{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:11:50Z","timestamp":1778080310846,"version":"3.51.4"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071127"],"award-info":[{"award-number":["62071127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101137"],"award-info":[{"award-number":["62101137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022ZD0160100"],"award-info":[{"award-number":["2022ZD0160100"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["23ZR1402900"],"award-info":[{"award-number":["23ZR1402900"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["M23L7b0021"],"award-info":[{"award-number":["M23L7b0021"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"A*STAR AME Programmatic Funding","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]},{"name":"RobotHTPO Seed Fund","award":["C211518008"],"award-info":[{"award-number":["C211518008"]}]},{"name":"EDB Space Technology Development","award":["S22-19016-STDP"],"award-info":[{"award-number":["S22-19016-STDP"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2013"],"award-info":[{"award-number":["U23B2013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276176"],"award-info":[{"award-number":["62276176"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tpami.2024.3387838","type":"journal-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T17:27:38Z","timestamp":1712942858000},"page":"7331-7347","source":"Crossref","is-referenced-by-count":26,"title":["Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1319-746X","authenticated-orcid":false,"given":"Sijin","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5177-8320","authenticated-orcid":false,"given":"Hongyuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup> R) and Centre for Frontier AI Research (CFAR), A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3758-0018","authenticated-orcid":false,"given":"Mingsheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9347-1367","authenticated-orcid":false,"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9848-2272","authenticated-orcid":false,"given":"Peng","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-3342","authenticated-orcid":false,"given":"Yinjie","family":"Lei","sequence":"additional","affiliation":[{"name":"Sichuan University, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5570-2710","authenticated-orcid":false,"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3279-7125","authenticated-orcid":false,"given":"Taihao","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9818","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref4","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref5","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref10","article-title":"Unit3D: A unified transformer for 3D dense captioning and visual grounding","author":"Chen","year":"2022"},{"key":"ref11","article-title":"D3Net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in RGB-D scans","author":"Chen","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00047"},{"key":"ref13","article-title":"Group DETR: Fast training convergence with decoupled one-to-many label assignment","author":"Chen","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref15","article-title":"Conditional DETR V2: Efficient detection transformer with box queries","author":"Chen","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref21","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083288"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref29","article-title":"DETRs with hybrid matching","author":"Jia","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01780"},{"key":"ref35","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref36","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059758"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00597"},{"key":"ref39","article-title":"CPTR: Full transformer network for image captioning","author":"Liu","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref41","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref43","article-title":"SQA3D: Situated question answering in 3D scenes","author":"Ma","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3279204"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3063611"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref48","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref51","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni"},{"key":"ref52","article-title":"ENet: A deep neural network architecture for real-time semantic segmentation","author":"Paszke","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref54","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref55","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref57","first-page":"1046","article-title":"LanguageRefer: Spatial-language model for 3D visual grounding","volume-title":"Proc. Conf. Robot Learn.","author":"Roh"},{"key":"ref58","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"Tancik","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/194"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262786"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3225327"},{"key":"ref69","first-page":"12705","article-title":"Coordinates are not lonely-codebook prior helps implicit neural 3D representations","volume":"35","author":"Yin","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref71","article-title":"DETR++: Taming your multi-scale detection transformer","author":"Zhang","year":"2022"},{"key":"ref72","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102025"},{"key":"ref75","article-title":"Contextual modeling for 3D dense captioning on point clouds","author":"Zhong","year":"2022"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref77","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref78","article-title":"Exploring discrete diffusion models for image captioning","author":"Zhu","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10704791\/10496863.pdf?arnumber=10496863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T17:36:28Z","timestamp":1728063388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10496863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":79,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3387838","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}