{"id":"https://openalex.org/W4403792305","doi":"https://doi.org/10.1145/3664647.3680998","title":"RefMask3D: Language-Guided Transformer for 3D Referring Segmentation","display_name":"RefMask3D: Language-Guided Transformer for 3D Referring Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792305","doi":"https://doi.org/10.1145/3664647.3680998"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680998","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5085200012","display_name":"Shuting He","orcid":"https://orcid.org/0000-0002-1582-5684"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuting He","raw_affiliation_strings":["Institute of Big Data, Fudan University & Nanyang Technological University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Big Data, Fudan University & Nanyang Technological University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036631624","display_name":"Henghui Ding","orcid":"https://orcid.org/0000-0003-4868-6526"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Henghui Ding","raw_affiliation_strings":["Institute of Big Data, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Big Data, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085200012"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.5599,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84811023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8316","last_page":"8325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.994700014591217,"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":0.7010593414306641},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5426687598228455},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5005016326904297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4448711574077606},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43909382820129395},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40564990043640137},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1308613419532776},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11095771193504333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010593414306641},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5426687598228455},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5005016326904297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4448711574077606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43909382820129395},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40564990043640137},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1308613419532776},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11095771193504333},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680998","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":41,"referenced_works":["https://openalex.org/W2489434015","https://openalex.org/W2963109634","https://openalex.org/W2999219213","https://openalex.org/W3035097537","https://openalex.org/W3095974555","https://openalex.org/W3108925098","https://openalex.org/W3138516171","https://openalex.org/W3140398265","https://openalex.org/W3175234951","https://openalex.org/W3201770677","https://openalex.org/W3203949114","https://openalex.org/W4214526701","https://openalex.org/W4214624153","https://openalex.org/W4214684415","https://openalex.org/W4224988000","https://openalex.org/W4286744945","https://openalex.org/W4287992068","https://openalex.org/W4288065874","https://openalex.org/W4303649010","https://openalex.org/W4307504011","https://openalex.org/W4312749817","https://openalex.org/W4312815172","https://openalex.org/W4312852845","https://openalex.org/W4377711491","https://openalex.org/W4382457953","https://openalex.org/W4386075724","https://openalex.org/W4390871962","https://openalex.org/W4390872495","https://openalex.org/W4390872914","https://openalex.org/W4390872957","https://openalex.org/W4390874439","https://openalex.org/W4392449449","https://openalex.org/W4393159162","https://openalex.org/W4393178520","https://openalex.org/W4400086661","https://openalex.org/W4401070841","https://openalex.org/W4402716304","https://openalex.org/W4402727277","https://openalex.org/W4402727770","https://openalex.org/W4402753915","https://openalex.org/W6843661293"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"3D":[0,154,157],"referring":[1,155,163],"segmentation":[2],"is":[3,33,185],"an":[4,115],"emerging":[5],"and":[6,37,52,81,130,139,160],"challenging":[7,181],"vision-language":[8,34,106],"task":[9,32],"that":[10,119],"aims":[11],"to":[12,45,61,94,126,135],"segment":[13],"the":[14,47,75,79,105,109,121,141,180],"object":[15],"described":[16],"by":[17,78,172],"a":[18,23,57,90,173],"natural":[19],"language":[20,63],"expression":[21],"in":[22],"point":[24,85],"cloud":[25],"scene.":[26],"The":[27,146],"key":[28],"challenge":[29],"behind":[30],"this":[31,40],"feature":[35,50],"fusion":[36],"alignment.":[38],"In":[39],"work,":[41],"we":[42,55,88,113],"propose":[43,56],"RefMask3D":[44,148,167],"explore":[46],"comprehensive":[48],"multi-modal":[49],"interaction":[51],"understanding.":[53],"First,":[54],"Geometry-Enhanced":[58],"Group-Word":[59],"Attention":[60],"integrate":[62],"with":[64],"geometrically":[65],"coherent":[66],"sub-clouds":[67],"through":[68],"cross-modal":[69],"group-word":[70],"attention,":[71],"which":[72,102],"effectively":[73],"addresses":[74],"challenges":[76],"posed":[77],"sparse":[80],"irregular":[82],"nature":[83],"of":[84,143,176],"clouds.":[86],"Then,":[87],"introduce":[89,114],"Linguistic":[91],"Primitives":[92],"Construction":[93],"produce":[95],"semantic":[96,100],"primitives":[97,125],"representing":[98],"distinct":[99],"attributes,":[101],"greatly":[103],"enhance":[104,140],"understanding":[107],"at":[108,187],"decoding":[110],"stage.":[111],"Furthermore,":[112],"Object":[116],"Cluster":[117],"Module":[118],"analyzes":[120],"interrelationships":[122],"among":[123],"linguistic":[124],"consolidate":[127],"their":[128],"insights":[129],"pinpoint":[131],"common":[132],"characteristics,":[133],"helping":[134],"capture":[136],"holistic":[137],"information":[138],"precision":[142],"target":[144],"identification.":[145],"proposed":[147],"achieves":[149],"new":[150],"state-of-the-art":[151,170],"performance":[152],"on":[153,179],"segmentation,":[156],"visual":[158],"grounding,":[159],"also":[161],"2D":[162],"image":[164],"segmentation.":[165],"Especially,":[166],"outperforms":[168],"previous":[169],"method":[171],"large":[174],"margin":[175],"3.16%":[177],"mIoU":[178],"ScanRefer":[182],"dataset.":[183],"Code":[184],"available":[186],"https://github.com/heshuting555/RefMask3D.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}