{"id":"https://openalex.org/W4205262979","doi":"https://doi.org/10.1109/tcsvt.2021.3132047","title":"Learning Hybrid Semantic Affinity for Point Cloud Segmentation","display_name":"Learning Hybrid Semantic Affinity for Point Cloud Segmentation","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4205262979","doi":"https://doi.org/10.1109/tcsvt.2021.3132047"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2021.3132047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3132047","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5028701730","display_name":"Zhanjie Song","orcid":"https://orcid.org/0000-0002-6654-767X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanjie Song","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-6654-767X","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077094563","display_name":"Linqing Zhao","orcid":"https://orcid.org/0000-0001-9635-0715"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linqing Zhao","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-9635-0715","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620306","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0001-7701-234X"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"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":"Jie Zhou","raw_affiliation_strings":["Department of Automation, State Key Laboratory of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology (BNRist), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7701-234X","affiliations":[{"raw_affiliation_string":"Department of Automation, State Key Laboratory of Intelligent Technologies and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), Beijing, China","institution_ids":["https://openalex.org/I4210156423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0408,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.97916786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":"7","first_page":"4599","last_page":"4612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.7337884306907654},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6972424387931824},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6529598832130432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5774290561676025},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5746572613716125},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5714181661605835},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5277089476585388},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4829218089580536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42421281337738037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4116436243057251},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4102945029735565},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.26609867811203003},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.10423445701599121}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337884306907654},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6972424387931824},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6529598832130432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5774290561676025},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5746572613716125},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5714181661605835},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5277089476585388},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4829218089580536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42421281337738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4116436243057251},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4102945029735565},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26609867811203003},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.10423445701599121}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2021.3132047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3132047","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G275709606","display_name":null,"funder_award_id":"2020YFC1522600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2112467991","https://openalex.org/W2143255850","https://openalex.org/W2153226019","https://openalex.org/W2250539671","https://openalex.org/W2278868814","https://openalex.org/W2412782625","https://openalex.org/W2460657278","https://openalex.org/W2516803306","https://openalex.org/W2532206188","https://openalex.org/W2560023338","https://openalex.org/W2565662353","https://openalex.org/W2594519801","https://openalex.org/W2769312834","https://openalex.org/W2788158258","https://openalex.org/W2795374598","https://openalex.org/W2796813206","https://openalex.org/W2797997528","https://openalex.org/W2798297823","https://openalex.org/W2798380924","https://openalex.org/W2888340395","https://openalex.org/W2912230690","https://openalex.org/W2918473435","https://openalex.org/W2932399282","https://openalex.org/W2948107928","https://openalex.org/W2956542947","https://openalex.org/W2960986959","https://openalex.org/W2961566087","https://openalex.org/W2962676885","https://openalex.org/W2962758679","https://openalex.org/W2962891704","https://openalex.org/W2963125977","https://openalex.org/W2963182550","https://openalex.org/W2963231572","https://openalex.org/W2963281829","https://openalex.org/W2963357556","https://openalex.org/W2963517242","https://openalex.org/W2964051675","https://openalex.org/W2968847206","https://openalex.org/W2975950300","https://openalex.org/W2981983525","https://openalex.org/W2983098675","https://openalex.org/W2984422960","https://openalex.org/W2990479855","https://openalex.org/W2990613095","https://openalex.org/W2991216808","https://openalex.org/W2997216793","https://openalex.org/W2997851315","https://openalex.org/W3008547073","https://openalex.org/W3010797203","https://openalex.org/W3012494314","https://openalex.org/W3014902535","https://openalex.org/W3034239841","https://openalex.org/W3034591723","https://openalex.org/W3034868495","https://openalex.org/W3034978279","https://openalex.org/W3035154952","https://openalex.org/W3035252826","https://openalex.org/W3035339581","https://openalex.org/W3035472394","https://openalex.org/W3084505175","https://openalex.org/W3089874271","https://openalex.org/W3105043467","https://openalex.org/W3107518100","https://openalex.org/W3109944402","https://openalex.org/W3110503160","https://openalex.org/W3127555982","https://openalex.org/W3178663471","https://openalex.org/W3180254007","https://openalex.org/W3184159242","https://openalex.org/W6687484953","https://openalex.org/W6726873649","https://openalex.org/W6739778489","https://openalex.org/W6755808539","https://openalex.org/W6763422710","https://openalex.org/W6772217312","https://openalex.org/W6774629189","https://openalex.org/W6788305448"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4287694812","https://openalex.org/W3128716822","https://openalex.org/W3046762217","https://openalex.org/W4399442168","https://openalex.org/W2114282491"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,63,79,125],"present":[4],"a":[5,56,60,95,122],"hybrid":[6,57],"semantic":[7,22,40,119,139],"affinity":[8,131],"learning":[9],"method":[10,154],"(HSA)":[11],"to":[12,33,47,71,100,114,132],"capture":[13],"and":[14,37,85,137,168],"leverage":[15],"the":[16,30,39,49,65,102,116,127,135,145,157],"dependencies":[17,51],"of":[18,83,118,129,159],"categories":[19],"for":[20,75,141],"3D":[21,53],"segmentation.":[23],"Unlike":[24],"existing":[25],"methods":[26],"that":[27,152],"only":[28],"use":[29],"cross-entropy":[31],"loss":[32],"perform":[34],"one-to-one":[35],"supervision":[36],"ignore":[38],"relations":[41],"between":[42,52],"points,":[43],"our":[44,153],"approach":[45],"aims":[46],"learn":[48],"label":[50],"points":[54],"from":[55],"perspective.":[58],"From":[59,121],"global":[61,73,104],"view,":[62,124],"introduce":[64],"structural":[66],"correlations":[67],"among":[68],"different":[69],"classes":[70],"provide":[72],"priors":[74,107],"point":[76,112],"features.":[77],"Specifically,":[78],"fuse":[80],"word":[81],"embeddings":[82],"labels":[84],"scene-level":[86],"features":[87,113],"as":[88],"category":[89],"nodes,":[90],"which":[91],"are":[92,108],"processed":[93],"via":[94],"graph":[96],"convolutional":[97],"network":[98],"(GCN)":[99],"produce":[101],"sample-adapted":[103],"priors.":[105],"These":[106],"then":[109],"combined":[110],"with":[111],"enhance":[115],"rationality":[117],"predictions.":[120],"local":[123,130],"propose":[126],"concept":[128],"effectively":[133],"model":[134],"intra-class":[136],"inter-class":[138],"similarities":[140],"adjacent":[142],"neighborhoods,":[143],"making":[144],"predictions":[146],"more":[147],"discriminative.":[148],"Experimental":[149],"results":[150],"show":[151],"consistently":[155],"improves":[156],"performance":[158],"state-of-the-art":[160],"models":[161],"across":[162],"indoor":[163],"(S3DIS,":[164],"ScanNet),":[165],"outdoor":[166],"(SemanticKITTI),":[167],"synthetic":[169],"(ShapeNet)":[170],"datasets.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}