{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:23:38Z","timestamp":1783113818677,"version":"3.54.6"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017691","name":"Guangxi Key Research and Development Program","doi-asserted-by":"publisher","award":["AB24010112"],"award-info":[{"award-number":["AB24010112"]}],"id":[{"id":"10.13039\/501100017691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62262006"],"award-info":[{"award-number":["62262006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007957","name":"Chongqing Municipal Education Commission","doi-asserted-by":"publisher","award":["KJZD-K202402501"],"award-info":[{"award-number":["KJZD-K202402501"]}],"id":[{"id":"10.13039\/501100007957","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115295","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T22:24:36Z","timestamp":1780957476000},"page":"115295","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Denoising diffusion bridge for cross-modal alignment in three-dimensional scene understanding"],"prefix":"10.1016","volume":"181","author":[{"given":"Junhui","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8820-8388","authenticated-orcid":false,"given":"Yong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wuyang","family":"Luan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pu","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanying","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guofan","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jintao","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115295_b1","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.engappai.2026.115295_b2","series-title":"European Conference on Computer Vision","first-page":"422","article-title":"Referit3d: Neural listeners for fine-grained 3d object identification in real-world scenes","author":"Achlioptas","year":"2020"},{"key":"10.1016\/j.engappai.2026.115295_b3","series-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2022"},{"key":"10.1016\/j.engappai.2026.115295_b4","doi-asserted-by":"crossref","unstructured":"Azuma, Daichi, Miyanishi, Taiki, Kurita, Shuhei, Kawanabe, Motoaki, 2022. Scanqa: 3d question answering for spatial scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 19129\u201319139.","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"10.1016\/j.engappai.2026.115295_b5","unstructured":"Banerjee, Satanjeev, Lavie, Alon, 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/Or Summarization. pp. 65\u201372."},{"key":"10.1016\/j.engappai.2026.115295_b6","doi-asserted-by":"crossref","unstructured":"Cai, Daigang, Zhao, Lichen, Zhang, Jing, Sheng, Lu, Xu, Dong, 2022. 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.","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"10.1016\/j.engappai.2026.115295_b7","series-title":"7th IEEE International Conference on 3D Vision, 3DV 2017","first-page":"667","article-title":"Matterport3D: Learning from RGB-d data in indoor environments","author":"Chang","year":"2018"},{"key":"10.1016\/j.engappai.2026.115295_b8","series-title":"European Conference on Computer Vision","first-page":"202","article-title":"Scanrefer: 3d object localization in rgb-d scans using natural language","author":"Chen","year":"2020"},{"key":"10.1016\/j.engappai.2026.115295_b9","doi-asserted-by":"crossref","unstructured":"Chen, Sijin, Chen, Xin, Zhang, Chi, Li, Mingsheng, Yu, Gang, Fei, Hao, Zhu, Hongyuan, Fan, Jiayuan, Chen, Tao, 2024. Ll3da: Visual interactive instruction tuning for omni-3d understanding reasoning and planning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 26428\u201326438.","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"10.1016\/j.engappai.2026.115295_b10","doi-asserted-by":"crossref","unstructured":"Chen, Zhenyu, Gholami, Ali, Nie\u00dfner, Matthias, Chang, Angel X, 2021. 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.","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"10.1016\/j.engappai.2026.115295_b11","doi-asserted-by":"crossref","unstructured":"Chen, Zhenyu, Hu, Ronghang, Chen, Xinlei, Nie\u00dfner, Matthias, Chang, Angel X, 2023. Unit3d: A unified transformer for 3d dense captioning and visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 18109\u201318119.","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"10.1016\/j.engappai.2026.115295_b12","doi-asserted-by":"crossref","unstructured":"Chen, Dave Zhenyu, Wu, Qirui, Nie\u00dfner, Matthias, Chang, Angel X., 2021. D3net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in rgb-d scans.","DOI":"10.1007\/978-3-031-19824-3_29"},{"key":"10.1016\/j.engappai.2026.115295_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112866","article-title":"Segmentation-enhanced medical visual question answering with mask-prompt alignment using contrastive learning and multitask object grounding","volume":"163","author":"Chen","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115295_b14","series-title":"Grounded 3d-llm with referent tokens","author":"Chen","year":"2024"},{"key":"10.1016\/j.engappai.2026.115295_b15","doi-asserted-by":"crossref","unstructured":"Chen, Sijin, Zhu, Hongyuan, Chen, Xin, Lei, Yinjie, Yu, Gang, Chen, Tao, 2023. 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.","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"10.1016\/j.engappai.2026.115295_b16","doi-asserted-by":"crossref","first-page":"135062","DOI":"10.52202\/079017-4293","article-title":"Spatialrgpt: Grounded spatial reasoning in vision-language models","volume":"37","author":"Cheng","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115295_b17","doi-asserted-by":"crossref","unstructured":"Dai, Angela, Chang, Angel X, Savva, Manolis, Halber, Maciej, Funkhouser, Thomas, Nie\u00dfner, Matthias, 2017. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5828\u20135839.","DOI":"10.1109\/CVPR.2017.261"},{"key":"10.1016\/j.engappai.2026.115295_b18","doi-asserted-by":"crossref","first-page":"49250","DOI":"10.52202\/075280-2142","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115295_b19","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115295_b20","unstructured":"Driess, Danny, Xia, Fei, Sajjadi, Mehdi SM, Lynch, Corey, Chowdhery, Aakanksha, Ichter, Brian, Wahid, Ayzaan, Tompson, Jonathan, Vuong, Quan, Yu, Tianhe, et al., 2023. PaLM-E: an embodied multimodal language model. In: Proceedings of the 40th International Conference on Machine Learning. pp. 8469\u20138488."},{"key":"10.1016\/j.engappai.2026.115295_b21","series-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023"},{"issue":"4","key":"10.1016\/j.engappai.2026.115295_b22","doi-asserted-by":"crossref","first-page":"asaf048","DOI":"10.1093\/biomet\/asaf048","article-title":"Simulating diffusion bridges with score matching","volume":"112","author":"Heng","year":"2025","journal-title":"Biometrika"},{"key":"10.1016\/j.engappai.2026.115295_b23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115295_b24","unstructured":"Ho, Jonathan, Salimans, Tim, 2021. Classifier-Free Diffusion Guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications."},{"key":"10.1016\/j.engappai.2026.115295_b25","doi-asserted-by":"crossref","first-page":"20482","DOI":"10.52202\/075280-0900","article-title":"3D-llm: Injecting the 3d world into large language models","volume":"36","author":"Hong","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115295_b26","doi-asserted-by":"crossref","first-page":"113991","DOI":"10.52202\/079017-3620","article-title":"Chat-scene: Bridging 3d scene and large language models with object identifiers","volume":"37","author":"Huang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115295_b27","series-title":"Chat-3d v2: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2023"},{"key":"10.1016\/j.engappai.2026.115295_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.jestch.2025.102232","article-title":"MRAN-VQA: Multimodal recursive attention network for visual question answering","volume":"72","author":"Islam","year":"2025","journal-title":"Eng. Sci. Technol. an Int. J."},{"key":"10.1016\/j.engappai.2026.115295_b29","series-title":"Opt-iml: Scaling language model instruction meta learning through the lens of generalization","author":"Iyer","year":"2022"},{"key":"10.1016\/j.engappai.2026.115295_b30","series-title":"International Conference on Machine Learning","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022"},{"key":"10.1016\/j.engappai.2026.115295_b31","series-title":"European Conference on Computer Vision","first-page":"528","article-title":"More: Multi-order relation mining for dense captioning in 3d scenes","author":"Jiao","year":"2022"},{"key":"10.1016\/j.engappai.2026.115295_b32","doi-asserted-by":"crossref","unstructured":"Jin, Zhao, Hayat, Munawar, Yang, Yuwei, Guo, Yulan, Lei, Yinjie, 2023. 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.","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"10.1016\/j.engappai.2026.115295_b33","doi-asserted-by":"crossref","first-page":"26565","DOI":"10.52202\/068431-1926","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115295_b34","doi-asserted-by":"crossref","unstructured":"Li, Bo, Xue, Kaitao, Liu, Bin, Lai, Yu-Kun, 2023. Bbdm: Image-to-image translation with brownian bridge diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1952\u20131961.","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"10.1016\/j.engappai.2026.115295_b35","series-title":"2024 IEEE International Conference on Multimedia and Expo Workshops","first-page":"1","article-title":"3Dmit: 3d multi-modal instruction tuning for scene understanding","author":"Li","year":"2024"},{"key":"10.1016\/j.engappai.2026.115295_b36","unstructured":"Lin, Chin-Yew, 2004. Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out. pp. 74\u201381."},{"key":"10.1016\/j.engappai.2026.115295_b37","doi-asserted-by":"crossref","unstructured":"Liu, Guisheng, Li, Yi, Fei, Zhengcong, Fu, Haiyan, Luo, Xiangyang, Guo, Yanqing, 2024. Prefix-diffusion: A lightweight diffusion model for diverse image captioning. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). pp. 12954\u201312965.","DOI":"10.63317\/4maaeqcvvp4d"},{"key":"10.1016\/j.engappai.2026.115295_b38","unstructured":"Liu, Xingchao, Wu, Lemeng, Ye, Mao, et al., 2022. Let us Build Bridges: Understanding and Extending Diffusion Generative Models. In: NeurIPS 2022 Workshop on Score-Based Methods."},{"key":"10.1016\/j.engappai.2026.115295_b39","unstructured":"Loshchilov, Ilya, Hutter, Frank, 2019. Decoupled Weight Decay Regularization. In: International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115295_b40","doi-asserted-by":"crossref","unstructured":"Lugmayr, Andreas, Danelljan, Martin, Romero, Andres, Yu, Fisher, Timofte, Radu, Van Gool, Luc, 2022. Repaint: Inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11461\u201311471.","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"10.1016\/j.engappai.2026.115295_b41","doi-asserted-by":"crossref","first-page":"50898","DOI":"10.52202\/079017-1611","article-title":"Mmscan: A multi-modal 3d scene dataset with hierarchical grounded language annotations","volume":"37","author":"Lyu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115295_b42","series-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2022"},{"issue":"8","key":"10.1016\/j.engappai.2026.115295_b43","doi-asserted-by":"crossref","first-page":"4867","DOI":"10.1109\/TVCG.2023.3279204","article-title":"Complete 3d relationships extraction modality alignment network for 3d dense captioning","volume":"30","author":"Mao","year":"2023","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.engappai.2026.115295_b44","doi-asserted-by":"crossref","unstructured":"Papineni, Kishore, Roukos, Salim, Ward, Todd, Zhu, Wei-Jing, 2002. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.engappai.2026.115295_b45","doi-asserted-by":"crossref","unstructured":"Rombach, Robin, Blattmann, Andreas, Lorenz, Dominik, Esser, Patrick, Ommer, Bj\u00f6rn, 2022. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.engappai.2026.115295_b46","doi-asserted-by":"crossref","unstructured":"Saharia, Chitwan, Chan, William, Chang, Huiwen, Lee, Chris, Ho, Jonathan, Salimans, Tim, Fleet, David, Norouzi, Mohammad, 2022. Palette: Image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings. pp. 1\u201310.","DOI":"10.1145\/3528233.3530757"},{"key":"10.1016\/j.engappai.2026.115295_b47","volume":"vol. 10","author":"S\u00e4rkk\u00e4","year":"2019"},{"key":"10.1016\/j.engappai.2026.115295_b48","series-title":"International Conference on Machine Learning","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015"},{"key":"10.1016\/j.engappai.2026.115295_b49","series-title":"Uncertainty in Artificial Intelligence","first-page":"1985","article-title":"Aligned diffusion schr\u00f6dinger bridges","author":"Somnath","year":"2023"},{"key":"10.1016\/j.engappai.2026.115295_b50","series-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"10.1016\/j.engappai.2026.115295_b51","unstructured":"Song, Yang, Sohl-Dickstein, Jascha, Kingma, Diederik P., Kumar, Abhishek, Ermon, Stefano, Poole, Ben, 2021. Score-Based Generative Modeling through Stochastic Differential Equations. In: International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115295_b52","doi-asserted-by":"crossref","unstructured":"Song, Chan Hee, Wu, Jiaman, Washington, Clayton, Sadler, Brian M., Chao, Wei-Lun, Su, Yu, 2023. Llm-planner: Few-shot grounded planning for embodied agents with large language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2998\u20133009.","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"10.1016\/j.engappai.2026.115295_b53","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112991","article-title":"Large-scale multimodal model based embodied intelligent robots: A survey","volume":"163","author":"Tu","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115295_b54","doi-asserted-by":"crossref","unstructured":"Vedantam, Ramakrishna, Lawrence Zitnick, C., Parikh, Devi, 2015. Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4566\u20134575.","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"10.1016\/j.engappai.2026.115295_b55","series-title":"Spatiality-guided transformer for 3d dense captioning on point clouds","author":"Wang","year":"2022"},{"key":"10.1016\/j.engappai.2026.115295_b56","unstructured":"Yang, Dejie, Xu, Zhu, Mo, Wentao, Chen, Qingchao, Huang, Siyuan, Liu, Yang, 2024. 3D vision and language pretraining with large-scale synthetic data. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. pp. 1552\u20131560."},{"issue":"3","key":"10.1016\/j.engappai.2026.115295_b57","doi-asserted-by":"crossref","first-page":"1772","DOI":"10.1109\/TVCG.2022.3225327","article-title":"3D question answering","volume":"30","author":"Ye","year":"2024","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.engappai.2026.115295_b58","series-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"issue":"6","key":"10.1016\/j.engappai.2026.115295_b59","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TCSVT.2022.3229081","article-title":"Toward explainable 3d grounded visual question answering: A new benchmark and strong baseline","volume":"33","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.115295_b60","series-title":"Contextual modeling for 3d dense captioning on point clouds","author":"Zhong","year":"2022"},{"key":"10.1016\/j.engappai.2026.115295_b61","unstructured":"Zhou, Linqi, Lou, Aaron, Khanna, Samar, Ermon, Stefano, 2024. Denoising Diffusion Bridge Models. In: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115295_b62","doi-asserted-by":"crossref","unstructured":"Zhu, Ziyu, Ma, Xiaojian, Chen, Yixin, Deng, Zhidong, Huang, Siyuan, Li, Qing, 2023. 3d-vista: Pre-trained transformer for 3d vision and text alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2911\u20132921.","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"10.1016\/j.engappai.2026.115295_b63","series-title":"Diffusion models for reinforcement learning: A survey","author":"Zhu","year":"2023"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626015794?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626015794?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T20:52:14Z","timestamp":1783111934000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626015794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":63,"alternative-id":["S0952197626015794"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115295","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Denoising diffusion bridge for cross-modal alignment in three-dimensional scene understanding","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115295","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115295"}}