{"id":"https://openalex.org/W7124501358","doi":"https://doi.org/10.1109/tmm.2026.3654455","title":"CSP: Channel and Space Pruning for Compressing Deep Convolutional Neural Networks","display_name":"CSP: Channel and Space Pruning for Compressing Deep Convolutional Neural Networks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124501358","doi":"https://doi.org/10.1109/tmm.2026.3654455"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3654455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654455","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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/A5123199945","display_name":"Yang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["School of Computer Science and Technology (School of Cyberspace Security), Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-3546-3104","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology (School of Cyberspace Security), Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123172082","display_name":"Liejun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liejun Wang","raw_affiliation_strings":["School of Computer Science and Technology (School of Cyberspace Security), Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-0210-2273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology (School of Cyberspace Security), Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016863397","display_name":"Minchi Kuang","orcid":"https://orcid.org/0000-0002-8082-539X"},"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":"Minchi Kuang","raw_affiliation_strings":["Department of Precision Instrument, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8082-539X","affiliations":[{"raw_affiliation_string":"Department of Precision Instrument, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06604173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"4146","last_page":"4157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6148999929428101,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6148999929428101,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0689999982714653,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06620000302791595,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.920799970626831},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7993999719619751},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5781000256538391},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3831999897956848},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.920799970626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105000257492065},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7993999719619751},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5781000256538391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691999793052673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3654455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654455","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3810548716","display_name":null,"funder_award_id":"2022ZD0115802","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pruning":[0,42],"is":[1,106],"widely":[2],"researched":[3],"as":[4],"one":[5],"of":[6,90,112,119,142,166],"the":[7,64,110,117,131,140,143,157,167],"effective":[8],"methods":[9,16,180],"for":[10,44,116,163],"model":[11,23,28,75,98,124,132],"compression.":[12,76],"However,":[13],"existing":[14],"pruning":[15,57,79,118,128,149,155],"still":[17],"have":[18],"shortcomings":[19],"in":[20,94,181],"achieving":[21],"high":[22],"compression":[24],"rates":[25],"and":[26,58,70,92],"maintaining":[27,97,123],"performance.":[29,99,125],"To":[30,137],"this":[31],"end,":[32],"we":[33],"propose":[34],"a":[35,81,101],"general":[36],"method":[37,54,172],"called":[38],"Channel":[39],"And":[40],"Space":[41],"(CSP)":[43],"compressing":[45],"deep":[46],"convolutional":[47,65,113,144],"neural":[48],"networks":[49],"(DCNNs).":[50],"The":[51,77,126,169],"proposed":[52,170],"CSP":[53,171],"comprises":[55],"Coarse-grained":[56,78,135,148],"Fine-grained":[59,127,154],"pruning,":[60],"which":[61],"operate":[62],"on":[63,134],"kernels":[66,121,145],"from":[67],"both":[68],"channel":[69],"spatial":[71,159,164],"dimensions":[72],"to":[73,86,108,177],"achieve":[74],"utilizes":[80],"Bottleneck-based":[82,102],"maximum":[83,88],"flow":[84,89],"mechanism":[85,105,161],"ensure":[87,138],"inputs":[91],"outputs":[93],"DCNNs,":[95],"thereby":[96],"Additionally,":[100],"dynamic":[103],"updating":[104],"employed":[107],"evaluate":[109],"importance":[111],"kernels,":[114],"allowing":[115],"redundant":[120],"while":[122],"further":[129],"compresses":[130],"based":[133],"pruning.":[136],"that":[139],"parameters":[141],"obtained":[146],"through":[147],"are":[150],"not":[151],"spatially":[152],"redundant,":[153],"employs":[156],"Parameters-free":[158],"attention":[160],"(PSAM)":[162],"sparsification":[165],"kernels.":[168],"demonstrates":[173],"promising":[174],"results":[175],"compared":[176],"state-of-the-art":[178],"(SOTA)":[179],"classic":[182],"DCNN":[183],"models.":[184]},"counts_by_year":[],"updated_date":"2026-06-05T06:17:00.636019","created_date":"2026-01-17T00:00:00"}