{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:07:41Z","timestamp":1789124861507,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376015","type":"print"},{"value":"9783032376022","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-37602-2_30","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:23:55Z","timestamp":1789122235000},"page":"527-545","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RealDyadic: Synthesizing Realistic Dyadic 3D Dialogue with\u00a0Neural Appearance Priors"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4795-9670","authenticated-orcid":false,"given":"Lei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8227-835X","authenticated-orcid":false,"given":"Lijian","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9842-3690","authenticated-orcid":false,"given":"Ye","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2859-5165","authenticated-orcid":false,"given":"Jiahao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7963-1557","authenticated-orcid":false,"given":"Xuehan","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1865-8276","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6898-0058","authenticated-orcid":false,"given":"Yunfei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9765-4523","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"30_CR1","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural. Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"issue":"3","key":"30_CR2","first-page":"413","volume":"20","author":"C Cao","year":"2013","unstructured":"Cao, C., Weng, Y., Zhou, S., Tong, Y., Zhou, K.: FaceWarehouse: a 3D facial expression database for visual computing. IEEE Trans. Visual Comput. Graphics 20(3), 413\u2013425 (2013)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Chae-Yeon, L., Hyun-Bin, O., EunGi, H., Sung-Bin, K., Nam, S., Oh, T.H.: Perceptually accurate 3D talking head generation: new definitions, speech-mesh representation, and evaluation metrics. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21065\u201321074 (2025)","DOI":"10.1109\/CVPR52734.2025.01962"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Chu, X., Goswami, N., Cui, Z., Wang, H., Harada, T.: ARTalk: speech-driven 3D head animation via autoregressive model. arXiv preprint arXiv:2502.20323 (2025)","DOI":"10.1145\/3757377.3763955"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M.J.: Capture, learning, and synthesis of 3D speaking styles. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10101\u201310111 (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., Komura, T.: FaceFormer: speech-driven 3D facial animation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18770\u201318780 (2022)","DOI":"10.1109\/CVPR52688.2022.01821"},{"issue":"4","key":"30_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459936","volume":"40","author":"Y Feng","year":"2021","unstructured":"Feng, Y., Feng, H., Black, M.J., Bolkart, T.: Learning an animatable detailed 3D face model from in-the-wild images. ACM Trans. Graph. (ToG) 40(4), 1\u201313 (2021)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Filntisis, P.P., Retsinas, G., Paraperas-Papantoniou, F., Katsamanis, A., Roussos, A., Maragos, P.: Visual speech-aware perceptual 3D facial expression reconstruction from videos. arXiv preprint arXiv:2207.11094 (2022)","DOI":"10.1109\/CVPRW59228.2023.00609"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Ghosh, A., et al.: DuetGen: music driven two-person dance generation via hierarchical masked modeling. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3721238.3730741"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Guan, J., et\u00a0al.: TALK-Act: enhance textural-awareness for 2D speaking avatar reenactment with diffusion model. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687571"},{"key":"30_CR11","unstructured":"Hannun, A., et al.: Deep Speech: scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Hao, L., et al.: Beyond Chemical QA: evaluating LLM\u2019s chemical reasoning with modular chemical operations. Adv. Neural. Inf. Process. Syst., 38 (2026)","DOI":"10.52202\/085713-5122"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Haque, K.I., Yumak, Z.: FaceXHuBERT: text-less speech-driven e(x)pressive 3D facial animation synthesis using self-supervised speech representation learning. In: Proceedings of the 25th International Conference on Multimodal Interaction, pp. 282\u2013291 (2023)","DOI":"10.1145\/3577190.3614157"},{"key":"30_CR14","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: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"30_CR15","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"4","key":"30_CR16","doi-asserted-by":"publisher","first-page":"139\u20131","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139\u20131 (2023)","journal-title":"ACM Trans. Graph."},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Kong, Z., et al.: Let them talk: audio-driven multi-person conversational video generation. arXiv preprint arXiv:2505.22647 (2025)","DOI":"10.52202\/085713-2387"},{"key":"30_CR18","doi-asserted-by":"publisher","first-page":"3367","DOI":"10.1109\/TIP.2023.3276570","volume":"32","author":"H Li","year":"2023","unstructured":"Li, H., Huang, J., Jin, P., Song, G., Wu, Q., Chen, J.: Weakly-supervised 3D spatial reasoning for text-based visual question answering. IEEE Trans. Image Process. 32, 3367\u20133382 (2023)","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"30_CR19","doi-asserted-by":"publisher","first-page":"194\u20131","DOI":"10.1145\/3130800.3130813","volume":"36","author":"T Li","year":"2017","unstructured":"Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. 36(6), 194\u20131 (2017)","journal-title":"ACM Trans. Graph."},{"issue":"1","key":"30_CR20","doi-asserted-by":"publisher","first-page":"e2226","DOI":"10.1002\/cav.2226","volume":"35","author":"C Liang","year":"2024","unstructured":"Liang, C., Wang, Q., Chen, Y., Tang, M.: Wav2Lip-HR: synthesising clear high-resolution talking head in the wild. Comput. Anim. Virtual Worlds 35(1), e2226 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Liu, T., et al.: AniTalker: animate vivid and diverse talking faces through identity-decoupled facial motion encoding. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 6696\u20136705 (2024)","DOI":"10.1145\/3664647.3681198"},{"key":"30_CR22","unstructured":"Liu, Y., Zhu, L., Lin, L., Zhu, Y., Zhang, A., Li, Y.: TEASER: token enhanced spatial modeling for expressions reconstruction (2025)"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Mughal, M.H., Dabral, R., Habibie, I., Donatelli, L., Habermann, M., Theobalt, C.: ConvoFusion: multi-modal conversational diffusion for co-speech gesture synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1388\u20131398 (2024)","DOI":"10.1109\/CVPR52733.2024.00138"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Ng, E., et al.: Learning to Listen: modeling non-deterministic dyadic facial motion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20395\u201320405 (2022)","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"30_CR25","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Paysan, P., Knothe, R., Amberg, B., Romdhani, S., Vetter, T.: A 3D face model for pose and illumination invariant face recognition. In: Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 296\u2013301. IEEE (2009)","DOI":"10.1109\/AVSS.2009.58"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: DualTalk: dual-speaker interaction for 3D talking head conversations. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21055\u201321064 (2025)","DOI":"10.1109\/CVPR52734.2025.01961"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: SyncTalk++: high-fidelity and efficient synchronized talking heads synthesis using Gaussian splatting. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3630057"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: SyncTalk: the devil is in the synchronization for talking head synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 666\u2013676 (2024)","DOI":"10.1109\/CVPR52733.2024.00070"},{"key":"30_CR30","first-page":"11405","volume":"38","author":"Z Peng","year":"2026","unstructured":"Peng, Z., et al.: OmniSync: towards universal lip synchronization via diffusion transformers. Adv. Neural. Inf. Process. Syst. 38, 11405\u201311424 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: SelfTalk: a self-supervised commutative training diagram to comprehend 3D talking faces. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 5292\u20135301 (2023)","DOI":"10.1145\/3581783.3611734"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: EmoTalk: speech-driven emotional disentanglement for 3D face animation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20687\u201320697 (2023)","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"30_CR33","unstructured":"Qi, X., et al.: Co$$^{3}$$ Gesture: towards coherent concurrent co-speech 3D gesture generation with interactive diffusion. arXiv preprint arXiv:2505.01746 (2025)"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Qian, S., Kirschstein, T., Schoneveld, L., Davoli, D., Giebenhain, S., Nie\u00dfner, M.: GaussianAvatars: photorealistic head avatars with rigged 3D gaussians. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20299\u201320309 (2024)","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"30_CR35","doi-asserted-by":"crossref","unstructured":"Ren, Y., Li, G., Chen, Y., Li, T.H., Liu, S.: PIRenderer: controllable portrait image generation via semantic neural rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13759\u201313768 (2021)","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Retsinas, G., et al.: SMIRK: 3D facial expressions through analysis-by-neural-synthesis. arXiv preprint arXiv:2404.04104 (2024)","DOI":"10.1109\/CVPR52733.2024.00241"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Richard, A., Zollh\u00f6fer, M., Wen, Y., De\u00a0la Torre, F., Sheikh, Y.: MeshTalk: 3D face animation from speech using cross-modality disentanglement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1173\u20131182 (2021)","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"Song, L., Yin, G., Jin, Z., Dong, X., Xu, C.: Emotional listener portrait: neural listener head generation with emotion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20839\u201320849 (2023)","DOI":"10.1109\/ICCV51070.2023.01905"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: DiffPoseTalk: speech-driven stylistic 3D facial animation and head pose generation via diffusion models. ACM Trans. Graph. (TOG) 43(4), 1\u20139 (2024)","DOI":"10.1145\/3658221"},{"key":"30_CR40","doi-asserted-by":"crossref","unstructured":"Tao, R., Pan, Z., Das, R.K., Qian, X., Shou, M.Z., Li, H.: Is someone speaking? Exploring long-term temporal features for audio-visual active speaker detection. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3927\u20133935 (2021)","DOI":"10.1145\/3474085.3475587"},{"key":"30_CR41","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)"},{"key":"30_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Xie, J.C., Li, X., Xu, F., Pun, C.M., Gao, H.: GaussianHead: high-fidelity head avatars with learnable Gaussian derivation. IEEE Trans. Visual Comput. Graph. (2025)","DOI":"10.1109\/TVCG.2025.3561794"},{"key":"30_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhu, X., Zhang, T., Wang, B., Lei, Z.: 3D face reconstruction with the geometric guidance of facial part segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1672\u20131682 (2024)","DOI":"10.1109\/CVPR52733.2024.00165"},{"key":"30_CR44","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: PEAR: pixel-aligned expressive human mesh recovery. arXiv preprint arXiv:2601.22693 (2026)","DOI":"10.1145\/3799902.3811096"},{"key":"30_CR45","unstructured":"Wu, J., et al.: Swift4D: adaptive divide-and-conquer gaussian splatting for compact and efficient reconstruction of dynamic scene. arXiv preprint arXiv:2503.12307 (2025)"},{"key":"30_CR46","doi-asserted-by":"crossref","unstructured":"Xing, J., Xia, M., Zhang, Y., Cun, X., Wang, J., Wong, T.T.: CodeTalker: speech-driven 3D facial animation with discrete motion prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12780\u201312790 (2023)","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"30_CR47","doi-asserted-by":"crossref","unstructured":"Xiong, L., et al.: SegTalker: segmentation-based talking face generation with mask-guided local editing. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 3170\u20133179 (2024)","DOI":"10.1145\/3664647.3681108"},{"key":"30_CR48","doi-asserted-by":"publisher","first-page":"51039","DOI":"10.52202\/079017-1615","volume":"37","author":"Q Yang","year":"2024","unstructured":"Yang, Q., et al.: ShowMaker: creating high-fidelity 2D human video via fine-grained diffusion modeling. Adv. Neural. Inf. Process. Syst. 37, 51039\u201351062 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Q., et\u00a0al.: GestureHYDRA: semantic co-speech gesture synthesis via hybrid modality diffusion transformer and cascaded-synchronized retrieval-augmented generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12615\u201312625 (2025)","DOI":"10.1109\/ICCV51701.2025.01172"},{"key":"30_CR50","doi-asserted-by":"publisher","unstructured":"Yin, F., et al.: StyleHEAT: one-shot high-resolution editable talking face generation via pre-trained StyleGAN. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13677, pp. 85\u2013101. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_6","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"30_CR51","unstructured":"Yu, H., et al.: LLIA\u2013enabling low-latency interactive avatars: real-time audio-driven portrait video generation with diffusion models. arXiv preprint arXiv:2506.05806 (2025)"},{"key":"30_CR52","doi-asserted-by":"crossref","unstructured":"Yu, H., et\u00a0al.: GaussianTalker: speaker-specific talking head synthesis via 3D Gaussian splatting. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 3548\u20133557 (2024)","DOI":"10.1145\/3664647.3681675"},{"key":"30_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: SadTalker: learning realistic 3D motion coefficients for stylized audio-driven single image talking face animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8652\u20138661 (2023)","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"30_CR54","doi-asserted-by":"crossref","unstructured":"Zhu, L., et al.: OmniHuman: a large-scale dataset and benchmark for human-centric video generation. arXiv preprint arXiv:2604.18326 (2026)","DOI":"10.1007\/978-3-032-37095-2_6"},{"key":"30_CR55","doi-asserted-by":"crossref","unstructured":"Zhu, L., Chen, Y., Liu, X., Li, T.H., Li, G.: Learning semantic facial descriptors for accurate face animation. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10889019"},{"key":"30_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhang, L., Rong, Z., Hu, T., Liang, S., Ge, Z.: INFP: audio-driven interactive head generation in dyadic conversations. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10667\u201310677 (2025)","DOI":"10.1109\/CVPR52734.2025.00997"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37602-2_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:24:13Z","timestamp":1789122253000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37602-2_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376015","9783032376022"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37602-2_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}