511","https://openalex.org/W2592962403","https://openalex.org/W2601564443","https://openalex.org/W2618530766","https://openalex.org/W2963404959","https://openalex.org/W2982619380","https://openalex.org/W2998508940","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3157506437","https://openalex.org/W3200947677","https://openalex.org/W4212819272","https://openalex.org/W4226297238","https://openalex.org/W4226363321","https://openalex.org/W4283809036","https://openalex.org/W4287184379","https://openalex.org/W4288804646","https://openalex.org/W4312853765","https://openalex.org/W4385346076","https://openalex.org/W4385656546","https://openalex.org/W4390889742","https://openalex.org/W6796417832","https://openalex.org/W6989086347"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2373577936","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W4387678054","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Modeling":[0],"in":[1,151],"Computer":[2],"Vision":[3,8],"has":[4],"evolved":[5],"to":[6,15,48,62,111,130],"MLPs.":[7],"MLPs":[9],"naturally":[10],"lack":[11],"local":[12,113,119],"modeling":[13,120],"capability,":[14],"which":[16,86,102],"the":[17,51,93,109,131,144,148],"simplest":[18],"treatment":[19],"is":[20,181],"combined":[21],"with":[22,50,147,170],"convolutional":[23,132,145],"layers.":[24],"Convolution,":[25],"famous":[26],"for":[27],"its":[28],"sliding":[29],"window":[30],"scheme,":[31],"also":[32],"suffers":[33],"from":[34],"this":[35,44,66],"scheme":[36,53],"of":[37,79,82,155],"redundancy":[38],"and":[39,54,59,99,106,122,166,173],"lower":[40],"parallel":[41],"computation.":[42],"In":[43],"paper,":[45],"we":[46,68,135],"seek":[47],"dispense":[49],"windowing":[52],"introduce":[55],"a":[56,70,127,137,152],"more":[57],"elaborate":[58],"parallelizable":[60],"method":[61],"exploit":[63],"locality.":[64],"To":[65],"end,":[67],"propose":[69],"new":[71],"MLP":[72],"module,":[73],"namely":[74],"Shifted-Pillars-Concatenation":[75],"(SPC),":[76],"that":[77],"consists":[78],"two":[80],"steps":[81],"processes:":[83],"(1)":[84],"Pillars-Shift,":[85],"generates":[87],"four":[88,97],"neighboring":[89],"maps":[90,110],"by":[91,142],"shifting":[92],"input":[94],"image":[95],"along":[96],"directions,":[98],"(2)":[100],"Pillars-Concatenation,":[101],"applies":[103],"linear":[104],"transformations":[105],"concatenation":[107],"on":[108,163],"aggregate":[112],"features.":[114],"SPC":[115,149],"module":[116,150],"offers":[117],"superior":[118],"power":[121],"performance":[123,162],"gains,":[124],"making":[125],"it":[126],"promising":[128],"alternative":[129],"layer.":[133],"Then,":[134],"build":[136],"pure-MLP":[138],"architecture":[139],"called":[140],"Caterpillar":[141],"replacing":[143],"layer":[146],"hybrid":[153],"model":[154],"sMLPNet.":[156],"Extensive":[157],"experiments":[158],"show":[159],"Caterpillar's":[160],"excellent":[161],"both":[164],"small-scale":[165],"ImageNet-1k":[167],"classification":[168],"benchmarks,":[169],"remarkable":[171],"scalability":[172],"transfer":[174],"capability":[175],"possessed":[176],"as":[177],"well.":[178],"The":[179],"code":[180],"available":[182],"at":[183],"https://github.com/sunjin19126/Caterpillar.":[184]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
