{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:02:40Z","timestamp":1774540960134,"version":"3.50.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"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":["61672461"],"award-info":[{"award-number":["61672461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s11554-024-01591-w","type":"journal-article","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T16:07:23Z","timestamp":1732810043000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A motion conditioned diffusion model for real-time hand trajectory semantic prediction"],"prefix":"10.1007","volume":"22","author":[{"given":"Chengfeng","family":"Jian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoran","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"issue":"4","key":"1591_CR1","doi-asserted-by":"publisher","first-page":"6687","DOI":"10.1021\/acsnano.2c01310","volume":"16","author":"J Xu","year":"2022","unstructured":"Xu, J., Li, X., Chang, H., et al.: Electrooculography and tactile perception collaborative interface for 3D human-machine interaction. J. Acs Nano 16(4), 6687\u20136699 (2022)","journal-title":"J. Acs Nano"},{"key":"1591_CR2","doi-asserted-by":"crossref","unstructured":"Sofianos, T., Sampieri, A., Franco, L., et al.: Space-time-separable graph convolutional network for pose forecasting. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 11209-11218 (2021)","DOI":"10.1109\/ICCV48922.2021.01102"},{"key":"1591_CR3","doi-asserted-by":"crossref","unstructured":"Chiu, H., Adeli, E., Wang, B., et al.: Action-agnostic human pose forecasting. In: IEEE winter conference on applications of computer vision (WACV). IEEE, pp. 1423-1432 (2019)","DOI":"10.1109\/WACV.2019.00156"},{"issue":"7","key":"1591_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3465400","volume":"54","author":"N Magrofuoco","year":"2021","unstructured":"Magrofuoco, N., Roselli, P., Vanderdonckt, J.J.A.C.S.: Two-dimensional stroke gesture recognition. A survey. ACM Comput. Surv. 54(7), 1\u201336 (2021)","journal-title":"ACM Comput. Surv."},{"key":"1591_CR5","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."},{"issue":"1","key":"1591_CR6","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1007\/s11554-023-01382-9","volume":"21","author":"C Jian","year":"2024","unstructured":"Jian, C., Wang, M., Ye, M., et al.: Real-time continuous handwritten trajectories recognition based on a regression-based temporal pyramid network. J. Real-Time Image Proc. 21(1), 10 (2024)","journal-title":"J. Real-Time Image Proc."},{"key":"1591_CR7","doi-asserted-by":"crossref","unstructured":"Flaborea, A., Collorone, L., Di, Melendugno. G.M.D.A., et al.: Multimodal motion conditioned diffusion model for skeleton-based video anomaly detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10318-10329 (2023)","DOI":"10.1109\/ICCV51070.2023.00947"},{"issue":"3","key":"1591_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11554-024-01454-4","volume":"21","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Qiao, Y., Wang, Y.: F2S-Net: learning frame-to-segment prediction for online action detection. J. Real-Time Image Proc. 21(3), 1\u201313 (2024)","journal-title":"J. Real-Time Image Proc."},{"issue":"1","key":"1591_CR9","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/s10489-021-02380-9","volume":"52","author":"C Jian","year":"2022","unstructured":"Jian, C., Liu, X., Zhang, M.: RD-Hand: a real-time regression-based detector for dynamic hand gesture. Appl. Intell. 52(1), 417\u2013428 (2022)","journal-title":"Appl. Intell."},{"issue":"3","key":"1591_CR10","doi-asserted-by":"publisher","first-page":"2862","DOI":"10.1007\/s10489-022-03524-1","volume":"53","author":"J Lian","year":"2023","unstructured":"Lian, J., Ren, W., Li, L., et al.: Ptp-stgcn: pedestrian trajectory prediction based on a spatio-temporal graph convolutional neural network. Appl. Intell. 53(3), 2862\u20132878 (2023)","journal-title":"Appl. Intell."},{"issue":"24","key":"1591_CR11","doi-asserted-by":"publisher","first-page":"31165","DOI":"10.1007\/s10489-023-05132-z","volume":"53","author":"X Yang","year":"2023","unstructured":"Yang, X., Bingxian, L., Xiangcheng, W.: SGAMTE-Net: A pedestrian trajectory prediction network based on spatiotemporal graph attention and multimodal trajectory endpoints. Appl. Intell. 53(24), 31165\u201331180 (2023)","journal-title":"Appl. Intell."},{"key":"1591_CR12","unstructured":"Ma, J., Chen, X., Bao, W., et al.: MADiff: Motion-aware mamba diffusion models for hand trajectory prediction on egocentric videos. arXiv preprint arXiv:2409.02638 (2024)"},{"key":"1591_CR13","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., et al. :Diffusiondet: Diffusion model for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 19830-19843 (2023)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"1591_CR14","unstructured":"Ramesh, A., Pavlov, M., Goh, G., et al.: Zero-shot text-to-image generation. In: International conference on machine learning. Pmlr, pp. 8821-8831 (2021)"},{"key":"1591_CR15","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et al.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10684-10695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1591_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, L., Du, Y., Wu, J.: 3d shape generation and completion through point-voxel diffusion. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 5826-5835 (2021)","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"1591_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, M., Cai, Z., Pan, L., et al. :Motiondiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"1591_CR18","unstructured":"Tevet, G., Raab, S., Gordon, B., et al.: Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)"},{"key":"1591_CR19","doi-asserted-by":"crossref","unstructured":"Tseng, J., Castellon, R., Liu, K.: Edge: editable dance generation from music. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 448-458 (2023)","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"1591_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wang, Ude B.: A unified driving engine for human motion generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5632-5641 (2023)","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"1591_CR21","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mughal, M.H., Golyanik, V., et al.: Mofusion: A framework for denoising-diffusion-based motion synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9760-9770 (2023)","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"1591_CR22","doi-asserted-by":"crossref","unstructured":"Saadatnejad, S., Rasekh, A., Mofayezi, M., et al.: A generic diffusion-based approach for 3d human pose prediction in the wild. In: 2023 IEEE international conference on robotics and automation (ICRA). IEEE, pp. 8246-8253 (2023)","DOI":"10.1109\/ICRA48891.2023.10160399"},{"key":"1591_CR23","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, B., Liu, W., et al.: Executing your commands via motion diffusion in latent space. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 18000-18010 (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"1591_CR24","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., et al.: Repaint: Inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11461-11471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"1591_CR25","first-page":"4328","volume":"35","author":"X Li","year":"2022","unstructured":"Li, X., Thickstun, J., Gulrajani, I., et al.: Diffusion-lm improves controllable text generation. Adv. Neural. Inf. Process. Syst. 35, 4328\u20134343 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1591_CR26","unstructured":"Nichol, A. Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International conference on machine learning. PMLR, pp. 8162-8171 (2021)"},{"key":"1591_CR27","doi-asserted-by":"crossref","unstructured":"Sampieri, A., di Melendugno, G.M.D.A., Avogaro, A., et al.: Pose forecasting in industrial human-robot collaboration. In: European conference on computer vision. Cham: Springer Nature Switzerland, pp. 51-69 (2022)","DOI":"10.1007\/978-3-031-19839-7_4"},{"key":"1591_CR28","doi-asserted-by":"crossref","unstructured":"Flaborea, A., Collorone, L., Di Melendugno, G.M.D.A., et al.: Multimodal motion conditioned diffusion model for skeleton-based video anomaly detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10318-10329 (2023)","DOI":"10.1109\/ICCV51070.2023.00947"},{"key":"1591_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., Cao, Z., Liang, A., et al.: Egocentric prediction of action target in 3d. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR). IEEE, pp. 20971-20980 (2022)","DOI":"10.1109\/CVPR52688.2022.02033"},{"key":"1591_CR30","doi-asserted-by":"crossref","unstructured":"Bao, W., Chen, L., Zeng, L., et al.: Uncertainty-aware state space transformer for egocentric 3d hand trajectory forecasting. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 13702-13711 (2023)","DOI":"10.1109\/ICCV51070.2023.01260"},{"issue":"6","key":"1591_CR31","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"1591_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"1591_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp. 770-778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1591_CR34","doi-asserted-by":"crossref","unstructured":"Pang, B., Zhao, T., Xie, X., et al.: Trajectory prediction with latent belief energy-based model. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11814-11824 (2021)","DOI":"10.1109\/CVPR46437.2021.01164"},{"key":"1591_CR35","doi-asserted-by":"crossref","unstructured":"Chao, Y. W., Yang, J., Price, B., et al.: Forecasting human dynamics from static images. In: IEEE conference on computer vision and pattern recognition, pp. 548-556 (2017)","DOI":"10.1109\/CVPR.2017.388"},{"key":"1591_CR36","unstructured":"Ma, J., et al.: Diff-IP2D: Diffusion-based hand-object interaction prediction on egocentric videos. arXiv preprint arXiv:2405.04370 (2024)"},{"key":"1591_CR37","unstructured":"Krishnan, R.G., Shalit, U., Sontag, D.: 11Deep kalman filters. arXiv preprint arXiv:1511.05121 (2015)"},{"key":"1591_CR38","doi-asserted-by":"crossref","unstructured":"Leglaive, S. et al.: A recurrent variational autoencoder for speech enhancement. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053164"},{"key":"1591_CR39","unstructured":"Li, Y., Mandt, S.: Disentangled sequential autoencoder. arXiv preprint arXiv:1803.02991 (2018)"},{"key":"1591_CR40","unstructured":"Bayer, J., Osendorfer, C.: Learning stochastic recurrent networks. arXiv preprint arXiv:1411.7610 (2014)"},{"key":"1591_CR41","unstructured":"Chung, J. et al.: A recurrent latent variable model for sequential data. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"1591_CR42","unstructured":"Fraccaro, M., et al.: Sequential neural models with stochastic layers. Adv. Neural Inf Process Syst. 29 (2016)"},{"key":"1591_CR43","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et al.: Agentformer: agent-aware transformers for socio-temporal multi-agent forecasting. In: Proceedings of the IEEE\/CVF international conference on computer vision (2021)","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"1591_CR44","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Joint hand motion and interaction hotspots prediction from egocentric videos. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"1591_CR45","first-page":"23592","volume":"34","author":"B Tang","year":"2021","unstructured":"Tang, B., Matteson, D.S.: Probabilistic transformer for time series analysis. Adv. Neural Inf. Process. Syst. 34, 23592\u201323608 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01591-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01591-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01591-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T17:17:00Z","timestamp":1738603020000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01591-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["1591"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01591-w","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"14 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"11"}}