{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:12:10Z","timestamp":1783768330989,"version":"3.55.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"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"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY23F020005"],"award-info":[{"award-number":["LY23F020005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02357-z","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:00:27Z","timestamp":1778047227000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CloudCap3D: enhancing 3D in-scene descriptions via point cloud integration and efficient text filtering"],"prefix":"10.1007","volume":"32","author":[{"given":"Zhiyuan","family":"Niu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyi","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tieqiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"2357_CR1","doi-asserted-by":"crossref","unstructured":"Nguyen, T.-T., Nguyen, P., Luu, K.: Hig: Hierarchical interlacement graph approach to scene graph generation in video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18384\u201318394 (2024)","DOI":"10.1109\/CVPR52733.2024.01740"},{"key":"2357_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Xu, Y., Shen, Y., Dai, B., Zhou, B., Yang, C.: Berfscene: Bev-conditioned equivariant radiance fields for infinite 3d scene generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6839\u20136849 (2024)","DOI":"10.1109\/CVPR52733.2024.00653"},{"key":"2357_CR3","doi-asserted-by":"crossref","unstructured":"Kim, K., Yoon, K., Jeon, J., In, Y., Moon, J., Kim, D., Park, C.: Llm4sgg: Large language models for weakly supervised scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28306\u201328316 (2024)","DOI":"10.1109\/CVPR52733.2024.02674"},{"key":"2357_CR4","doi-asserted-by":"crossref","unstructured":"Ning, S., Wang, D., Qin, Y., Jin, Z., Wang, B., Han, X.: Picture: Photorealistic virtual try-on from unconstrained designs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6976\u20136985 (2024)","DOI":"10.1109\/CVPR52733.2024.00666"},{"key":"2357_CR5","doi-asserted-by":"crossref","unstructured":"Yang, X., Ding, C., Hong, Z., Huang, J., Tao, J., Xu, X.: Texture-preserving diffusion models for high-fidelity virtual try-on. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7017\u20137026 (2024)","DOI":"10.1109\/CVPR52733.2024.00670"},{"key":"2357_CR6","doi-asserted-by":"crossref","unstructured":"Khanna, M., Mao, Y., Jiang, H., Haresh, S., Shacklett, B., Batra, D., Clegg, A., Undersander, E., Chang, A.X., Savva, M.: Habitat synthetic scenes dataset (hssd-200): An analysis of 3d scene scale and realism tradeoffs for objectgoal navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16384\u201316393 (2024)","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"2357_CR7","doi-asserted-by":"crossref","unstructured":"Ehsani, K., Gupta, T., Hendrix, R., Salvador, J., Weihs, L., Zeng, K.-H., Singh, K.P., Kim, Y., Han, W., Herrasti, A., Krishna, R., Schwenk, D., VanderBilt, E., Kembhavi, A.: Spoc: Imitating shortest paths in simulation enables effective navigation and manipulation in the real world. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16238\u201316250 (2024)","DOI":"10.1109\/CVPR52733.2024.01537"},{"issue":"9","key":"2357_CR8","doi-asserted-by":"publisher","first-page":"7998","DOI":"10.1109\/TCSVT.2024.3384311","volume":"34","author":"F Chu","year":"2024","unstructured":"Chu, F., Cong, Y., Chen, R.: Open: Occlusion-invariant perception network for single image-based 3d shape retrieval. IEEE Trans. Circuits Syst. Video Technol. 34(9), 7998\u20138012 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2024.3384311","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"7","key":"2357_CR9","doi-asserted-by":"publisher","first-page":"5589","DOI":"10.1109\/TCSVT.2024.3358850","volume":"34","author":"Z Yu","year":"2024","unstructured":"Yu, Z., Li, L., Xie, J., Wang, C., Li, W., Ning, X.: Pedestrian 3d shape understanding for person re-identification via multi-view learning. IEEE Trans. Circuits Syst. Video Technol. 34(7), 5589\u20135602 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2024.3358850","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2357_CR10","doi-asserted-by":"crossref","unstructured":"Ju, X., Huang, Z., Li, Y., Zhang, G., Qiao, Y., Li, H.: Diffindscene: Diffusion-based high-quality 3d indoor scene generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4526\u20134535 (2024)","DOI":"10.1109\/CVPR52733.2024.00433"},{"key":"2357_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, Y., Guo, X., Yang, R., Li, W.: Leveraging predicate and triplet learning for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28369\u201328379 (2024)","DOI":"10.1109\/CVPR52733.2024.02680"},{"issue":"6","key":"2357_CR12","doi-asserted-by":"publisher","first-page":"3697","DOI":"10.1109\/TCSVT.2021.3107153","volume":"32","author":"M Xi","year":"2022","unstructured":"Xi, M., Zhou, Y., Chen, Z., Zhou, W., Li, H.: Anti-distractor active object tracking in 3d environments. IEEE Trans. Circuits Syst. Video Technol. 32(6), 3697\u20133707 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3107153","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2357_CR13","doi-asserted-by":"crossref","unstructured":"Cha, J., Kim, J., Yoon, J.S., Baek, S.: Text2hoi: Text-guided 3d motion generation for hand-object interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1577\u20131585 (2024)","DOI":"10.1109\/CVPR52733.2024.00156"},{"key":"2357_CR14","doi-asserted-by":"crossref","unstructured":"Yu, T., Lin, X., Wang, S., Sheng, W., Huang, Q., Yu, J.: A comprehensive survey of 3d dense captioning: Localizing and describing objects in 3d scenes. IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3296889"},{"key":"2357_CR15","doi-asserted-by":"crossref","unstructured":"Luo, T., Rockwell, C., Lee, H., Johnson, J.: Scalable 3d captioning with pretrained models. Advances in Neural Information Processing Systems 36 (2024)","DOI":"10.52202\/075280-3291"},{"key":"2357_CR16","doi-asserted-by":"crossref","unstructured":"Luo, T., Rockwell, C., al., L.: Scalable 3d captioning with pretrained models. arXiv preprint arXiv:2306.07279 (2023)","DOI":"10.52202\/075280-3291"},{"key":"2357_CR17","doi-asserted-by":"crossref","unstructured":"Hu, A., Chen, S., al., Z.: Explore and tell: Embodied visual captioning in 3d environments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2482\u20132491 (2023)","DOI":"10.1109\/ICCV51070.2023.00235"},{"key":"2357_CR18","unstructured":"Hong, F., Tang, J., Cao, Z., Shi, M., Wu, T., Chen, Z., Wang, T., Pan, L., Lin, D., Liu, Z.: 3dtopia: Large text-to-3d generation model with hybrid diffusion priors. arXiv preprint arXiv:2403.02234 (2024)"},{"key":"2357_CR19","doi-asserted-by":"crossref","unstructured":"Qi, Z., Fang, Y., Sun, Z., Wu, X., Wu, T., Wang, J., Lin, D., Zhao, H.: GPT4Point: A Unified Framework for Point-Language Understanding and Generation (2023)","DOI":"10.1109\/CVPR52733.2024.02495"},{"key":"2357_CR20","unstructured":"OpenAI: Gpt-4v(ision) system card (2023). https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf"},{"issue":"240","key":"2357_CR21","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H.W., Sutton, C., Gehrmann, S., et al.: Palm: Scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"2357_CR22","unstructured":"Li, J., Li, D., al., S.S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"2357_CR23","doi-asserted-by":"crossref","unstructured":"Deitke, M., Liu, R., al., M.W.: Objaverse-xl: A universe of 10m+ 3d objects. arXiv preprint arXiv:2307.05663 (2023)","DOI":"10.52202\/075280-1554"},{"key":"2357_CR24","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., al., M.F.: CLIPScore: A Reference-free Evaluation Metric for Image Captioning (2022)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"2357_CR25","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, X., al., W.: Pointllm: Empowering large language models to understand point clouds. arXiv preprint arXiv:2308.16911 (2023)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"2357_CR26","doi-asserted-by":"crossref","unstructured":"Hong, Y., Zhen, H., al., C.: 3d-llm: Injecting the 3d world into large language models. NeurIPS (2023)","DOI":"10.52202\/075280-0900"},{"key":"2357_CR27","unstructured":"Huang, J., Yong, S., Ma, X., Linghu, X., Li, P., Wang, Y., Li, Q., Zhu, S.-C., Jia, B., Huang, S.: An embodied generalist agent in 3d world. In: Proceedings of the International Conference on Machine Learning (ICML) (2024)"},{"key":"2357_CR28","doi-asserted-by":"publisher","unstructured":"Ilharco, G., Wortsman, M., al., W.: OpenCLIP. https:\/\/doi.org\/10.5281\/zenodo.5143773 . If you use this software, please cite it as below. https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"2357_CR29","doi-asserted-by":"crossref","unstructured":"Hegde, D., Valanarasu, J.M.J., al., P.: Clip goes 3d: Leveraging prompt tuning for language grounded 3d recognition. arXiv preprint arXiv:2303.11313 (2023)","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"2357_CR30","unstructured":"Zhou, J., Wang, J., Ma, B., Liu, Y.-S., Huang, T., Wang, X.: Uni3d: Exploring unified 3d representation at scale. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"2357_CR31","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.imavis.2016.04.002","volume":"55","author":"T Li","year":"2016","unstructured":"Li, T., Meng, Z., Ni, B., Shen, J., Wang, M.: Robust geometric p-norm feature pooling for image classification and action recognition. Image Vis. Comput. 55, 64\u201376 (2016)","journal-title":"Image Vis. Comput."},{"issue":"4","key":"2357_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2856058","volume":"7","author":"T Li","year":"2016","unstructured":"Li, T., Cheng, B., Ni, B., Liu, G., Yan, S.: Multitask low-rank affinity graph for image segmentation and image annotation. ACM Transactions on Intelligent Systems and Technology (TIST) 7(4), 1\u201318 (2016)","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"2357_CR33","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gholami, A., Nie\u00dfner, M., Chang, A.X.: Scan2cap: Context-aware dense captioning in rgb-d scans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3193\u20133203 (2021)","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"2357_CR34","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Wu, Q., al., M.N.: D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding (2022)","DOI":"10.1007\/978-3-031-19824-3_29"},{"key":"2357_CR35","doi-asserted-by":"crossref","unstructured":"Mao, A., Yang, Z., al., W.C.: Complete 3d relationships extraction modality alignment network for 3d dense captioning. IEEE Transactions on Visualization and Computer Graphics (2023)","DOI":"10.1109\/TVCG.2023.3279204"},{"key":"2357_CR36","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Chen, S., Jie, Z., Chen, J., Ma, L., Jiang, Y.-G.: More: Multi-order relation mining for dense captioning in 3d scenes. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXV, pp. 528\u2013545 (2022). Springer","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"2357_CR37","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhao, L., Zhang, J., Sheng, L., Xu, D.: 3djcg: A unified framework for joint dense captioning and visual grounding on 3d point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16464\u201316473 (2022)","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"2357_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, C., al., J.Y.: Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds (2022)","DOI":"10.24963\/ijcai.2022\/194"},{"key":"2357_CR39","doi-asserted-by":"crossref","unstructured":"Jin, Z., Hayat, M., al., Y.Y.: Context-aware alignment and mutual masking for 3d-language pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10984\u201310994 (2023)","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"2357_CR40","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Yan, X., al., L.: X-trans2cap: Cross-modal knowledge transfer using transformer for 3d dense captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8563\u20138573 (2022)","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"2357_CR41","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Hu, R., al., X.C.: UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding (2022)","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"2357_CR42","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhu, H., Chen, X., Lei, Y., Yu, G., Chen, T.: End-to-end 3d dense captioning with vote2cap-detr. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11124\u201311133 (2023)","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"2357_CR43","unstructured":"Zhang, X., Lu, Y., al., W.W.: GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks (2023)"},{"key":"2357_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, L., Chiang, W.-L., al., Y.S.: Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena (2023)","DOI":"10.52202\/075280-2020"},{"key":"2357_CR45","doi-asserted-by":"crossref","unstructured":"Wu, T., Yang, G., al., Z.L.: Gpt-4v(ision) is a human-aligned evaluator for text-to-3d generation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"2357_CR46","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., al., D.L.: High-Resolution Image Synthesis with Latent Diffusion Models (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2357_CR47","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2357_CR48","unstructured":"Song, Y., Sohl-Dickstein, J., al., D.P.K.: Score-Based Generative Modeling through Stochastic Differential Equations (2021)"},{"key":"2357_CR49","unstructured":"Sohl-Dickstein, J., Weiss, E.A., al., N.M.: Deep Unsupervised Learning using Nonequilibrium Thermodynamics (2015)"},{"key":"2357_CR50","unstructured":"Shi, R., Chen, H., al., Z.Z.: Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model (2023)"},{"key":"2357_CR51","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., al., B.V.H.: Zero-1-to-3: Zero-shot One Image to 3D Object (2023)","DOI":"10.1109\/ICCV51070.2023.00853"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02357-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02357-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02357-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:19:31Z","timestamp":1783765171000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02357-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2357"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02357-z","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"20 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"271"}}