{"id":"https://openalex.org/W4416251454","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229175","title":"MarIns3D: A Open Vocabulary 3D Instance Segmentation Model with Mask Refinement","display_name":"MarIns3D: A Open Vocabulary 3D Instance Segmentation Model with Mask Refinement","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251454","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229175"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100342523","display_name":"Haiyang Li","orcid":"https://orcid.org/0009-0002-2019-9419"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haiyang Li","raw_affiliation_strings":["JiMei University,The College of Computer Engineering,Xiamen,China,361021"],"affiliations":[{"raw_affiliation_string":"JiMei University,The College of Computer Engineering,Xiamen,China,361021","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041661823","display_name":"Mengyun Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyun Cao","raw_affiliation_strings":["JiMei University,The College of Computer Engineering,Xiamen,China,361021"],"affiliations":[{"raw_affiliation_string":"JiMei University,The College of Computer Engineering,Xiamen,China,361021","institution_ids":["https://openalex.org/I161346416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100342523"],"corresponding_institution_ids":["https://openalex.org/I161346416"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3789171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3546999990940094,"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":0.3546999990940094,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.156700000166893,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.10520000010728836,"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/segmentation","display_name":"Segmentation","score":0.8220999836921692},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.548799991607666},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5486000180244446},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5404999852180481},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5015000104904175},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48030000925064087},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.4293999969959259},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4275999963283539}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8220999836921692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958999872207642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7233999967575073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5633000135421753},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.548799991607666},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4293999969959259},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41510000824928284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1999478155","https://openalex.org/W2594519801","https://openalex.org/W2904332125","https://openalex.org/W2939250925","https://openalex.org/W3172351327","https://openalex.org/W4312327508","https://openalex.org/W4312649925","https://openalex.org/W4312912313","https://openalex.org/W4312935996","https://openalex.org/W4313166301","https://openalex.org/W4383109105","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386066126","https://openalex.org/W4386075819","https://openalex.org/W4386076397","https://openalex.org/W4390189960","https://openalex.org/W4390874575","https://openalex.org/W4391582647","https://openalex.org/W4399410938","https://openalex.org/W4402704512","https://openalex.org/W4402715795","https://openalex.org/W4402716083","https://openalex.org/W4402733574","https://openalex.org/W4403906550"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"3D":[1,24,95],"instance":[2,25,96],"segmentation":[3,28,108,129],"has":[4],"gained":[5],"significant":[6],"attention":[7],"due":[8],"to":[9,56,84,104],"its":[10],"potential":[11],"role":[12],"in":[13,46,101,122,141],"scene":[14,82],"perception.":[15],"Existing":[16],"methods":[17],"typically":[18],"involve":[19],"two":[20,53],"stages:":[21],"generating":[22],"class-agnostic":[23],"masks":[26,45,97],"using":[27],"models,":[29],"followed":[30],"by":[31],"semantic":[32],"classification":[33,39],"of":[34,133],"these":[35,94,134],"masks.":[36,87],"However,":[37],"poor":[38],"performance":[40],"often":[41],"stems":[42],"from":[43],"low-quality":[44],"the":[47,58,89,113],"first":[48],"stage.":[49],"This":[50],"paper":[51],"proposes":[52],"key":[54,81],"components":[55,135],"optimize":[57],"mask":[59,126],"generation":[60],"process:":[61],"a":[62,67,119],"dynamic":[63],"offset":[64],"module":[65],"and":[66,115,128],"projection":[68,90],"consistency":[69],"loss.":[70],"By":[71],"dynamically":[72],"adjusting":[73],"sampling":[74],"point":[75],"positions,":[76],"query":[77],"points":[78],"can":[79],"capture":[80],"features":[83],"generate":[85],"high-quality":[86],"Then":[88],"consistencey":[91],"loss":[92],"compares":[93],"with":[98],"ground":[99],"truth":[100],"2D":[102],"projections":[103],"refine":[105],"them,":[106],"improving":[107],"accuracy.":[109],"Experimental":[110],"results":[111],"on":[112],"ScanNetv2":[114],"ScanNet200":[116],"datasets":[117],"show":[118],"1.8%":[120],"improvement":[121],"AP_25,":[123],"demonstrating":[124],"superior":[125],"quality":[127],"performance.":[130],"The":[131],"synergy":[132],"enhances":[136],"our":[137],"model\u2019s":[138],"performance,":[139],"especially":[140],"complex":[142],"scenes.":[143]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}