{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T17:32:25Z","timestamp":1762882345259,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819531011","type":"print"},{"value":"9789819531028","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-3102-8_9","type":"book-chapter","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T17:29:38Z","timestamp":1762882178000},"page":"139-149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HTDiff: Self-Guiding Diffusion Models for\u00a0Hand Trajectory Prediction"],"prefix":"10.1007","author":[{"given":"Yu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zipei","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlv","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiqi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Bao, W., 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\u201313711 (2023)","DOI":"10.1109\/ICCV51070.2023.01260"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Chai, S., Zhuang, L., Yan, F.: Layoutdm: transformer-based diffusion model for layout generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18349\u201318358 (2023)","DOI":"10.1109\/CVPR52729.2023.01760"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., Gao, J., Xu, C.: Uncertainty-aware dual-evidential learning for weakly-supervised temporal action localization. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3308571"},{"key":"9_CR4","unstructured":"Dhariwal, P., Nichol, A.Q.: Diffusion models beat GANs on image synthesis. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021)"},{"key":"9_CR5","unstructured":"Godahewa, R., Bergmeir, C., Webb, G.I., Hyndman, R.J., Montero-Manso, P.: Monash time series forecasting archive. arXiv preprint arXiv:2105.06643 (2021)"},{"key":"9_CR6","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":"9_CR7","unstructured":"Kingma, D.P.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"9_CR8","unstructured":"Kollovieh, M., Ansari, A.F., Bohlke-Schneider, M., Zschiegner, J., Wang, H., Wang, Y.B.: Predict, refine, synthesize: self-guiding diffusion models for probabilistic time series forecasting. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"9_CR9","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: Diffwave: a versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761 (2020)"},{"issue":"3","key":"9_CR10","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1007\/s11263-023-01879-7","volume":"132","author":"B Lai","year":"2024","unstructured":"Lai, B., Liu, M., Ryan, F., Rehg, J.M.: In the eye of transformer: global-local correlation for egocentric gaze estimation and beyond. Int. J. Comput. Vision 132(3), 854\u2013871 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"9_CR11","unstructured":"Li, X.L., Thickstun, J., Gulrajani, I., Liang, P., Hashimoto, T.: Diffusion-LM improves controllable text generation. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M., Rehg, J.M.: In the eye of beholder: joint learning of gaze and actions in first person video. In: Proceedings of the European conference on computer vision (ECCV), pp. 619\u2013635 (2018)","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., Zhong, Y., Song, R., Li, T., Ma, L., Zhang, W.: Detal: open-vocabulary temporal action localization with decoupled networks. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3395778"},{"key":"9_CR14","unstructured":"Lienen, M., L\u00fcdke, D., Hansen-Palmus, J., G\u00fcnnemann, S.: From zero to turbulence: generative modeling for 3d flow simulation. arXiv preprint arXiv:2306.01776 (2023)"},{"key":"9_CR15","first-page":"56784","volume":"36","author":"D L\u00fcdke","year":"2023","unstructured":"L\u00fcdke, D., Bilo\u0161, M., Shchur, O., Lienen, M., G\u00fcnnemann, S.: Add and thin: diffusion for temporal point processes. Adv. Neural. Inf. Process. Syst. 36, 56784\u201356801 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR16","unstructured":"Ma, J., Chen, X., Bao, W., Xu, J., Wang, H.: Madiff: motion-aware mamba diffusion models for hand trajectory prediction on egocentric videos. arXiv preprint arXiv:2409.02638 (2024)"},{"key":"9_CR17","unstructured":"O\u2019Neill, A., et\u00a0al.: Open x-embodiment: robotic learning datasets and rt-x models: open x-embodiment collaboration 0. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 6892\u20136903. IEEE (2024)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Pasca, R.G., et al.: Summarize the past to predict the future: natural language descriptions of context boost multimodal object interaction anticipation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18286\u201318296 (2024)","DOI":"10.1109\/CVPR52733.2024.01731"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Qi, Z., Wang, S., Zhang, W., Huang, Q.: Uncertainty-boosted robust video activity anticipation. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3393730"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Ragusa, F., Farinella, G.M., Furnari, A.: Stillfast: an end-to-end approach for short-term object interaction anticipation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3636\u20133645 (2023)","DOI":"10.1109\/CVPRW59228.2023.00371"},{"key":"9_CR21","unstructured":"Rasul, K., Seward, C., Schuster, I., Vollgraf, R.: Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting. In: International Conference on Machine Learning, pp. 8857\u20138868. PMLR (2021)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Shan, D., Geng, J., Shu, M., Fouhey, D.F.: Understanding human hands in contact at internet scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9869\u20139878 (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"9_CR23","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"9_CR24","first-page":"24804","volume":"34","author":"Y Tashiro","year":"2021","unstructured":"Tashiro, Y., Song, J., Song, Y., Ermon, S.: CSDI: conditional score-based diffusion models for probabilistic time series imputation. Adv. Neural. Inf. Process. Syst. 34, 24804\u201324816 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR25","unstructured":"Vaswani, A.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"9_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917, pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Wang, B., Zhao, Y., Yang, L., Long, T., Li, X.: Temporal action localization in the deep learning era: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3330794"},{"key":"9_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIP.2023.3334954","volume":"33","author":"X Wang","year":"2023","unstructured":"Wang, X., Zhang, W., Wang, C., Gao, Y., Liu, M.: Dynamic dense graph convolutional network for skeleton-based human motion prediction. IEEE Trans. Image Process. 33, 1\u201315 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Ye, Y., et al.: Affordance diffusion: synthesizing hand-object interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22479\u201322489 (2023)","DOI":"10.1109\/CVPR52729.2023.02153"},{"key":"9_CR30","unstructured":"Yuan, X., Qiao, Y.: Diffusion-TS: interpretable diffusion for general time series generation. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"9_CR31","unstructured":"Zeng, A., Chen, M., Zhang, L., Xu, Q.: Are transformers effective for time series forecasting? In: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence. AAAI\u201923\/IAAI\u201923\/EAAI\u201923, AAAI Press (2023)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Object-centric video representation for long-term action anticipation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6751\u20136761 (2024)","DOI":"10.1109\/WACV57701.2024.00661"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Zheng, Y.D., Chen, G., Yuan, M., Lu, T.: MRSN: multi-relation support network for video action detection. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 1026\u20131031. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00180"}],"container-title":["Lecture Notes in Computer Science","Spatial Data and Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3102-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T17:29:42Z","timestamp":1762882182000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3102-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"ISBN":["9789819531011","9789819531028"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3102-8_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,12]]},"assertion":[{"value":"12 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"SpatialDI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Spatial Data and Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"spatialdi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}