{"id":"https://openalex.org/W4313135247","doi":"https://doi.org/10.1109/iros47612.2022.9982276","title":"CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning","display_name":"CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4313135247","doi":"https://doi.org/10.1109/iros47612.2022.9982276"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9982276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982276","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5101398346","display_name":"Mahdi Saleh","orcid":"https://orcid.org/0009-0007-0390-5955"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mahdi Saleh","raw_affiliation_strings":["Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748"],"affiliations":[{"raw_affiliation_string":"Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076333732","display_name":"Yige Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yige Wang","raw_affiliation_strings":["Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748"],"affiliations":[{"raw_affiliation_string":"Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046896448","display_name":"Nassir Navab","orcid":"https://orcid.org/0000-0002-6032-5611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nassir Navab","raw_affiliation_strings":["Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748"],"affiliations":[{"raw_affiliation_string":"Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067135033","display_name":"Benjamin Busam","orcid":"https://orcid.org/0000-0002-0620-5774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Busam","raw_affiliation_strings":["Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748"],"affiliations":[{"raw_affiliation_string":"Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041092666","display_name":"Federico Tombari","orcid":"https://orcid.org/0000-0001-5598-5212"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Federico Tombari","raw_affiliation_strings":["Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748","Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Technische Universität München (TUM),Faculty of Computer Science,Garching bei München,Germany,85748","institution_ids":[]},{"raw_affiliation_string":"Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101398346"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4443,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8966725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1986","last_page":"1992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9962000250816345,"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":0.7942955493927002},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.7288042902946472},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5969992876052856},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5171939134597778},{"id":"https://openalex.org/keywords/space-partitioning","display_name":"Space partitioning","score":0.5018658638000488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47724294662475586},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.44469359517097473},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4226039946079254},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3999375104904175},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3982320725917816},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3401668071746826},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3027645945549011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942955493927002},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7288042902946472},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5969992876052856},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5171939134597778},{"id":"https://openalex.org/C13670688","wikidata":"https://www.wikidata.org/wiki/Q3500548","display_name":"Space partitioning","level":2,"score":0.5018658638000488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47724294662475586},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.44469359517097473},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4226039946079254},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3999375104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3982320725917816},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3401668071746826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3027645945549011},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9982276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982276","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1644641054","https://openalex.org/W1920022804","https://openalex.org/W2211722331","https://openalex.org/W2460657278","https://openalex.org/W2553307952","https://openalex.org/W2560609797","https://openalex.org/W2788158258","https://openalex.org/W2797997528","https://openalex.org/W2798297823","https://openalex.org/W2953273646","https://openalex.org/W2963121255","https://openalex.org/W2963123724","https://openalex.org/W2963158438","https://openalex.org/W2963226018","https://openalex.org/W2963231572","https://openalex.org/W2963263347","https://openalex.org/W2963517242","https://openalex.org/W2963727135","https://openalex.org/W2979750740","https://openalex.org/W2995435108","https://openalex.org/W3034314779","https://openalex.org/W3094502228","https://openalex.org/W3111535274","https://openalex.org/W3126711100","https://openalex.org/W3136608016","https://openalex.org/W3153465022","https://openalex.org/W3169064633","https://openalex.org/W3205269569","https://openalex.org/W3205586691","https://openalex.org/W3212992486","https://openalex.org/W4297733535","https://openalex.org/W4312808629","https://openalex.org/W4385245566","https://openalex.org/W6640300118","https://openalex.org/W6726497184","https://openalex.org/W6739778489","https://openalex.org/W6739901393","https://openalex.org/W6750189863","https://openalex.org/W6755477022","https://openalex.org/W6762287338","https://openalex.org/W6763422710","https://openalex.org/W6784333009","https://openalex.org/W6788305448","https://openalex.org/W6790830454","https://openalex.org/W6802758728"],"related_works":["https://openalex.org/W2542847180","https://openalex.org/W3034994054","https://openalex.org/W2805712290","https://openalex.org/W2155226960","https://openalex.org/W2909129499","https://openalex.org/W2392087771","https://openalex.org/W2761598930","https://openalex.org/W2553994394","https://openalex.org/W2356600124","https://openalex.org/W2114282491"],"abstract_inverted_index":{"Processing":[0],"3D":[1],"data":[2],"efficiently":[3],"has":[4],"always":[5],"been":[6],"a":[7,70,91],"challenge.":[8],"Spatial":[9],"operations":[10],"on":[11,54,147],"large-scale":[12],"point":[13,57,117],"clouds,":[14,118],"stored":[15],"as":[16],"sparse":[17],"data,":[18],"require":[19],"extra":[20],"cost.":[21],"Attracted":[22],"by":[23,103],"the":[24,46,114,150,168,174],"success":[25],"of":[26,48,116,173],"transformers,":[27],"researchers":[28],"are":[29],"using":[30],"multi-head":[31],"attention":[32,37,85,131],"for":[33,73,130],"vision":[34],"tasks.":[35],"However,":[36],"calculations":[38],"in":[39,45,63,90,141],"transformers":[40,62],"come":[41],"with":[42,149,165,179],"quadratic":[43],"complexity":[44],"number":[47],"inputs":[49],"and":[50,66,76,78,98,106,144,170],"miss":[51],"spatial":[52,92],"intuition":[53],"sets":[55],"like":[56],"clouds.":[58],"We":[59,81,94],"redesign":[60],"set":[61],"this":[64],"work":[65],"incorporate":[67],"them":[68],"into":[69],"hierarchical":[71,135],"framework":[72],"shape":[74,139],"classification":[75,140],"part":[77],"scene":[79],"segmentation.":[80],"propose":[82,120],"our":[83],"local":[84],"unit,":[86],"which":[87,126],"captures":[88],"features":[89],"neighborhood.":[93],"also":[95],"compute":[96],"efficient":[97,122],"dynamic":[99],"global":[100],"cross":[101],"attentions":[102],"leveraging":[104],"sampling":[105],"grouping":[107],"at":[108,186],"each":[109],"iteration.":[110],"Finally,":[111],"to":[112],"mitigate":[113],"non-heterogeneity":[115],"we":[119],"an":[121],"Multi-Scale":[123],"Tokenization":[124],"(MST),":[125],"extracts":[127],"scale-invariant":[128],"tokens":[129],"operations.":[132],"The":[133,182],"proposed":[134,160],"model":[136],"achieves":[137],"state-of-the-art":[138],"mean":[142],"accuracy":[143],"yields":[145],"results":[146],"par":[148],"previous":[151,175],"segmentation":[152,163],"methods":[153],"while":[154],"requiring":[155],"significantly":[156],"fewer":[157],"computations.":[158],"Our":[159],"architecture":[161],"predicts":[162],"labels":[164],"around":[166],"half":[167],"latency":[169],"parameter":[171],"count":[172],"most":[176],"effi-cient":[177],"method":[178],"comparable":[180],"performance.":[181],"code":[183],"is":[184],"available":[185],"https://github.com/YigeWang-WHU/CloudAttention.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}