{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T23:02:50Z","timestamp":1789686170922,"version":"4.0.1"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370310","type":"print"},{"value":"9783032370327","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\/978-3-032-37032-7_37","type":"book-chapter","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:11:43Z","timestamp":1789683103000},"page":"680-697","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["InteractiveAvatar: Real-Time Streaming Video Generation for\u00a0Consistent and\u00a0Intent-Aware Avatars"],"prefix":"10.1007","author":[{"given":"Quanyue","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yishan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihao","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixiang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhizhi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caigui","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"37_CR1","unstructured":"An, H., et\u00a0al.: Ai flow: perspectives, scenarios, and approaches. arXiv preprint arXiv:2506.12479 (2025)"},{"key":"37_CR2","unstructured":"Chen, Y., et al.: Hunyuanvideo-avatar: high-fidelity audio-driven human animation for multiple characters. arXiv preprint arXiv:2505.20156 (2025)"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Cao, J., Chen, Z., Li, Y., Ma, C.: Echomimic: lifelike audio-driven portrait animations through editable landmark conditions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 2403\u20132410 (2025)","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: Unison: harmonizing motion, speech, and sound for human-centric audio-video generation (2026). https:\/\/arxiv.org\/abs\/2605.08729","DOI":"10.1007\/978-3-032-37574-2_6"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: Voxceleb2: deep speaker recognition. In: INTERSPEECH (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"37_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-54427-4_19","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10117, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Cui, J., et al.: Hallo3: highly dynamic and realistic portrait image animation with video diffusion transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21086\u201321095 (2025)","DOI":"10.1109\/CVPR52734.2025.01964"},{"key":"37_CR8","unstructured":"Cui, J., et al.: Self-forcing++: towards minute-scale high-quality video generation. arXiv preprint arXiv:2510.02283 (2025)"},{"key":"37_CR9","unstructured":"Ding, Y., Hu, X., Guo, Z., Zhang, C., Wang, Y.: Mtvcrafter: 4d motion tokenization for open-world human image animation. arXiv preprint arXiv:2505.10238 (2025)"},{"key":"37_CR10","unstructured":"Gan, Q., Yang, R., Zhu, J., Xue, S., Hoi, S.: Omniavatar: efficient audio-driven avatar video generation with adaptive body animation. arXiv preprint arXiv:2506.18866 (2025)"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3497\u20133506 (2019)","DOI":"10.1109\/CVPR.2019.00361"},{"key":"37_CR12","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. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, Z., He, G., Zhou, M., Shechtman, E.: Self forcing: bridging the train-test gap in autoregressive video diffusion. arXiv preprint arXiv:2506.08009 (2025)","DOI":"10.52202\/085713-5576"},{"key":"37_CR14","unstructured":"Huang, Y., et\u00a0al.: Live avatar: streaming real-time audio-driven avatar generation with infinite length. arXiv preprint arXiv:2512.04677 (2025)"},{"issue":"1","key":"37_CR15","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1007\/s44336-024-00002-9","volume":"1","author":"W Jiang","year":"2024","unstructured":"Jiang, W., Zhang, Y., Zheng, S., Liu, S., Yan, S.: Data augmentation in human-centric vision. Vicinagearth 1(1), 8 (2024)","journal-title":"Vicinagearth"},{"key":"37_CR16","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":"37_CR17","doi-asserted-by":"crossref","unstructured":"Li, H., et\u00a0al.: Openhumanvid: a large-scale high-quality dataset for enhancing human-centric video generation. arXiv preprint arXiv:2412.00115 (2024)","DOI":"10.1109\/CVPR52734.2025.00726"},{"issue":"1","key":"37_CR18","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s44336-024-00009-2","volume":"1","author":"X Li","year":"2024","unstructured":"Li, X., Wang, S., Zeng, S., Wu, Y., Yang, Y.: A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth 1(1), 9 (2024)","journal-title":"Vicinagearth"},{"issue":"6","key":"37_CR19","doi-asserted-by":"publisher","first-page":"8708","DOI":"10.1109\/TNNLS.2022.3224577","volume":"35","author":"X Li","year":"2022","unstructured":"Li, X.: Positive-incentive noise. IEEE Trans. Neural Netw. Learn. Syst. 35(6), 8708\u20138714 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"37_CR20","unstructured":"Low, C., Wang, W.: Talkingmachines: real-time audio-driven facetime-style video via autoregressive diffusion models. arXiv preprint arXiv:2506.03099 (2025)"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Meng, R., Wang, Y., Wu, W., Zheng, R., Li, Y., Ma, C.: Echomimicv 3: 1.3 b parameters are all you need for unified multi-modal and multi-task human animation. arXiv preprint arXiv:2507.03905 (2025)","DOI":"10.1609\/aaai.v40i10.37746"},{"key":"37_CR22","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":"37_CR23","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Mukhopadhyay, R., Namboodiri, V.P., Jawahar, C.: A lip sync expert is all you need for speech to lip generation in the wild. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 484\u2013492 (2020)","DOI":"10.1145\/3394171.3413532"},{"issue":"140","key":"37_CR24","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"37_CR25","unstructured":"Sim\u00e9oni, O., et al.: DINOv3 (2025). https:\/\/arxiv.org\/abs\/2508.10104"},{"key":"37_CR26","unstructured":"Sun, Z., et\u00a0al.: Streamavatar: streaming diffusion models for real-time interactive human avatars. arXiv preprint arXiv:2512.22065 (2025)"},{"key":"37_CR27","doi-asserted-by":"publisher","unstructured":"Tian, L., Wang, Q., Zhang, B., Bo, L.: Emo: emote portrait alive generating expressive portrait videos with audio2video diffusion model under weak conditions. In: European Conference on Computer Vision, pp. 244\u2013260. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73010-8_15","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"37_CR28","unstructured":"Tschannen, M., et al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"37_CR29","unstructured":"Tu, S., et al.: Stableavatar: infinite-length audio-driven avatar video generation (2025). https:\/\/arxiv.org\/abs\/2508.08248"},{"key":"37_CR30","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"37_CR31","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"37_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., Wang, C., Huang, K., Huang, J., Jin, L.: Videoclip-xl: advancing long description understanding for video clip models (2024). https:\/\/arxiv.org\/abs\/2410.00741","DOI":"10.18653\/v1\/2024.emnlp-main.898"},{"key":"37_CR33","unstructured":"Wang, L., et\u00a0al.: Flowact-r1: towards interactive humanoid video generation. arXiv preprint arXiv:2601.10103 (2026)"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Wang, M., et al.: Fantasytalking: realistic talking portrait generation via coherent motion synthesis. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 9891\u20139900 (2025)","DOI":"10.1145\/3746027.3755217"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fan, Y., Wang, X., Yu, G., Wang, F.: Diffusion-based realistic listening head generation via hybrid motion modeling. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15885\u201315895 (2025)","DOI":"10.1109\/CVPR52734.2025.01481"},{"key":"37_CR36","unstructured":"Wu, H., et\u00a0al.: Q-align: teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090 (2023)"},{"key":"37_CR37","doi-asserted-by":"crossref","unstructured":"Xie, L., Wang, X., Zhang, H., Dong, C., Shan, Y.: Vfhq: a high-quality dataset and benchmark for video face super-resolution. In: The IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW (2022)","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"37_CR38","unstructured":"Xie, Y., et al.: X-streamer: unified human world modeling with audiovisual interaction. arXiv preprint arXiv:2509.21574 (2025)"},{"key":"37_CR39","unstructured":"Xu, J., et\u00a0al.: Qwen3-omni technical report. arXiv preprint arXiv:2509.17765 (2025)"},{"key":"37_CR40","doi-asserted-by":"publisher","first-page":"660","DOI":"10.52202\/079017-0021","volume":"37","author":"S Xu","year":"2024","unstructured":"Xu, S., et al.: Vasa-1: lifelike audio-driven talking faces generated in real time. Adv. Neural. Inf. Process. Syst. 37, 660\u2013684 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR41","unstructured":"Yang, S., et al.: Longlive: real-time interactive long video generation. arXiv preprint arXiv:2509.22622 (2025)"},{"key":"37_CR42","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: From slow bidirectional to fast autoregressive video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22963\u201322974 (2025)","DOI":"10.1109\/CVPR52734.2025.02138"},{"key":"37_CR43","doi-asserted-by":"crossref","unstructured":"Yu, J., Zhu, H., Jiang, L., Loy, C.C., Cai, W., Wu, W.: CelebV-text: a large-scale facial text-video dataset. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01422"},{"key":"37_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, H., Huang, S., Guo, Y., Li, X.: Variational positive-incentive noise: How noise benefits models. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3575295"},{"key":"37_CR45","unstructured":"Zhang, L., et al.: Pretraining frame preservation in autoregressive video memory compression. arXiv preprint arXiv:2512.23851 (2025)"},{"key":"37_CR46","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":"37_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y., Fan, C.: Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3661\u20133670 (2021)","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"37_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Pytorch fsdp: experiences on scaling fully sharded data parallel. arXiv preprint arXiv:2304.11277 (2023)","DOI":"10.14778\/3611540.3611569"},{"issue":"6","key":"37_CR49","first-page":"1","volume":"39","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y., Han, X., Shechtman, E., Echevarria, J., Kalogerakis, E., Li, D.: Makelttalk: speaker-aware talking-head animation. ACM Trans. Graph. (TOG) 39(6), 1\u201315 (2020)","journal-title":"ACM Trans. Graph. (TOG)"}],"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\/978-3-032-37032-7_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:11:55Z","timestamp":1789683115000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37032-7_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370310","9783032370327"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37032-7_37","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":"18 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"}}]}}