{"id":"https://openalex.org/W2981787830","doi":"https://doi.org/10.1145/3343031.3351029","title":"Fast Non-Local Neural Networks with Spectral Residual Learning","display_name":"Fast Non-Local Neural Networks with Spectral Residual Learning","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981787830","doi":"https://doi.org/10.1145/3343031.3351029","mag":"2981787830"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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/A5100543665","display_name":"Lu Chi","orcid":"https://orcid.org/0009-0004-2274-6142"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Chi","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024163245","display_name":"Guiyu Tian","orcid":"https://orcid.org/0009-0005-6262-0146"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiyu Tian","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028877572","display_name":"Yadong Mu","orcid":"https://orcid.org/0000-0001-7815-3750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Mu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075290241","display_name":"Lingxi Xie","orcid":"https://orcid.org/0000-0003-4831-9451"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxi Xie","raw_affiliation_strings":["Noah's Ark Lab, Huawei, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab, Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0009-0003-2676-5300"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Noah's Ark Lab, Huawei, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab, Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100543665"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.5061,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.69721268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2142","last_page":"2151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983000159263611,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9853000044822693,"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/computer-science","display_name":"Computer science","score":0.6940584778785706},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6036021709442139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.565141499042511},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5405383110046387},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5161346197128296},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47021034359931946},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.45336395502090454},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.44168123602867126},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43768221139907837},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.4354628324508667},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4150921702384949},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38551247119903564},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.35140520334243774},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3283834457397461},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18359330296516418},{"id":"https://openalex.org/keywords/fractional-fourier-transform","display_name":"Fractional Fourier transform","score":0.08785480260848999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940584778785706},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6036021709442139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565141499042511},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5405383110046387},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5161346197128296},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47021034359931946},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.45336395502090454},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.44168123602867126},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43768221139907837},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.4354628324508667},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4150921702384949},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38551247119903564},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.35140520334243774},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3283834457397461},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18359330296516418},{"id":"https://openalex.org/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.08785480260848999},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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":67,"referenced_works":["https://openalex.org/W23953656","https://openalex.org/W303331833","https://openalex.org/W639708223","https://openalex.org/W1498368596","https://openalex.org/W1522734439","https://openalex.org/W1559083155","https://openalex.org/W1779006005","https://openalex.org/W1903029394","https://openalex.org/W1979005107","https://openalex.org/W1983364832","https://openalex.org/W1993149133","https://openalex.org/W1993229407","https://openalex.org/W1996478295","https://openalex.org/W1997500560","https://openalex.org/W2016053056","https://openalex.org/W2030536784","https://openalex.org/W2031004336","https://openalex.org/W2031614119","https://openalex.org/W2055178055","https://openalex.org/W2061171222","https://openalex.org/W2073246097","https://openalex.org/W2102605133","https://openalex.org/W2113325037","https://openalex.org/W2117539524","https://openalex.org/W2131263044","https://openalex.org/W2143158307","https://openalex.org/W2145108814","https://openalex.org/W2157939923","https://openalex.org/W2161565164","https://openalex.org/W2163605009","https://openalex.org/W2175012183","https://openalex.org/W2194775991","https://openalex.org/W2235034809","https://openalex.org/W2307770531","https://openalex.org/W2382036597","https://openalex.org/W2412782625","https://openalex.org/W2507009361","https://openalex.org/W2509865052","https://openalex.org/W2560023338","https://openalex.org/W2601564443","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2630837129","https://openalex.org/W2761659801","https://openalex.org/W2773514261","https://openalex.org/W2804078698","https://openalex.org/W2916798096","https://openalex.org/W2949117887","https://openalex.org/W2952186347","https://openalex.org/W2955058313","https://openalex.org/W2962835968","https://openalex.org/W2962899219","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963266682","https://openalex.org/W2963402313","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963524571","https://openalex.org/W2963526497","https://openalex.org/W2963645879","https://openalex.org/W2964121744","https://openalex.org/W2964169985","https://openalex.org/W2964221239","https://openalex.org/W2964304707","https://openalex.org/W2964309882","https://openalex.org/W4299428766"],"related_works":["https://openalex.org/W2079003682","https://openalex.org/W2089544495","https://openalex.org/W2913266608","https://openalex.org/W1555021777","https://openalex.org/W1970258141","https://openalex.org/W2162611351","https://openalex.org/W2516295475","https://openalex.org/W2053055950","https://openalex.org/W2766639751","https://openalex.org/W2390401148"],"abstract_inverted_index":{"Effectively":[0],"modeling":[1],"long-range":[2],"spatial":[3],"correlation":[4],"is":[5,23,147,188,196],"crucial":[6],"in":[7,26,96,122,169,179,235],"context-sensitive":[8],"visual":[9],"computing":[10],"tasks,":[11,216],"such":[12,28,138],"as":[13,139],"human":[14,218],"pose":[15,219],"estimation":[16,220],"and":[17,100,126,191,205,223],"video":[18,224],"classification.":[19,225],"Enlarging":[20],"receptive":[21,51,69,154],"field":[22],"popularly":[24],"adopted":[25],"building":[27],"non-local":[29,239],"deep":[30],"networks.":[31],"However,":[32],"current":[33],"solutions,":[34],"including":[35,217],"dilation":[36],"convolution":[37],"or":[38,49,141],"self-attention":[39],"based":[40],"operators,":[41],"mostly":[42],"suffer":[43],"from":[44,221],"either":[45],"low":[46],"computational":[47],"efficacy":[48],"insufficient":[50],"field.":[52,70],"This":[53,163],"paper":[54],"proposes":[55],"spectral":[56,92,98,124,136],"residual":[57,120],"learning":[58,121],"(SRL),":[59],"a":[60,81,91,101,129,197],"novel":[61],"network":[62,240],"architectural":[63],"design":[64],"for":[65],"achieving":[66],"fully":[67],"global":[68,153],"A":[71],"neural":[72,132],"block":[73],"that":[74,84,104],"implements":[75],"SRL":[76,146,180,195],"has":[77],"three":[78],"key":[79],"components:":[80],"local-to-global":[82,175],"transform":[83,103,204],"projects":[85],"some":[86,123],"ordinary":[87],"local":[88,112],"features":[89],"into":[90,134],"domain,":[93,99],"compiled":[94],"operations":[95,151],"the":[97,110,174],"global-to-local":[102,177],"converts":[105],"all":[106,150,160],"data":[107],"back":[108],"to":[109,118],"original":[111],"format.":[113],"We":[114,209],"show":[115,229],"its":[116],"equivalence":[117],"conducting":[119],"domain":[125],"carefully":[127],"re-formulate":[128],"variety":[130],"of":[131,145],"layers":[133],"their":[135],"forms,":[137],"ReLU":[140],"convolutions.":[142],"The":[143],"benefits":[144],"three-fold:":[148],"first,":[149],"have":[152],"field,":[155],"namely":[156],"any":[157],"update":[158],"affects":[159],"image":[161],"positions.":[162],"can":[164],"extract":[165],"richer":[166],"context":[167],"information":[168],"various":[170],"vision":[171],"tasks;":[172],"Secondly,":[173],"/":[176],"transforms":[178],"are":[181],"defined":[182],"by":[183,202,232],"bi-linear":[184],"unitary":[185],"matrices,":[186],"which":[187],"both":[189],"computation":[190],"parameter":[192],"economic;":[193],"Lastly,":[194],"generic":[198],"formulation,":[199],"here":[200],"instantiated":[201],"Fourier":[203],"real":[206],"orthogonal":[207],"matrix.":[208],"conduct":[210],"comprehensive":[211],"evaluations":[212],"on":[213],"two":[214],"challenging":[215],"images":[222],"All":[226],"experiments":[227],"clearly":[228],"performance":[230],"improvement":[231],"large":[233],"margins":[234],"comparison":[236],"with":[237],"conventional":[238],"designs.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}