{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:50:20Z","timestamp":1757616620343,"version":"3.44.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tvcg.2025.3564664","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T13:33:30Z","timestamp":1745847210000},"page":"8129-8142","source":"Crossref","is-referenced-by-count":0,"title":["Diff-3DCap: Shape Captioning With Diffusion Models"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5733-6638","authenticated-orcid":false,"given":"Zhenyu","family":"Shu","sequence":"first","affiliation":[{"name":"School of Computer and Data Engineering, NingboTech University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9690-1211","authenticated-orcid":false,"given":"Jiawei","family":"Wen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7788-0418","authenticated-orcid":false,"given":"Shiyang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8452-8723","authenticated-orcid":false,"given":"Shiqing","family":"Xin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, ShanDong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4352-1431","authenticated-orcid":false,"given":"Ligang","family":"Liu","sequence":"additional","affiliation":[{"name":"Graphics & Geometric Computing Laboratory, School of Mathematical Sciences, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301126"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413889"},{"key":"ref4","first-page":"75307","article-title":"Scalable 3D captioning with pretrained models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref6","first-page":"19 730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"article-title":"GPT-4 technical report","year":"2023","author":"Achiam","key":"ref8"},{"key":"ref9","first-page":"44860","article-title":"OpenShape: Scaling up 3D shape representation towards open-world understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref11","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00815"},{"key":"ref14","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref15","first-page":"4328","article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref16","first-page":"39 957","article-title":"AR-diffusion: Auto-regressive diffusion model for text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref17","first-page":"35","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gong"},{"key":"ref18","first-page":"21 051","article-title":"Text generation with diffusion language models: A pre-training approach with continuous paragraph denoise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"article-title":"GENIE: Large scale pre-training for text generation with diffusion model","year":"2022","author":"Lin","key":"ref19"},{"key":"ref20","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"article-title":"Imagen Video: High definition video generation with diffusion models","year":"2022","author":"Ho","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00590"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3357568"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3388514"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"article-title":"Masked non-autoregressive image captioning","year":"2019","author":"Gao","key":"ref43"},{"article-title":"ShapeNet: An information-rich 3D model repository","year":"2015","author":"Chang","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_11"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref47","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":"ref48","first-page":"169","article-title":"Minimum Bayes-Risk decoding for statistical machine translation","volume-title":"Proc. Hum. Lang. Technol. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Kumar"},{"key":"ref49","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":"ref50","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref54","first-page":"120","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11837"},{"article-title":"Cross-modal retrieval with implicit concept association","year":"2018","author":"Song","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref58","first-page":"20 482","article-title":"3D-LLM: Injecting the 3D world into large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong"},{"article-title":"GPT-4o system card","year":"2024","author":"Hurst","key":"ref59"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11151252\/10978057.pdf?arnumber=10978057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T19:16:59Z","timestamp":1757099819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10978057\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":59,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3564664","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"type":"print","value":"1077-2626"},{"type":"electronic","value":"1941-0506"},{"type":"electronic","value":"2160-9306"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}