{"id":"https://openalex.org/W4403792055","doi":"https://doi.org/10.1145/3664647.3680841","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","display_name":"3D-GRES: Generalized 3D Referring Expression Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792055","doi":"https://doi.org/10.1145/3664647.3680841"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680841","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/A5019828141","display_name":"Changli Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changli Wu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006484057","display_name":"Yihang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Liu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084510895","display_name":"Jiayi Ji","orcid":"https://orcid.org/0000-0002-9956-6308"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073144816","display_name":"Yiwei Ma","orcid":"https://orcid.org/0000-0002-8744-3423"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Ma","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325633","display_name":"Haowei Wang","orcid":"https://orcid.org/0009-0006-0289-9672"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haowei Wang","raw_affiliation_strings":["Youtu Lab, Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997988","display_name":"Gen Luo","orcid":"https://orcid.org/0000-0001-5334-1843"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gen Luo","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5019828141"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.7799,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7392148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7852","last_page":"7861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5629410743713379},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5194351673126221},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5087864995002747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49169331789016724},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4158194065093994},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38996073603630066},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32924598455429077},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05756175518035889}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5629410743713379},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5194351673126221},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5087864995002747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49169331789016724},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4158194065093994},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38996073603630066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32924598455429077},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05756175518035889}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680841","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W2250378130","https://openalex.org/W2251512949","https://openalex.org/W2328720669","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2594519801","https://openalex.org/W2770129969","https://openalex.org/W2798556392","https://openalex.org/W2799263800","https://openalex.org/W2904910963","https://openalex.org/W2946086442","https://openalex.org/W2952524542","https://openalex.org/W2963109634","https://openalex.org/W2963182550","https://openalex.org/W2963281829","https://openalex.org/W2963735856","https://openalex.org/W2964187781","https://openalex.org/W2964345792","https://openalex.org/W2986803748","https://openalex.org/W3008105217","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3096609285","https://openalex.org/W3107521863","https://openalex.org/W3140398265","https://openalex.org/W3169998662","https://openalex.org/W3175234951","https://openalex.org/W3183392001","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3203949114","https://openalex.org/W3206171352","https://openalex.org/W3206209177","https://openalex.org/W4212774754","https://openalex.org/W4214526701","https://openalex.org/W4224988000","https://openalex.org/W4304014690","https://openalex.org/W4307504011","https://openalex.org/W4312749817","https://openalex.org/W4320487288","https://openalex.org/W4377711491","https://openalex.org/W4382457953","https://openalex.org/W4382458695","https://openalex.org/W4385569940","https://openalex.org/W4387969417","https://openalex.org/W4387969771","https://openalex.org/W4390872957","https://openalex.org/W4390874439","https://openalex.org/W4392449449","https://openalex.org/W4393159162","https://openalex.org/W4394938913","https://openalex.org/W4395470960","https://openalex.org/W4402753940"],"related_works":["https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W4379231730","https://openalex.org/W2328518092","https://openalex.org/W4389858081","https://openalex.org/W3101249758","https://openalex.org/W2382079200","https://openalex.org/W3129895999","https://openalex.org/W2374091470","https://openalex.org/W1522196789"],"abstract_inverted_index":{"3D":[0,14,45,170],"Referring":[1,46],"Expression":[2,47],"Segmentation":[3,48],"(3D-RES)":[4],"is":[5,120],"dedicated":[6],"to":[7,27,54,79,129,139],"segmenting":[8,28],"a":[9,13,18,29,145,164],"specific":[10],"instance":[11],"within":[12],"space":[15],"based":[16,60],"on":[17,61,153],"natural":[19,62],"language":[20,63],"description.":[21],"However,":[22],"current":[23],"approaches":[24],"are":[25,177],"limited":[26],"single":[30],"target,":[31],"restricting":[32],"the":[33,36,52,72,114],"versatility":[34],"of":[35,58],"task.":[37],"To":[38,137],"overcome":[39],"this":[40,67,140,154],"limitation,":[41],"we":[42,70,143],"introduce":[43],"Generalized":[44],"(3D-GRES),":[49],"which":[50],"extends":[51],"capability":[53],"segment":[55],"any":[56],"number":[57],"instances":[59],"instructions.":[64],"In":[65],"addressing":[66],"broader":[68],"task,":[69,142],"propose":[71],"Multi-Query":[73],"Decoupled":[74],"Interaction":[75],"Network":[76],"(MDIN),":[77],"designed":[78],"break":[80],"down":[81],"multi-object":[82,127,169],"segmentation":[83],"tasks":[84],"into":[85],"simpler,":[86],"individual":[87],"segmentations.":[88],"MDIN":[89],"comprises":[90],"two":[91],"fundamental":[92],"components:":[93],"Text-driven":[94],"Sparse":[95],"Queries":[96],"(TSQ)":[97],"and":[98,175],"Multi-object":[99],"Decoupling":[100],"Optimization":[101],"(MDO).":[102],"TSQ":[103],"generates":[104],"sparse":[105],"point":[106],"cloud":[107],"features":[108],"distributed":[109],"over":[110,159],"key":[111],"targets":[112],"as":[113],"initialization":[115],"for":[116,167],"queries.":[117],"Meanwhile,":[118],"MDO":[119],"tasked":[121],"with":[122],"assigning":[123],"each":[124],"target":[125],"in":[126],"scenarios":[128],"different":[130],"queries":[131],"while":[132],"maintaining":[133],"their":[134],"semantic":[135],"consistency.":[136],"adapt":[138],"new":[141,146,165],"build":[144],"dataset,":[147],"namely":[148],"Multi3DRes.":[149],"Our":[150],"comprehensive":[151],"evaluations":[152],"dataset":[155],"demonstrate":[156],"substantial":[157],"enhancements":[158],"existing":[160],"models,":[161],"thus":[162],"charting":[163],"path":[166],"intricate":[168],"scene":[171],"comprehension.":[172],"The":[173],"benchmark":[174],"code":[176],"available":[178],"at":[179],"https://github.com/sosppxo/MDIN.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}