{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:36:24Z","timestamp":1783697784661,"version":"3.55.0"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736674","type":"print"},{"value":"9783031736681","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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\/978-3-031-73668-1_15","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:02:13Z","timestamp":1733018533000},"page":"252-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["SignGen: End-to-End Sign Language Video Generation with\u00a0Latent Diffusion"],"prefix":"10.1007","author":[{"given":"Fan","family":"Qi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaiwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"15_CR1","unstructured":"Text to video synthesis in modelscope (2023). https:\/\/modelscope.cn\/models\/damo\/text-to-video-synthesis\/summary"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Ao, T., Zhang, Z., Liu, L.: Gesturediffuclip: gesture diffusion model with clip latents. ACM Trans. Graph. 42(4) (2023)","DOI":"10.1145\/3592097"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Arkushin, R.S., Moryossef, A., Fried, O.: Ham2pose: animating sign language notation into pose sequences, pp. 21046\u201321056 (2023)","DOI":"10.1109\/CVPR52729.2023.02016"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Bangham, J.A., et al.: Virtual signing: capture, animation, storage and transmission-an overview of the visicast project. In: IEE Seminar on Speech and Language Processing for Disabled and Elderly People (Ref. No. 2000\/025), pp.\u00a06\u20131. IET (2000)","DOI":"10.1049\/ic:20000136"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"15_CR6","unstructured":"Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Sign language transformers: joint end-to-end sign language recognition and translation (2020)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset (2018)","DOI":"10.1109\/CVPR.2017.502"},{"key":"15_CR8","unstructured":"Chen, W., et al.: Control-a-video: controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840 (2023)"},{"key":"15_CR9","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/978-0-85729-997-0_27","volume-title":"Visual Analysis of Humans: Looking at People","author":"H Cooper","year":"2011","unstructured":"Cooper, H., Holt, B., Bowden, R.: Sign language recognition. In: Moeslund, T., Hilton, A., Kruger, V., Sigal, L. (eds.) Visual Analysis of Humans: Looking at People, pp. 539\u2013562. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-0-85729-997-0_27"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Cox, S., et al.: Tessa, a system to aid communication with deaf people. In: ASSETS, pp. 205\u2013212. ACM (2002)","DOI":"10.1145\/638249.638287"},{"key":"15_CR11","unstructured":"Dao, T., Fu, D.Y., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with io-awareness (2022)"},{"key":"15_CR12","unstructured":"Doe, J.: Example website title (2022). https:\/\/www.who.int\/health-topics\/hearing-loss. Accessed 26 Nov 2023"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Duarte, A., et al.: How2sign: a large-scale multimodal dataset for continuous American sign language, pp. 2735\u20132744 (2021)","DOI":"10.1109\/CVPR46437.2021.00276"},{"key":"15_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-642-31534-3_32","volume-title":"Computers Helping People with Special Needs","author":"E Efthimiou","year":"2012","unstructured":"Efthimiou, E., et al.: The dicta-sign wiki: enabling web communication for the deaf. In: Miesenberger, K., Karshmer, A., Penaz, P., Zagler, W. (eds.) ICCHP 2012. LNCS, vol. 7383, pp. 205\u2013212. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31534-3_32"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models, pp. 7346\u20137356 (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"15_CR17","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":"15_CR18","unstructured":"Fardo, F.A., Conforto, V.H., de\u00a0Oliveira, F.C., Rodrigues, P.S.: A formal evaluation of PSNR as quality measurement parameter for image segmentation algorithms (2016)"},{"key":"15_CR19","unstructured":"Forster, J., Schmidt, C., Koller, O., Bellgardt, M., Ney, H.: Extensions of the sign language recognition and translation corpus RWTH-PHOENIX-weather (2014)"},{"key":"15_CR20","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/s10209-015-0411-6","volume":"15","author":"S Gibet","year":"2016","unstructured":"Gibet, S., Lefebvre-Albaret, F., Hamon, L., Brun, R., Turki, A.: Interactive editing in french sign language dedicated to virtual signers: requirements and challenges. Univ. Access Inf. Soc. 15, 525\u2013539 (2016)","journal-title":"Univ. Access Inf. Soc."},{"key":"15_CR21","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"15_CR22","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2022)"},{"key":"15_CR23","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"15_CR25","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":"15_CR26","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.cviu.2015.09.013","volume":"141","author":"O Koller","year":"2015","unstructured":"Koller, O., Forster, J., Ney, H.: Continuous sign language recognition: towards large vocabulary statistical recognition systems handling multiple signers. Comput. Vis. Image Underst. 141, 108\u2013125 (2015)","journal-title":"Comput. Vis. Image Underst."},{"key":"15_CR27","unstructured":"Lee, A.X., Zhang, R., Ebert, F., Abbeel, P., Finn, C., Levine, S.: Stochastic adversarial video prediction. arXiv preprint arXiv:1804.01523 (2018)"},{"key":"15_CR28","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: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1459\u20131469 (2020)","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., Och, F.J.: Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics (2004)","DOI":"10.3115\/1218955.1219032"},{"key":"15_CR30","unstructured":"Liu, Y., et al.: Temporally consistent video colorization with deep feature propagation and self-regularization learning (2021)"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Videofusion: decomposed diffusion models for high-quality video generation, pp. 10209\u201310218 (2023)","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"15_CR32","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning (2021)"},{"key":"15_CR33","unstructured":"Van\u00a0den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et\u00a0al.: Conditional image generation with pixelcnn decoders. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"15_CR35","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"15_CR36","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. ArXiv arxiv:2204.06125 (2022)"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Reda, F., Kontkanen, J., Tabellion, E., Sun, D., Pantofaru, C., Curless, B.: Film: frame interpolation for large motion, pp. 250\u2013266 (2022)","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"15_CR41","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. ArXiv arxiv:2205.11487 (2022)"},{"key":"15_CR42","unstructured":"Saunders, B., Camg\u00f6z, N.C., Bowden, R.: Everybody sign now: translating spoken language to photo realistic sign language video. CoRR arxiv:2011.09846 (2020)"},{"key":"15_CR43","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)"},{"key":"15_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1007\/978-3-030-58621-8_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Saunders","year":"2020","unstructured":"Saunders, B., Camgoz, N.C., Bowden, R.: Progressive transformers for end-to-end sign language production. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 687\u2013705. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_40"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Saunders, B., Camg\u00f6z, N.C., Bowden, R.: Progressive transformers for end-to-end sign language production. CoRR arxiv:2004.14874 (2020)","DOI":"10.1007\/978-3-030-58621-8_40"},{"issue":"7","key":"15_CR46","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":"15_CR47","doi-asserted-by":"crossref","unstructured":"Saunders, B., Camg\u00f6z, N.C., Bowden, R.: Continuous 3d multi-channel sign language production via progressive transformers and mixture density networks. CoRR arxiv:2103.06982 (2021)","DOI":"10.1007\/s11263-021-01457-9"},{"key":"15_CR48","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 International Conference on Computer Vision, pp. 1919\u20131929 (2021)","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Saunders, B., Camg\u00f6z, N.C., Bowden, R.: Mixed signals: sign language production via a mixture of motion primitives. CoRR arxiv:2107.11317 (2021)","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"15_CR50","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, pp. 5141\u20135151 (2022)","DOI":"10.1109\/CVPR52688.2022.00508"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Shalev-Arkushin, R., Moryossef, A., Fried, O.: Ham2pose: animating sign language notation into pose sequences. In: CVPR, pp. 21046\u201321056. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.02016"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Sangineto, E., Lathuiliere, S., Sebe, N.: Deformable gans for pose-based human image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3408\u20133416 (2018)","DOI":"10.1109\/CVPR.2018.00359"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Sincan, O.M., Junior, J., Jacques, C., Escalera, S., Keles, H.Y.: Chalearn lap large scale signer independent isolated sign language recognition challenge: design, results and future research. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3472\u20133481 (2021)","DOI":"10.1109\/CVPRW53098.2021.00386"},{"key":"15_CR54","doi-asserted-by":"publisher","first-page":"181340","DOI":"10.1109\/ACCESS.2020.3028072","volume":"8","author":"OM Sincan","year":"2020","unstructured":"Sincan, O.M., Keles, H.Y.: Autsl: a large scale multi-modal Turkish sign language dataset and baseline methods. IEEE Access 8, 181340\u2013181355 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3028072","journal-title":"IEEE Access"},{"key":"15_CR55","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICCV, pp. 2256\u20132265 (2015)"},{"key":"15_CR56","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. ArXiv arxiv:2010.02502 (2020)"},{"key":"15_CR57","unstructured":"Stoll, S., Camg\u00f6z, N.C., Hadfield, S., Bowden, R.: Sign language production using neural machine translation and generative adversarial networks. In: Proceedings of the 29th British Machine Vision Conference (BMVC 2018). British Machine Vision Association (2018)"},{"issue":"4","key":"15_CR58","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1007\/s11263-019-01281-2","volume":"128","author":"S Stoll","year":"2020","unstructured":"Stoll, S., Camg\u00f6z, N.C., Hadfield, S., Bowden, R.: Text2sign: towards sign language production using neural machine translation and generative adversarial networks. Int. J. Comput. Vis. 128(4), 891\u2013908 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"15_CR59","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric 2018)"},{"key":"15_CR60","doi-asserted-by":"crossref","unstructured":"Vasani, N., Autee, P., Kalyani, S., Karani, R.: Generation of Indian sign language by sentence processing and generative adversarial networks. In: 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), pp. 1250\u20131255. IEEE (2020)","DOI":"10.1109\/ICISS49785.2020.9315979"},{"key":"15_CR61","first-page":"23371","volume":"35","author":"V Voleti","year":"2022","unstructured":"Voleti, V., Jolicoeur-Martineau, A., Pal, C.: MCVD-masked conditional video diffusion for prediction, generation, and interpolation. Adv. Neural. Inf. Process. Syst. 35, 23371\u201323385 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR62","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"15_CR63","unstructured":"Weast, T.P.: Questions in American sign language: a quantitative analysis of raised and lowered eyebrows. The University of Texas at Arlington (2008)"},{"key":"15_CR64","doi-asserted-by":"crossref","unstructured":"Wei, F., Chen, Y.: Improving continuous sign language recognition with cross-lingual signs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23612\u201323621 (2023)","DOI":"10.1109\/ICCV51070.2023.02158"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. arXiv preprint arXiv:2212.11565 (2022)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"15_CR66","unstructured":"Xie, P., Zhang, Q., Li, Z., Tang, H., Du, Y., Hu, X.: Vector quantized diffusion model with codeunet for text-to-sign pose sequences generation. arXiv preprint arXiv:2208.09141 (2022)"},{"key":"15_CR67","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zeng, A., Yuan, C., Li, Y.: Effective whole-body pose estimation with two-stages distillation (2023)","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"15_CR68","doi-asserted-by":"crossref","unstructured":"Yu, S., Sohn, K., Kim, S., Shin, J.: Video probabilistic diffusion models in projected latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18456\u201318466 (2023)","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"15_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"15_CR70","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 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"15_CR71","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: Controlvideo: training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)"},{"key":"15_CR72","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, pp. 1316\u20131325 (2021)","DOI":"10.1109\/CVPR46437.2021.00137"}],"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\/978-3-031-73668-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:11:54Z","timestamp":1733019114000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73668-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"ISBN":["9783031736674","9783031736681"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73668-1_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"1 December 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"}}]}}