{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:09:19Z","timestamp":1769558959065,"version":"3.49.0"},"reference-count":141,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"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":["62002314"],"award-info":[{"award-number":["62002314"]}],"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":["62125201"],"award-info":[{"award-number":["62125201"]}],"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":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"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":["62022083"],"award-info":[{"award-number":["62022083"]}],"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":["62236008"],"award-info":[{"award-number":["62236008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LY23F020005"],"award-info":[{"award-number":["LY23F020005"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tcsvt.2023.3296889","type":"journal-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T21:11:48Z","timestamp":1689801108000},"page":"1322-1338","source":"Crossref","is-referenced-by-count":15,"title":["A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6918-3157","authenticated-orcid":false,"given":"Ting","family":"Yu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"given":"Xiaojun","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-0527","authenticated-orcid":false,"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9680-5126","authenticated-orcid":false,"given":"Weiguo","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1167\/7.1.10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3155795"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00640"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00643"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref20","first-page":"1","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00217"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/194"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref28","article-title":"D3Net: Densely connected multidilated DenseNet for music source separation","author":"Takahashi","year":"2020","journal-title":"arXiv:2010.01733"},{"key":"ref29","article-title":"Contextual modeling for 3D dense captioning on point clouds","author":"Zhong","year":"2022","journal-title":"arXiv:2210.03925"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref38","article-title":"Graph neural networks in vision-language image understanding: A survey","author":"Senior","year":"2023","journal-title":"arXiv:2303.03761"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref46","first-page":"1","article-title":"Faster R-CNN: Towards realtime object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref47","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv:1609.02907"},{"key":"ref48","first-page":"1","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Herdade"},{"key":"ref49","first-page":"10575","article-title":"Meshedmemory transformer for image captioning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Cornia"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"8","key":"ref51","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref58","first-page":"1","article-title":"Adaptively aligned image captioning via adaptive attention time","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Huang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6898"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref62","first-page":"1","article-title":"High-order attention models for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Schwartz"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02247"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350913"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01462"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.226"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.83"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref70","article-title":"UniVL: A unified video and language pretraining model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv:2002.06353"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref75","article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","author":"Iashin","year":"2020","journal-title":"arXiv:2005.08271"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00677"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00030"},{"key":"ref84","article-title":"End-to-end dense video captioning as sequence generation","author":"Zhu","year":"2022","journal-title":"arXiv:2204.08121"},{"key":"ref85","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Gan"},{"key":"ref86","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3276518"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3272734"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref94","article-title":"Learning point-language hierarchical alignment for 3D visual grounding","author":"Chen","year":"2022","journal-title":"arXiv:2210.12513"},{"issue":"1","key":"ref95","first-page":"411","article-title":"spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing","volume":"7","author":"Honnibal","year":"2017","journal-title":"Appear"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref99","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.377"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.94"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref108","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv:1512.03012"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925867"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref114","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.","author":"Banerjee"},{"key":"ref115","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref117","first-page":"1","article-title":"Koehn, re-evaluation the role of Bleu in machine translation research","volume-title":"Proc. 11th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Callison-Burch"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1108\/00220410410560582"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.131"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"ref132","article-title":"ENet: A deep neural network architecture for real-time semantic segmentation","author":"Paszke","year":"2016","journal-title":"arXiv:1606.02147"},{"key":"ref133","article-title":"Learning 3D representations from 2D pre-trained models via image-to-point masked autoencoders","author":"Zhang","year":"2022","journal-title":"arXiv:2212.06785"},{"key":"ref134","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref135","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","author":"Chen","year":"2022","journal-title":"arXiv:2208.04202"},{"key":"ref136","article-title":"Semantic-conditional diffusion networks for image captioning","author":"Luo","year":"2022","journal-title":"arXiv:2212.03099"},{"key":"ref137","volume-title":"Gpt-4 Technical Report","year":"2023"},{"key":"ref138","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16249"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10461325\/10187165.pdf?arnumber=10187165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T19:01:03Z","timestamp":1709924463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10187165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":141,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3296889","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}