{"id":"https://openalex.org/W4394773594","doi":"https://doi.org/10.1109/tpami.2024.3387838","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","display_name":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394773594","doi":"https://doi.org/10.1109/tpami.2024.3387838","pmid":"https://pubmed.ncbi.nlm.nih.gov/38607711"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3387838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3387838","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5114804332","display_name":"Sijin Chen","orcid":"https://orcid.org/0009-0008-1319-746X"},"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":"Sijin Chen","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-1319-746X","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015639955","display_name":"Hongyuan Zhu","orcid":"https://orcid.org/0000-0001-5177-8320"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongyuan Zhu","raw_affiliation_strings":["Institute for Infocomm Research (I<sup>2</sup> R) and Centre for Frontier AI Research (CFAR), A*STAR, Singapore","Institute for Infocomm Research (I2 R) and Centre for Frontier AI Research (CFAR), A*STAR, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5177-8320","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I<sup>2</sup> R) and Centre for Frontier AI Research (CFAR), A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2 R) and Centre for Frontier AI Research (CFAR), A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698381","display_name":"Mingsheng Li","orcid":"https://orcid.org/0009-0004-3758-0018"},"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":"Mingsheng Li","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-3758-0018","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363100","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-9347-1367"},"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":"Xin Chen","raw_affiliation_strings":["Tencent PCG, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9347-1367","affiliations":[{"raw_affiliation_string":"Tencent PCG, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114804035","display_name":"Peng Guo","orcid":"https://orcid.org/0009-0006-9848-2272"},"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":"Peng Guo","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-9848-2272","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102831936","display_name":"Yinjie Lei","orcid":"https://orcid.org/0000-0001-6856-3342"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinjie Lei","raw_affiliation_strings":["Sichuan University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0001-6856-3342","affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003400275","display_name":"Gang Yu","orcid":"https://orcid.org/0000-0001-5570-2710"},"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":"Gang Yu","raw_affiliation_strings":["Tencent PCG, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5570-2710","affiliations":[{"raw_affiliation_string":"Tencent PCG, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021697903","display_name":"Taihao Li","orcid":"https://orcid.org/0000-0003-3279-7125"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taihao Li","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-3279-7125","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021220108","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0002-0779-9818"},"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":"Tao Chen","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0779-9818","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5114804332"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":5.3498,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96684538,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"46","issue":"11","first_page":"7331","last_page":"7347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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":0.9973000288009644,"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":0.8347557783126831},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.771203875541687},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6164599061012268},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.539191722869873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49769094586372375},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.452007919549942},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4213288426399231},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3399427533149719},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32318419218063354},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13203313946723938},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09700354933738708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8347557783126831},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.771203875541687},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6164599061012268},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.539191722869873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49769094586372375},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.452007919549942},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4213288426399231},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3399427533149719},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32318419218063354},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13203313946723938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09700354933738708},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3387838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3387838","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38607711","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38607711","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1972214355","display_name":null,"funder_award_id":"M23L7b0021","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"},{"id":"https://openalex.org/G3977413633","display_name":null,"funder_award_id":"62071127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5412412958","display_name":null,"funder_award_id":"62276176","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5491202952","display_name":null,"funder_award_id":"23ZR1402900","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G7626924423","display_name":null,"funder_award_id":"62101137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8813799148","display_name":null,"funder_award_id":"U23B2013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":100,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1956340063","https://openalex.org/W2108598243","https://openalex.org/W2144506857","https://openalex.org/W2194775991","https://openalex.org/W2594519801","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2963084599","https://openalex.org/W2963121255","https://openalex.org/W2963351113","https://openalex.org/W2963916161","https://openalex.org/W2979750740","https://openalex.org/W2982770724","https://openalex.org/W2986670728","https://openalex.org/W2988715931","https://openalex.org/W3034579518","https://openalex.org/W3034655362","https://openalex.org/W3034949383","https://openalex.org/W3036167779","https://openalex.org/W3036843665","https://openalex.org/W3039448353","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3095974555","https://openalex.org/W3096609285","https://openalex.org/W3107521863","https://openalex.org/W3124149278","https://openalex.org/W3132888871","https://openalex.org/W3134233478","https://openalex.org/W3162787701","https://openalex.org/W3182910454","https://openalex.org/W3188283811","https://openalex.org/W3199093552","https://openalex.org/W3203949114","https://openalex.org/W3206171352","https://openalex.org/W4200629315","https://openalex.org/W4214526701","https://openalex.org/W4214624153","https://openalex.org/W4214627427","https://openalex.org/W4214663214","https://openalex.org/W4221146106","https://openalex.org/W4221167937","https://openalex.org/W4226376247","https://openalex.org/W4281834668","https://openalex.org/W4285606658","https://openalex.org/W4286231713","https://openalex.org/W4292779060","https://openalex.org/W4293406525","https://openalex.org/W4304699901","https://openalex.org/W4306704712","https://openalex.org/W4307077525","https://openalex.org/W4307106676","https://openalex.org/W4309805488","https://openalex.org/W4310463627","https://openalex.org/W4312289196","https://openalex.org/W4312385518","https://openalex.org/W4312650216","https://openalex.org/W4318718936","https://openalex.org/W4361802179","https://openalex.org/W4377707861","https://openalex.org/W4385245566","https://openalex.org/W4386065848","https://openalex.org/W4386066792","https://openalex.org/W4386072307","https://openalex.org/W4386075583","https://openalex.org/W4386076079","https://openalex.org/W4386076628","https://openalex.org/W4390871672","https://openalex.org/W4390872240","https://openalex.org/W4390872495","https://openalex.org/W6620707391","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6717372056","https://openalex.org/W6739778489","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6780179280","https://openalex.org/W6780226713","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6789705400","https://openalex.org/W6798634944","https://openalex.org/W6803567076","https://openalex.org/W6805700901","https://openalex.org/W6809665764","https://openalex.org/W6838311405","https://openalex.org/W6841090899","https://openalex.org/W6841543928","https://openalex.org/W6846068340","https://openalex.org/W6846381433","https://openalex.org/W6846472937","https://openalex.org/W6846560892","https://openalex.org/W6847648678","https://openalex.org/W6849177959","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"3D":[0,13,37,66],"dense":[1],"captioning":[2],"requires":[3],"a":[4,26,36,75,113,197],"model":[5],"to":[6,54,118,138,150,166],"translate":[7],"its":[8],"understanding":[9],"of":[10,58,84,105,116],"an":[11,125],"input":[12],"scene":[14,106],"into":[15,133],"several":[16],"captions":[17],"associated":[18],"with":[19,39],"different":[20,103],"object":[21,88,97],"regions.":[22],"Existing":[23],"methods":[24,45,195],"adopt":[25],"sophisticated":[27],"\"detect-then-describe\"":[28,194],"pipeline,":[29],"which":[30,108,129],"builds":[31],"explicit":[32],"relation":[33],"modules":[34],"upon":[35],"detector":[38],"numerous":[40],"hand-crafted":[41],"components.":[42],"While":[43],"these":[44],"have":[46],"achieved":[47],"initial":[48],"success,":[49],"the":[50,81,131,145,167],"cascade":[51],"pipeline":[52],"tends":[53],"accumulate":[55],"errors":[56],"because":[57],"duplicated":[59],"and":[60,64,87,99,135,156,176,186,190],"inaccurate":[61],"box":[62],"estimations":[63],"messy":[65],"scenes.":[67],"In":[68],"this":[69,121],"paper,":[70],"we":[71,94,123,143],"first":[72],"propose":[73,124],"Vote2Cap-DETR,":[74],"simple-yet-effective":[76],"transformer":[77],"framework":[78],"that":[79,96],"decouples":[80,130],"decoding":[82],"process":[83],"caption":[85,136,168],"generation":[86,101],"localization":[89,98,134,158],"through":[90],"parallel":[91],"decoding.":[92],"Moreover,":[93],"argue":[95],"description":[100],"require":[102],"levels":[104],"understanding,":[107],"could":[109],"be":[110],"challenging":[111],"for":[112,153,170],"shared":[114],"set":[115],"queries":[117,132,137,152],"capture.":[119],"To":[120],"end,":[122],"advanced":[126],"version,":[127],"Vote2Cap-DETR++,":[128],"capture":[139],"task-specific":[140],"features.":[141],"Additionally,":[142],"introduce":[144],"iterative":[146],"spatial":[147,164],"refinement":[148],"strategy":[149],"vote":[151],"faster":[154],"convergence":[155],"better":[157],"performance.":[159],"We":[160],"also":[161],"insert":[162],"additional":[163],"information":[165],"head":[169],"more":[171],"accurate":[172],"descriptions.":[173],"Without":[174],"bells":[175],"whistles,":[177],"extensive":[178],"experiments":[179],"on":[180],"two":[181],"commonly":[182],"used":[183],"datasets,":[184],"ScanRefer":[185],"Nr3D,":[187],"demonstrate":[188],"Vote2Cap-DETR":[189],"Vote2Cap-DETR++":[191],"surpass":[192],"conventional":[193],"by":[196],"large":[198],"margin.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":6}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}