{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:17:15Z","timestamp":1743081435228,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730153"},{"type":"electronic","value":"9783031730160"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73016-0_1","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T19:02:40Z","timestamp":1729882960000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spline-Based Transformers"],"prefix":"10.1007","author":[{"given":"Prashanth","family":"Chandran","sequence":"first","affiliation":[]},{"given":"Agon","family":"Serifi","sequence":"additional","affiliation":[]},{"given":"Markus","family":"Gross","sequence":"additional","affiliation":[]},{"given":"Moritz","family":"B\u00e4cher","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","unstructured":"Al-Khateeb, F., Dey, N., Soboleva, D., Hestness, J.: Position interpolation improves alibi extrapolation. CoRR abs\/2310.13017 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2310.13017","DOI":"10.48550\/ARXIV.2310.13017"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Aneja, S., Thies, J., Dai, A., Nie\u00dfner, M.: Facetalk: Audio-driven motion diffusion for neural parametric head models (2023)","DOI":"10.1109\/CVPR52733.2024.02009"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Chandran, P., Bradley, D., Gross, M., Beeler, T.: Semantic deep face models. In: 2020 International Conference on 3D Vision (3DV), pp. 345\u2013354. IEEE Computer Society, Los Alamitos, CA, USA (Nov 2020)","DOI":"10.1109\/3DV50981.2020.00044"},{"issue":"8","key":"1_CR4","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/cgf.14641","volume":"41","author":"P Chandran","year":"2022","unstructured":"Chandran, P., Zoss, G., Gross, M., Gotardo, P., Bradley, D.: Facial animation with disentangled identity and motion using transformers. Comput. Graph. Forum 41(8), 267\u2013277 (2022)","journal-title":"Comput. Graph. Forum"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chandran, P., Zoss, G., Gross, M., Gotardo, P., Bradley, D.: Shape transformers: topology-independent 3d shape models using transformers. In: Computer Graphics Forum, vol.\u00a041, pp. 195\u2013207. Wiley Online Library (2022)","DOI":"10.1111\/cgf.14468"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: Stargan v2: diverse image synthesis for multiple domains. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Dan??ek, R., Chhatre, K., Tripathi, S., Wen, Y., Black, M., Bolkart, T.: Emotional speech-driven animation with content-emotion disentanglement. ACM (Dec 2023). https:\/\/doi.org\/10.1145\/3610548.3618183, https:\/\/emote.is.tue.mpg.de\/index.html","DOI":"10.1145\/3610548.3618183"},{"key":"1_CR8","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR (2018)"},{"key":"1_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale (2021)"},{"key":"1_CR10","unstructured":"Duan, Y., et al.: Single-shot motion completion with transformer. arXiv preprint arXiv:2103.00776 (2021)"},{"key":"1_CR11","volume-title":"Curves and surfaces for CAGD: A Practical Guide","author":"G Farin","year":"2001","unstructured":"Farin, G.: Curves and surfaces for CAGD: A Practical Guide, 5th edn. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2001)","edition":"5"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3d human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5152\u20135161 (June 2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Action2motion: Conditioned generation of 3D human motions. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2021\u20132029 (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1_CR15","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"issue":"8","key":"1_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Hu, L., Ma, C., Luo, L., Li, H.: Single-view hair modeling using a hairstyle database. ACM Trans. Graph. 34(4) (Jul 2015)","DOI":"10.1145\/2766931"},{"key":"1_CR18","unstructured":"Kazemnejad, A., Padhi, I., Natesan, K., Das, P., Reddy, S.: The impact of positional encoding on length generalization in transformers. In: Thirty-seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=Drrl2gcjzl"},{"key":"1_CR19","unstructured":"Ke, G., He, D., Liu, T.Y.: Rethinking positional encoding in language pre-training. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=09-528y2Fgf"},{"key":"1_CR20","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"1_CR21","unstructured":"Liu, L., et al.: On the variance of the adaptive learning rate and beyond. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=rkgz2aEKDr"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer v2: scaling up capacity and resolution. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 34(6), 248:1\u2013248:16 (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"1_CR25","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=Skq89Scxx"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: Archive of motion capture as surface shapes. In: International Conference on Computer Vision, pp. 5442\u20135451 (Oct 2019)","DOI":"10.1109\/ICCV.2019.00554"},{"issue":"1","key":"1_CR27","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021). https:\/\/doi.org\/10.1145\/3503250","journal-title":"Commun. ACM"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: Deepsdf: learning continuous signed distance functions for shape representation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4195\u20134205 (October 2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"1_CR31","unstructured":"Press, O., Smith, N.A., Lewis, M.: Train short, test long: attention with linear biases enables input length extrapolation. In: The Tenth International Conference on Learning Representations, ICLR. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=R8sQPpGCv0"},{"key":"1_CR32","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. CoRR abs\/2103.00020 (2021)"},{"key":"1_CR33","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., Mcleavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 28492\u201328518. PMLR (23\u201329 Jul 2023). https:\/\/proceedings.mlr.press\/v202\/radford23a.html"},{"key":"1_CR34","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1) (2020)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Rosu, R.A., Saito, S., Wang, Z., Wu, C., Behnke, S., Nam, G.: Neural strands: learning hair geometry and appearance from multi-view images. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_5"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533\u2013536 (1986)","DOI":"10.1038\/323533a0"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Ruoss, A., et al.: Randomized positional encodings boost length generalization of transformers. In: 61st Annual Meeting of the Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.acl-short.161"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., Liu, Y.: Roformer: enhanced transformer with rotary position embedding (2023)","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"1_CR39","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: NeurIPS (2020)"},{"key":"1_CR40","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1007\/978-3-031-20047-2_21","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII","author":"G Tevet","year":"2022","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: MotionCLIP: exposing human motion generation to\u00a0CLIP space. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII, pp. 358\u2013374. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_21"},{"key":"1_CR41","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano, A.H.: Human motion diffusion model. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu"},{"key":"1_CR42","unstructured":"Touvron, H., Cord, M., El-Nouby, A., Bojanowski, P., Joulin, A., Synnaeve, G., J\u00e9gou, H.: Augmenting convolutional networks with attention-based aggregation. CoRR abs\/2112.13692 (2021)"},{"key":"1_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems In: NeurIPS 30 (2017)"},{"issue":"6","key":"1_CR44","first-page":"1","volume":"42","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y., Chai, M., Pepe, A., Gross, M., Beeler, T.: Groomgen: a high-quality generative hair model using hierarchical latent representations. ACM Trans. Graph. 42(6), 1\u201316 (2023)","journal-title":"ACM Trans. Graph."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73016-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T19:02:56Z","timestamp":1729882976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73016-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031730153","9783031730160"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73016-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}