{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:09:09Z","timestamp":1789124949797,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370372","type":"print"},{"value":"9783032370389","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\/978-3-032-37038-9_37","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:42:50Z","timestamp":1789123370000},"page":"650-667","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MMControl: Unified Multi-modal Control for\u00a0Joint Audio-Video Generation"],"prefix":"10.1007","author":[{"given":"Liyang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Canyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianjian","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyue","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"37_CR1","unstructured":"Blattmann, A., et al.: Stable video diffusion: Scaling latent video diffusion models to large datasets (2023). arXiv preprint arXiv:2311.15127"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: High-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"6","key":"37_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3687945","volume":"43","author":"H Chefer","year":"2024","unstructured":"Chefer, H., et al.: Still-moving: Customized video generation without customized video data. ACM Trans. Graph. (TOG) 43(6), 1\u201311 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Disenstudio: customized multi-subject text-to-video generation with disentangled spatial control. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 3637\u20133646 (2024)","DOI":"10.1145\/3664647.3680637"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Chen, T.S., et al.: Multi-subject open-set personalization in video generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6099\u20136110 (2025)","DOI":"10.1109\/CVPR52734.2025.00572"},{"key":"37_CR7","unstructured":"Chen, W., et al.: Control-a-video: Controllable text-to-video diffusion models with motion prior and reward feedback learning. arXiv preprint arXiv:2305.13840 (2023)"},{"key":"37_CR8","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":"37_CR9","unstructured":"Cui, J., et al.: Hallo2: Long-duration and high-resolution audio-driven portrait image animation. In: ICLR (2025)"},{"key":"37_CR10","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_CR11","doi-asserted-by":"crossref","unstructured":"Deng, Y., Wang, R., Zhang, Y., Tai, Y.W., Tang, C.K.: Dragvideo: interactive drag-style video editing. In: European Conference on Computer Vision, pp. 183\u2013199. Springer (2024)","DOI":"10.1007\/978-3-031-72992-8_11"},{"key":"37_CR12","unstructured":"Fei, Z., et\u00a0al.: Skyreels-a2: Compose anything in video diffusion transformers. arXiv preprint arXiv:2504.02436 (2025)"},{"key":"37_CR13","unstructured":"GoogleDeepMind: Veo3. https:\/\/deepmind.google\/models\/veo\/ (2025). Accessed 28 June 2026"},{"key":"37_CR14","unstructured":"HaCohen, Y., et\u00a0al.: Ltx-2: Efficient joint audio-visual foundation model. arXiv preprint arXiv:2601.03233 (2026)"},{"key":"37_CR15","unstructured":"He, X., .: Id-animator: Zero-shot identity-preserving human video generation (2024). arXiv preprint arXiv:2404.15275"},{"key":"37_CR16","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR17","doi-asserted-by":"publisher","first-page":"8633","DOI":"10.52202\/068431-0628","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. Adv. Neural. Inf. Process. Syst. 35, 8633\u20138646 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR18","unstructured":"Hu, T., et al.: Hunyuancustom: A multimodal-driven architecture for customized video generation. arXiv preprint arXiv:2505.04512 (2025)"},{"key":"37_CR19","unstructured":"Huang, Y., et al.: Conceptmaster: Multi-concept video customization on diffusion transformer models without test-time tuning. arXiv preprint arXiv:2501.04698 (2025)"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: Vbench: Comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"37_CR21","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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17191\u201317202 (2025)","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: Text-to-image diffusion models are zero-shot video generators. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15954\u201315964 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"37_CR23","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Gligen: Open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"37_CR25","unstructured":"Liu, K., et\u00a0al.: Javisdit: Joint audio-video diffusion transformer with hierarchical spatio-temporal prior synchronization. arXiv preprint arXiv:2503.23377 (2025)"},{"key":"37_CR26","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":"37_CR27","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: Follow your pose: Pose-guided text-to-video generation using pose-free videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4117\u20134125 (2024)","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"37_CR30","unstructured":"OpenAI: Sora 2. https:\/\/openai.com\/index\/sora-2\/ (2025). Accessed 28 June 2026"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"37_CR32","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":"37_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"37_CR34","unstructured":"Ravi, N., et\u00a0al.: Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference On Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"37_CR36","doi-asserted-by":"crossref","unstructured":"Shen, S., et al.: Difftalk: Crafting diffusion models for generalized audio-driven portraits animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1982\u20131991 (2023)","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"37_CR37","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: Vividtalk: One-shot audio-driven talking head generation based on 3D hybrid prior. In: 2025 International Conference on 3D Vision (3DV), pp. 713\u2013722. IEEE (2025)","DOI":"10.1109\/3DV66043.2025.00071"},{"key":"37_CR38","unstructured":"Team, O., et\u00a0al.: Mova: Towards scalable and synchronized video-audio generation. arXiv preprint arXiv:2602.08794 (2026)"},{"key":"37_CR39","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: Raft: Recurrent all-pairs field transforms for optical flow. In: European Conference on Computer Vision, pp. 402\u2013419. Springer (2020)","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"37_CR40","doi-asserted-by":"crossref","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 (2024)","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"37_CR41","unstructured":"Wan, T., et\u00a0al.: Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"37_CR42","unstructured":"Wang, D., et al.: Universe-1: Unified audio-video generation via stitching of experts. arXiv preprint arXiv:2509.06155 (2025)"},{"key":"37_CR43","doi-asserted-by":"publisher","first-page":"7594","DOI":"10.52202\/075280-0334","volume":"36","author":"X Wang","year":"2023","unstructured":"Wang, X., et al.: Videocomposer: compositional video synthesis with motion controllability. Adv. Neural. Inf. Process. Syst. 36, 7594\u20137611 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, A., Zhu, L., Guo, Y., Dou, Q., Li, Z.: Customvideo: Customizing text-to-video generation with multiple subjects. IEEE Transactions on Multimedia (2026)","DOI":"10.1109\/TMM.2026.3668653"},{"key":"37_CR45","doi-asserted-by":"crossref","unstructured":"Wei, C., et\u00a0al.: Mocha: Towards movie-grade talking character synthesis. arXiv preprint arXiv:2503.23307 (2025)","DOI":"10.52202\/085713-2369"},{"key":"37_CR46","unstructured":"Wei, H., Yang, Z., Wang, Z.: Aniportrait: Audio-driven synthesis of photorealistic portrait animation (2024). arXiv preprint arXiv:2403.17694 arXiv preprint"},{"key":"37_CR47","unstructured":"Wu, B., et\u00a0al.: Hunyuanvideo 1.5 technical report. arXiv preprint arXiv:2511.18870 (2025)"},{"key":"37_CR48","doi-asserted-by":"crossref","unstructured":"Wu, T., et al.: Customcrafter: Customized video generation with preserving motion and concept composition abilities. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 8469\u20138477 (2025)","DOI":"10.1609\/aaai.v39i8.32914"},{"key":"37_CR49","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., Jiang, H.: Omnicontrol: Control any joint at any time for human motion generation (2023). arXiv preprint arXiv:2310.08580"},{"key":"37_CR50","unstructured":"Xu, J., et\u00a0al.: Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215 (2025)"},{"key":"37_CR51","unstructured":"Xu, M., et al.: Hallo: Hierarchical audio-driven visual synthesis for portrait image animation. arXiv preprint arXiv:2406.08801 (2024)"},{"key":"37_CR52","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., et al.: Depth anything v2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR53","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zeng, A., Yuan, C., Li, Y.: Effective whole-body pose estimation with two-stages distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4210\u20134220. (2023)","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"37_CR54","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"37_CR55","doi-asserted-by":"crossref","unstructured":"Yuan, S., et al.: Identity-preserving text-to-video generation by frequency decomposition. arXiv preprint arXiv:2411.17440 (2024)","DOI":"10.32388\/TZIID6"},{"key":"37_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847. (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"37_CR57","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_CR58","unstructured":"Zhang, Y., Wei, Y., Jiang, D., ZHANG, X., Zuo, W., Tian, Q.: Controlvideo: Training-free controllable text-to-video generation. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"37_CR59","doi-asserted-by":"publisher","first-page":"11127","DOI":"10.52202\/075280-0491","volume":"36","author":"S Zhao","year":"2023","unstructured":"Zhao, S., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models. Adv. Neural. Inf. Process. Syst. 36, 11127\u201311150 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"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\/978-3-032-37038-9_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:43:06Z","timestamp":1789123386000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37038-9_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370372","9783032370389"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37038-9_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":"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"}}]}}