{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:06:54Z","timestamp":1788991614121,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370259","type":"print"},{"value":"9783032370266","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\/978-3-032-37026-6_26","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:11:50Z","timestamp":1788988310000},"page":"467-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ID-LoRA: Identity-Driven Audio-Video Personalization with\u00a0In-Context LoRA"],"prefix":"10.1007","author":[{"given":"Aviad","family":"Dahan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moran","family":"Yanuka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noa","family":"Kraicer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lior","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raja","family":"Giryes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Chen, A., et al.: Just-dub-it: video dubbing via joint audio-visual diffusion (2026). https:\/\/arxiv.org\/abs\/2601.22143","DOI":"10.1145\/3799902.3811061"},{"issue":"6","key":"26_CR2","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: WavLM: Large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"26_CR3","unstructured":"Chen, S., et al.: Talkvid: a large-scale diversified dataset for audio-driven talking head synthesis (2025)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Asian Conference on Computer Vision, pp. 251\u2013263. Springer (2016)","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. arXiv preprint arXiv:2005.07143 (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"26_CR7","unstructured":"Du, Z., et\u00a0al.: CosyVoice: a scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens. arXiv preprint arXiv:2407.05407 (2024)"},{"key":"26_CR8","unstructured":"Du, Z., et\u00a0al.: CosyVoice 3: towards in-the-wild speech generation via scaling-up and post-training. arXiv preprint arXiv:2505.17589 (2025)"},{"key":"26_CR9","unstructured":"ElevenLabs: Elevenlabs. https:\/\/elevenlabs.io\/. Accessed 02 Mar 2026"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Elizalde, B., Deshmukh, S., Al\u00a0Ismail, M., Wang, H.: Clap learning audio concepts from natural language supervision. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"26_CR11","unstructured":"Flynn, J., et al.: EditYourself: audio-driven generation and manipulation of talking head videos with diffusion transformers. arXiv preprint arXiv:2601.22127 (2026)"},{"key":"26_CR12","doi-asserted-by":"publisher","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion (2022). https:\/\/doi.org\/10.48550\/ARXIV.2208.01618, https:\/\/arxiv.org\/abs\/2208.01618","DOI":"10.48550\/ARXIV.2208.01618"},{"key":"26_CR13","unstructured":"Google DeepMind: Nano Banana Pro (gemini 3 pro image) (2026). https:\/\/blog.google\/innovation-and-ai\/products\/nano-banana-pro\/"},{"key":"26_CR14","unstructured":"Guo, X., et al.: Dreamid-omni: Unified framework for controllable human-centric audio-video generation (2026). https:\/\/arxiv.org\/abs\/2602.12160"},{"key":"26_CR15","unstructured":"HaCohen, Y., et al.: LTX-2: efficient joint audio-visual foundation model (2026). https:\/\/arxiv.org\/abs\/2601.03233"},{"key":"26_CR16","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"26_CR17","unstructured":"Huang, L., et al.: In-context lora for diffusion transformers. arXiv preprint arXiv:2410.23775 (2024)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Hyung, J., Kim, K., Hong, S., Kim, M.J., Choo, J.: Spatiotemporal skip guidance for enhanced video diffusion sampling. arXiv preprint arXiv:2411.18664 (2024)","DOI":"10.1109\/CVPR52734.2025.01028"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Han, Z., Mao, C., Zhang, J., Pan, Y., Liu, Y.: VACE: all-in-one video creation and editing (2025). https:\/\/arxiv.org\/abs\/2503.07598","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"26_CR20","unstructured":"Kuaishou Technology: Kling 2.6 pro: Audio-visual generation model (2026). https:\/\/app.klingai.com\/global\/. Accessed 2026"},{"key":"26_CR21","unstructured":"Lightricks: LTX-2.3 (2026). https:\/\/ltx.io\/model\/ltx-2-3. Accessed 21 June 2026"},{"key":"26_CR22","doi-asserted-by":"publisher","first-page":"2871","DOI":"10.1109\/TASLP.2024.3399607","volume":"32","author":"H Liu","year":"2024","unstructured":"Liu, H., et al.: AudioLDM 2: learning holistic audio generation with self-supervised pretraining. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 2871\u20132883 (2024). https:\/\/doi.org\/10.1109\/TASLP.2024.3399607","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"26_CR23","unstructured":"Liu, K., et\u00a0al.: JavisDiT: joint audio-video diffusion transformer with hierarchical spatio-temporal prior synchronization. arXiv preprint arXiv:2503.23377 (2025)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Liu, L., et al.: Phantom: subject-consistent video generation via cross-modal alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14951\u201314961 (2025)","DOI":"10.1109\/ICCV51701.2025.01387"},{"key":"26_CR25","unstructured":"Low, C., Wang, W., Katyal, C.: OVI: twin backbone cross-modal fusion for audio-video generation (2025). https:\/\/arxiv.org\/abs\/2510.01284"},{"key":"26_CR26","doi-asserted-by":"publisher","unstructured":"Peng, P., Huang, P.Y., Li, S.W., Mohamed, A., Harwath, D.: VoiceCraft: zero-shot speech editing and text-to-speech in the wild. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12442\u201312462. Association for Computational Linguistics, Bangkok (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.673, https:\/\/aclanthology.org\/2024.acl-long.673\/","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"26_CR27","unstructured":"Polaczek, S., Patashnik, O., Mahdavi-Amiri, A., Cohen-Or, D.: In-context sync-lora for portrait video editing (2025). https:\/\/arxiv.org\/abs\/2512.03013"},{"key":"26_CR28","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"},{"key":"26_CR29","unstructured":"Qiang, C., et\u00a0al.: MM-sonate: multimodal controllable audio-video generation with zero-shot voice cloning. arXiv preprint arXiv:2601.01568 (2026)"},{"key":"26_CR30","doi-asserted-by":"publisher","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision (2022). https:\/\/doi.org\/10.48550\/ARXIV.2212.04356, https:\/\/arxiv.org\/abs\/2212.04356","DOI":"10.48550\/ARXIV.2212.04356"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"26_CR32","unstructured":"Vyas, A., et\u00a0al.: AudioBox: unified audio generation with natural language prompts. arXiv preprint arXiv:2312.15821 (2023)"},{"key":"26_CR33","unstructured":"Wan, T., et al.: WAN: open and advanced large-scale video generative models (2025). https:\/\/arxiv.org\/abs\/2503.20314"},{"key":"26_CR34","unstructured":"Wang, C., et al.: Neural codec language models are zero-shot text to speech synthesizers (2023). https:\/\/arxiv.org\/abs\/2301.02111"},{"key":"26_CR35","unstructured":"Wang, C., et al.: UniSpeech: unified speech representation learning with labeled and unlabeled data. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 10937\u201310947. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/wang21y.html"},{"key":"26_CR36","unstructured":"Wang, J., Qiang, C., Guo, Y., Wang, Y., Zeng, X., Deng, F.: Apollo: unified multi-task audio-video joint generation (2026). https:\/\/arxiv.org\/abs\/2601.04151"},{"key":"26_CR37","unstructured":"Wang, K., Deng, S., Shi, J., Hatzinakos, D., Tian, Y.: AV-DiT: efficient audio-visual diffusion transformer for joint audio and video generation (2024). https:\/\/arxiv.org\/abs\/2406.07686"},{"key":"26_CR38","unstructured":"Wang, Q., et al.: InstantID: zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:2401.07519 (2024)"},{"key":"26_CR39","unstructured":"Wang, Y., et al.: MaskGCT: zero-shot text-to-speech with masked generative codec transformer. arXiv preprint arXiv:2409.00750 (2024)"},{"key":"26_CR40","unstructured":"Xu, M., et al.: Hallo: hierarchical audio-driven visual synthesis for portrait image animation. arXiv preprint arXiv:2406.08801 (2024)"},{"key":"26_CR41","doi-asserted-by":"crossref","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)","DOI":"10.52202\/079017-0021"},{"key":"26_CR42","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"26_CR43","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":"26_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, H., et al.: CelebV-HQ: a large-scale video facial attributes dataset. In: European Conference on Computer Vision, pp. 650\u2013667. Springer (2022)","DOI":"10.1007\/978-3-031-20071-7_38"}],"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\/978-3-032-37026-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:11:58Z","timestamp":1788988318000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37026-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370259","9783032370266"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37026-6_26","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":"10 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"}}]}}