{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:36:26Z","timestamp":1783697786130,"version":"3.55.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729799","type":"print"},{"value":"9783031729805","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72980-5_23","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"392-409","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Pose-Guided Fine-Grained Sign Language Video Generation"],"prefix":"10.1007","author":[{"given":"Tongkai","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fanhua","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jichao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peidong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, D., Kim, S., Hong, H., Ko, B.C.: Star-transformer: a spatio-temporal cross attention transformer for human action recognition. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 3330\u20133339 (2023)","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Baltatzis, V., Potamias, R.A., Ververas, E., Sun, G., Deng, J., Zafeiriou, S.: Neural sign actors: a diffusion model for 3d sign language production from text. arXiv preprint arXiv:2312.02702 (2023)","DOI":"10.1109\/CVPR52733.2024.00194"},{"issue":"3","key":"23_CR3","first-page":"3522","volume":"45","author":"X Bruce","year":"2022","unstructured":"Bruce, X., Liu, Y., Zhang, X., Zhong, S.H., Chan, K.C.: Mmnet: a model-based multimodal network for human action recognition in rgb-d videos. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3522\u20133538 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Neural sign language translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7784\u20137793 (2018)","DOI":"10.1109\/CVPR.2018.00812"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"23_CR6","first-page":"17043","volume":"35","author":"Y Chen","year":"2022","unstructured":"Chen, Y., Zuo, R., Wei, F., Wu, Y., Liu, S., Mak, B.: Two-stream network for sign language recognition and translation. Adv. Neural Inf. Process. Syst. 35, 17043\u201317056 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Cox, S., et al.: Tessa, a system to aid communication with deaf people. In: Proceedings of the Fifth International ACM Conference on Assistive Technologies, pp. 205\u2013212 (2002)","DOI":"10.1145\/638249.638287"},{"issue":"10","key":"23_CR8","doi-asserted-by":"publisher","first-page":"2551","DOI":"10.1109\/TMM.2019.2960700","volume":"22","author":"R Cui","year":"2019","unstructured":"Cui, R., Cao, Z., Pan, W., Zhang, C., Wang, J.: Deep gesture video generation with learning on regions of interest. IEEE Trans. Multimedia 22(10), 2551\u20132563 (2019)","journal-title":"IEEE Trans. Multimedia"},{"issue":"12","key":"23_CR9","doi-asserted-by":"publisher","first-page":"9703","DOI":"10.1109\/TPAMI.2021.3127885","volume":"44","author":"S Das","year":"2021","unstructured":"Das, S., Dai, R., Yang, D., Bremond, F.: Vpn++: rethinking video-pose embeddings for understanding activities of daily living. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9703\u20139717 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-030-58545-7_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Das","year":"2020","unstructured":"Das, S., Sharma, S., Dai, R., Br\u00e9mond, F., Thonnat, M.: VPN: learning video-pose embedding for activities of daily living. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 72\u201390. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_5"},{"key":"23_CR11","unstructured":"Fang, S., Sui, C., Zhang, X., Tian, Y.: Signdiff: learning diffusion models for american sign language production. arXiv preprint arXiv:2308.16082 (2023)"},{"key":"23_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"23_CR13","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6629\u20136640 (2017)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Hu, L., Gao, L., Liu, Z., Feng, W.: Continuous sign language recognition with correlation network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2529\u20132539 (2023)","DOI":"10.1109\/CVPR52729.2023.00249"},{"key":"23_CR15","unstructured":"Jia, Z., Zhang, Z., Wang, L., Tan, T.: Human image generation: a comprehensive survey. arXiv preprint arXiv:2212.08896 (2022)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, S., Sun, B., Wang, L., Bai, Y., Li, K., Fu, Y.: Skeleton aware multi-modal sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3413\u20133423 (2021)","DOI":"10.1109\/CVPRW53098.2021.00380"},{"key":"23_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/978-3-030-58545-7_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S.: Whole-body human pose estimation in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 196\u2013214. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_12"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Kim, S., Ahn, D., Ko, B.C.: Cross-modal learning with 3d deformable attention for action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10265\u201310275 (2023)","DOI":"10.1109\/ICCV51070.2023.00942"},{"key":"23_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/978-3-642-23974-8_13","volume-title":"Intelligent Virtual Agents","author":"M Kipp","year":"2011","unstructured":"Kipp, M., Heloir, A., Nguyen, Q.: Sign language avatars: animation and comprehensibility. In: Vilhj\u00e1lmsson, H.H., Kopp, S., Marsella, S., Th\u00f3risson, K.R. (eds.) IVA 2011. LNCS (LNAI), vol. 6895, pp. 113\u2013126. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-23974-8_13"},{"key":"23_CR20","unstructured":"Kissel, C., K\u00fcmmel, C., Ritter, D., Hildebrand, K.: Pose-guided sign language video gan with dynamic lambda. arXiv preprint arXiv:2105.02742 (2021)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Li, D., Rodriguez, C., Yu, X., Li, H.: Word-level deep sign language recognition from video: a new large-scale dataset and methods comparison. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 1459\u20131469 (2020)","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"23_CR22","doi-asserted-by":"publisher","first-page":"9584","DOI":"10.1109\/TIP.2020.3029455","volume":"29","author":"K Li","year":"2020","unstructured":"Li, K., Zhang, J., Liu, Y., Lai, Y.K., Dai, Q.: Pona: pose-guided non-local attention for human pose transfer. IEEE Trans. Image Process. 29, 9584\u20139599 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., Loy, C.C.: Dense intrinsic appearance flow for human pose transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3693\u20133702 (2019)","DOI":"10.1109\/CVPR.2019.00381"},{"key":"23_CR24","doi-asserted-by":"publisher","unstructured":"Liu, S., Ye, J., Ren, S., Wang, X.: Dynast: dynamic sparse transformer for exemplar-guided image generation. In: European Conference on Computer Vision, pp. 72\u201390. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19787-1_5","DOI":"10.1007\/978-3-031-19787-1_5"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Liu, W., Piao, Z., Min, J., Luo, W., Ma, L., Gao, S.: Liquid warping gan: a unified framework for human motion imitation, appearance transfer and novel view synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5904\u20135913 (2019)","DOI":"10.1109\/ICCV.2019.00600"},{"key":"23_CR26","first-page":"405","volume":"30","author":"L Ma","year":"2017","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. Adv. Neural Inf. Process. Syst. 30, 405\u2013415 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"23_CR27","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/TMM.2021.3134157","volume":"25","author":"L Ma","year":"2023","unstructured":"Ma, L., Huang, K., Wei, D., Ming, Z.Y., Shen, H.: Fda-gan: flow-based dual attention gan for human pose transfer. IEEE Trans. Multimedia 25, 930\u2013941 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"23_CR28","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1007\/s10209-015-0407-2","volume":"15","author":"J McDonald","year":"2016","unstructured":"McDonald, J., et al.: An automated technique for real-time production of lifelike animations of American sign language. Univ. Access Inf. Soc. 15, 551\u2013566 (2016)","journal-title":"Univ. Access Inf. Soc."},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Ren, Y., Fan, X., Li, G., Liu, S., Li, T.H.: Neural texture extraction and distribution for controllable person image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13535\u201313544 (2022)","DOI":"10.1109\/CVPR52688.2022.01317"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Ren, Y., Wu, Y., Li, T.H., Liu, S., Li, G.: Combining attention with flow for person image synthesis. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3737\u20133745 (2021)","DOI":"10.1145\/3474085.3475256"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Ren, Y., Yu, X., Chen, J., Li, T.H., Li, G.: Deep image spatial transformation for person image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7690\u20137699 (2020)","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"23_CR32","unstructured":"Ronchetti, F., Quiroga, F., Estrebou, C., Lanzarini, L., Rosete, A.: Lsa64: a dataset of Argentinian sign language. In: XX II Congreso Argentino de Ciencias de la Computaci\u00f3n (CACIC) (2016)"},{"key":"23_CR33","unstructured":"Saunders, B., Camgoz, N.C., Bowden, R.: Everybody sign now: translating spoken language to photo realistic sign language video. arXiv preprint arXiv:2011.09846 (2020)"},{"issue":"7","key":"23_CR34","doi-asserted-by":"publisher","first-page":"2113","DOI":"10.1007\/s11263-021-01457-9","volume":"129","author":"B Saunders","year":"2021","unstructured":"Saunders, B., Camgoz, N.C., Bowden, R.: Continuous 3d multi-channel sign language production via progressive transformers and mixture density networks. Int. J. Comput. Vision 129(7), 2113\u20132135 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Saunders, B., Camgoz, N.C., Bowden, R.: Mixed signals: sign language production via a mixture of motion primitives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1919\u20131929 (2021)","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Saunders, B., Camgoz, N.C., Bowden, R.: Signing at scale: learning to co-articulate signs for large-scale photo-realistic sign language production. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5141\u20135151 (2022)","DOI":"10.1109\/CVPR52688.2022.00508"},{"key":"23_CR37","unstructured":"Saunders, B., Camg\u00f6z, N.C., Bowden, R.: Skeletal graph self-attention: embedding a skeleton inductive bias into sign language production. In: Proceedings of the 7th International Workshop on Sign Language Translation and Avatar Technology: The Junction of the Visual and the Textual: Challenges and Perspectives. European Language Resources Association (D2022)"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: Animating arbitrary objects via deep motion transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2377\u20132386 (2019)","DOI":"10.1109\/CVPR.2019.00248"},{"key":"23_CR39","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13653\u201313662 (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"issue":"4","key":"23_CR41","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1007\/s11263-019-01281-2","volume":"128","author":"S Stoll","year":"2020","unstructured":"Stoll, S., Camgoz, N.C., Hadfield, S., Bowden, R.: Text2sign: towards sign language production using neural machine translation and generative adversarial networks. Int. J. Comput. Vision 128(4), 891\u2013908 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"23_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/978-3-030-66823-5_21","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"S Stoll","year":"2020","unstructured":"Stoll, S., Hadfield, S., Bowden, R.: SignSynth: data-driven sign language video generation. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12538, pp. 353\u2013370. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66823-5_21"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Su, K.Y., Wu, M.W., Chang, J.S.: A new quantitative quality measure for machine translation systems. In: COLING 1992 Volume 2: The 14th International Conference on Computational Linguistics (1992)","DOI":"10.3115\/992133.992137"},{"key":"23_CR44","doi-asserted-by":"publisher","DOI":"10.1145\/3648368","author":"Y Suo","year":"2024","unstructured":"Suo, Y., Zheng, Z., Wang, X., Zhang, B., Yang, Y.: Jointly harnessing prior structures and temporal consistency for sign language video generation. ACM Trans. Multimedia Comput. Commun. Appl. (2024). https:\/\/doi.org\/10.1145\/3648368","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"23_CR45","unstructured":"Sural, S., et al.: Performance comparison of distance metrics in content-based image retrieval applications. In: Proceedings of International Conference on Information Technology, Bhubaneswar, India, pp. 159\u2013164 (2003)"},{"key":"23_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/978-3-030-58595-2_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Tang","year":"2020","unstructured":"Tang, H., Bai, S., Zhang, L., Torr, P.H.S., Sebe, N.: XingGAN for person image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 717\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_43"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Tang, J., Yuan, Y., Shao, T., Liu, Y., Wang, M., Zhou, K.: Structure-aware person image generation with pose decomposition and semantic correlation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 2656\u20132664 (2021)","DOI":"10.1609\/aaai.v35i3.16369"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Tao, J., Wang, B., Xu, B., Ge, T., Jiang, Y., Li, W., Duan, L.: Structure-aware motion transfer with deformable anchor model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3637\u20133646 (2022)","DOI":"10.1109\/CVPR52688.2022.00362"},{"key":"23_CR49","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2019)"},{"key":"23_CR50","unstructured":"Ventura, L., Duarte, A., i\u00a0Nieto, X.G.: Can everybody sign now? exploring sign language video generation from 2d poses. arXiv preprint arXiv:2012.10941 (2021)"},{"key":"23_CR51","unstructured":"Wang, Y., Yang, D., Bremond, F., Dantcheva, A.: Latent image animator: learning to animate images via latent space navigation. In: International Conference on Learning Representations (ICLR) (2022)"},{"issue":"4","key":"23_CR52","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, P., Yang, L., Lai, J.H., Xie, X.: Exploring dual-task correlation for pose guided person image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7713\u20137722 (2022)","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"23_CR55","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhang, H.: Thin-plate spline motion model for image animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3657\u20133666 (2022)","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Qi, W., Pu, J., Li, H.: Improving sign language translation with monolingual data by sign back-translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1316\u20131325 (2021)","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"23_CR57","doi-asserted-by":"crossref","unstructured":"Zuo, R., Wei, F., Chen, Z., Mak, B., Yang, J., Tong, X.: A simple baseline for spoken language to sign language translation with 3d avatars. arXiv preprint arXiv:2401.04730 (2024)","DOI":"10.1007\/978-3-031-72967-6_3"}],"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\/978-3-031-72980-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:22:28Z","timestamp":1732962148000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72980-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031729799","9783031729805"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72980-5_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 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"}}]}}