{"id":"https://openalex.org/W4415709190","doi":"https://doi.org/10.1109/icme59968.2025.11209210","title":"Prototype Optimal Transport for Box-Supervised 3D Instance Segmentation","display_name":"Prototype Optimal Transport for Box-Supervised 3D Instance Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709190","doi":"https://doi.org/10.1109/icme59968.2025.11209210"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085272002","display_name":"Ye Zhou","orcid":"https://orcid.org/0000-0003-0188-8366"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Zhou","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054606798","display_name":"Wenfei Yang","orcid":"https://orcid.org/0000-0003-3599-7659"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Yang","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648981","display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668156","display_name":"Xiang Liu","orcid":"https://orcid.org/0000-0002-4874-4071"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["Dongguan University of Technology,School of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguan University of Technology,School of Computer Science and Technology","institution_ids":["https://openalex.org/I2799850029"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9121000170707703,"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":0.9121000170707703,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.038600001484155655,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.005499999970197678,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7215999960899353},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6780999898910522},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6685000061988831},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.602400004863739},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4643000066280365},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4268999993801117},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4047999978065491},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7215999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203999757766724},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6780999898910522},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6685000061988831},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007999777793884},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.28859999775886536},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1935978687","https://openalex.org/W2246915724","https://openalex.org/W2594519801","https://openalex.org/W2607098679","https://openalex.org/W2769312834","https://openalex.org/W2962759414","https://openalex.org/W3034949383","https://openalex.org/W3116959466","https://openalex.org/W3166573884","https://openalex.org/W3204034406","https://openalex.org/W4312274934","https://openalex.org/W4312903773","https://openalex.org/W4319300040","https://openalex.org/W4382457953","https://openalex.org/W4383109105","https://openalex.org/W4386076523","https://openalex.org/W4390872695","https://openalex.org/W4390873466","https://openalex.org/W4390873582","https://openalex.org/W4402727594"],"related_works":[],"abstract_inverted_index":{"3D":[0,15],"Instance":[1],"segmentation":[2],"(3DIS)":[3],"on":[4,29,118,157],"point":[5],"clouds":[6],"is":[7,43],"a":[8,44,58],"fundamental":[9],"task":[10],"in":[11,110],"the":[12,34,49,90,95,119,130,145],"field":[13],"of":[14,132,147],"scene":[16],"understanding.":[17],"Existing":[18],"fully-supervised":[19],"networks":[20],"have":[21],"achieved":[22],"promising":[23],"results":[24],"but":[25],"remain":[26],"heavily":[27],"reliant":[28],"point-wise":[30,65,133],"annotated":[31],"data.":[32],"Using":[33],"instance":[35,99],"bounding":[36,69,96],"boxes":[37,97],"as":[38,98],"annotations":[39],"for":[40,138],"weakly-supervised":[41],"learning":[42,83],"feasible":[45],"way":[46],"to":[47,63,85,107,113,154],"solve":[48],"label-efficiency":[50],"problem.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"propose":[56],"POTNet,":[57],"novel":[59],"training":[60],"paradigm":[61],"designed":[62],"generate":[64],"pseudo-labels":[66,134],"using":[67],"only":[68],"box":[70],"annotations,":[71],"which":[72],"effectively":[73],"considering":[74],"both":[75],"local":[76,87,139],"and":[77,124,140],"global":[78,141],"information.":[79],"We":[80,101,143],"leverage":[81],"prototype":[82],"method":[84,149],"extract":[86],"features":[88],"from":[89],"non-overlapping":[91],"regions":[92,112],"indicated":[93],"by":[94,150],"prototypes.":[100],"employ":[102],"an":[103],"optimal":[104],"transport":[105],"algorithm":[106],"assign":[108],"points":[109],"overlapping":[111],"their":[114],"corresponding":[115],"instances":[116],"based":[117],"similarity":[120],"matrix":[121],"between":[122],"prototypes":[123],"these":[125],"points.":[126],"Our":[127],"approach":[128],"enables":[129],"generation":[131],"that":[135],"fully":[136],"account":[137],"correlations.":[142],"demonstrate":[144],"effectiveness":[146],"our":[148],"achieving":[151],"performance":[152],"comparable":[153],"state-of-the-art":[155],"approaches":[156],"multiple":[158],"datasets,":[159],"without":[160],"requiring":[161],"any":[162],"additional":[163],"supplementary":[164],"data":[165],"or":[166],"retraining":[167],"processes.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}