{"id":"https://openalex.org/W7133247191","doi":"https://doi.org/10.52202/068431-0488","title":"Spatial Pruned Sparse Convolution for Efficient 3D Object Detection","display_name":"Spatial Pruned Sparse Convolution for Efficient 3D Object Detection","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7133247191","doi":"https://doi.org/10.52202/068431-0488"},"language":"en","primary_location":{"id":"doi:10.52202/068431-0488","doi":"https://doi.org/10.52202/068431-0488","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-0488","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 35","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.14201","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157653923","display_name":"Jianhui Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianhui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127862128","display_name":"Yukang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127813121","display_name":"Xiaojuan Qi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqing Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127825712","display_name":"Zhuotao Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuotao Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127799981","display_name":"Xiao Tan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127813121","display_name":"Xiaojuan Qi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojuan Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.776,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.90681692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6735","last_page":"6748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.00019999999494757503,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.0,"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/3d-object-detection","display_name":"3D object detection","score":0.9269999861717224},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.6050000190734863},{"id":"https://openalex.org/keywords/redundancy-reduction","display_name":"redundancy reduction","score":0.7509999871253967},{"id":"https://openalex.org/keywords/point-clouds","display_name":"point clouds","score":0.32899999618530273},{"id":"https://openalex.org/keywords/magnitude-based-pruning","display_name":"magnitude-based pruning","score":0.6169999837875366},{"id":"https://openalex.org/keywords/downsampling","display_name":"downsampling","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6007000207901001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595300018787384},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5264999866485596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5217000246047974},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4494999945163727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.323199987411499},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2953000068664551},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.2768999934196472},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/068431-0488","doi":"https://doi.org/10.52202/068431-0488","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-0488","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 35","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.14201","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.14201","pdf_url":"https://arxiv.org/pdf/2209.14201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.14201","doi":"https://doi.org/10.48550/arxiv.2209.14201","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.14201","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.14201","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.14201","pdf_url":"https://arxiv.org/pdf/2209.14201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133247191.pdf","grobid_xml":"https://content.openalex.org/works/W7133247191.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W189277179","https://openalex.org/W2561238782","https://openalex.org/W2601564443","https://openalex.org/W2624273542","https://openalex.org/W2938428612","https://openalex.org/W2969987486","https://openalex.org/W2991680559","https://openalex.org/W3034602892","https://openalex.org/W3053706811","https://openalex.org/W3113028524","https://openalex.org/W3118341329","https://openalex.org/W3201719054","https://openalex.org/W3204896784","https://openalex.org/W3209639308","https://openalex.org/W4310078553","https://openalex.org/W4313141028","https://openalex.org/W4313149358"],"related_works":["https://openalex.org/W4386597219","https://openalex.org/W4405491171","https://openalex.org/W4313149358","https://openalex.org/W4392903997","https://openalex.org/W4400377786","https://openalex.org/W4403922463","https://openalex.org/W4319453654","https://openalex.org/W2522897152","https://openalex.org/W7202436382","https://openalex.org/W4375869730"],"abstract_inverted_index":{"3D":[0,36,41,149],"scenes":[1],"are":[2,102],"dominated":[3],"by":[4,68],"a":[5,58,72],"large":[6],"number":[7],"of":[8,33,46,61,100,107,132,136],"background":[9],"points,":[10],"which":[11,56,82,101,129],"is":[12],"redundant":[13],"for":[14,112],"the":[15,44,53,105,118,133,158,178],"detection":[16],"task":[17],"that":[18,40,117,165],"mainly":[19],"needs":[20],"to":[21,125],"focus":[22],"on":[23,104,157],"foreground":[24],"objects.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,70],"analyze":[30],"major":[31],"components":[32],"existing":[34,147],"sparse":[35,79,89,96,148],"CNNs":[37,42,150],"and":[38,48,63,92,161],"find":[39],"ignore":[43],"redundancy":[45,113],"data":[47],"further":[49],"amplify":[50],"it":[51],"in":[52,174],"down-sampling":[54],"process,":[55],"brings":[57],"huge":[59],"amount":[60],"extra":[62,134,152],"unnecessary":[64],"computational":[65],"overhead.":[66],"Inspired":[67],"this,":[69],"propose":[71],"new":[73],"convolution":[74,80,90,97],"operator":[75],"named":[76],"spatial":[77,86,93],"pruned":[78,87,94],"(SPS-Conv),":[81],"includes":[83],"two":[84],"variants,":[85],"submanifold":[88],"(SPSS-Conv)":[91],"regular":[95],"(SPRS-Conv),":[98],"both":[99],"based":[103],"idea":[106],"dynamically":[108],"determining":[109],"crucial":[110,127],"areas":[111,128],"reduction.":[114],"We":[115],"validate":[116],"magnitude":[119],"can":[120,142,168],"serve":[121],"as":[122],"important":[123],"cues":[124],"determine":[126],"get":[130],"rid":[131],"computations":[135],"learning-based":[137],"methods.":[138],"The":[139],"proposed":[140],"modules":[141],"easily":[143],"be":[144],"incorporated":[145],"into":[146],"without":[151,176],"architectural":[153],"modifications.":[154],"Extensive":[155],"experiments":[156],"KITTI,":[159],"Waymo":[160],"nuScenes":[162],"datasets":[163],"demonstrate":[164],"our":[166],"method":[167],"achieve":[169],"more":[170],"than":[171],"50%":[172],"reduction":[173],"GFLOPs":[175],"compromising":[177],"performance.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-03-03T00:00:00"}