{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T10:17:34Z","timestamp":1789726654459,"version":"4.0.1"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375735","type":"print"},{"value":"9783032375742","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\/978-3-032-37574-2_6","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:26:02Z","timestamp":1789251962000},"page":"96-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation"],"prefix":"10.1007","author":[{"given":"Shihao","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanyue","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shansong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhizhi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Lei","family":"Zhang","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":"Zhigang","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"6_CR1","unstructured":"Abu-El-Haija, S., Kothari, N., Lee, J., Natsev, A.P., Toderici, G., Varadarajan, B., Vijayanarasimhan, S.: Youtube-8m: a large-scale video classification benchmark (2016). arXiv:1609.08675, https:\/\/arxiv.org\/pdf\/1609.08675v1.pdf"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"An, H., Hu, W., Huang, S., Huang, S., Li, R., Liang, Y., Shao, J., Song, Y., Wang, Z., Yuan, C., Zhang, C., Zhang, H., Zhuang, W., Li, X.: Ai flow: perspectives, scenarios, and approaches (2025). https:\/\/arxiv.org\/abs\/2506.12479","DOI":"10.1007\/s44336-025-00031-y"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, B., Monso, D.M., Du, Y., Simchowitz, M., Tedrake, R., Sitzmann, V.: Diffusion forcing: next-token prediction meets full-sequence diffusion (2024). https:\/\/arxiv.org\/abs\/2407.01392","DOI":"10.52202\/079017-0759"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Vedaldi, A., Zisserman, A.: Vggsound: A large-scale audio-visual dataset. In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2020)","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"6_CR5","unstructured":"Chen, K., Zhang, J., Li, M., Zheng, Z., Fan, H.: Clusterstyle: Modeling intra-style diversity with prototypical clustering for stylized motion generation, (2025). arXiv:2512.02453"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Ishii, M., Hayakawa, A., Shibuya, T., Schwing, A., Mitsufuji, Y.: MMAudio: Taming multimodal joint training for high-quality video-to-audio synthesis, CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02691"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Workshop on Multi-view Lip-Reading, ACCV (2016)","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"6_CR8","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":"6_CR9","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., Ellis, D.P.W., Freedman, D., Jansen, A., Lawrence, W., Moore, R.C., Plakal, M., Ritter, M.: Audio set: an ontology and human-labeled dataset for audio events. In: Proceedings of IEEE ICASSP 2017, New Orleans, LA (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Girdhar, R., El-Nouby, A., Liu, Z., Singh, M., Alwala, K.V., Joulin, A., Misra, I.: ImageBind: one embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15180\u201315190 (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"6_CR11","unstructured":"Google DeepMind: Veo: a text-to-video generation system (2025). https:\/\/storage.googleapis.com\/deepmind-media\/veo\/Veo-3-Tech-Report.pdf"},{"key":"6_CR12","unstructured":"HaCohen, Y., Brazowski, B., Chiprut, N., Bitterman, Y., Kvochko, A., Berkowitz, A., Shalem, D., Lifschitz, D., Moshe, D., Porat, E., Richardson, E., Shiran, G., Chachy, I., Chetboun, J., Finkelson, M., Kupchick, M., Zabari, N., Guetta, N., Kotler, N., Bibi, O., Gordon, O., Panet, P., Benita, R., Armon, S., Kulikov, V., Inger, Y., Shiftan, Y., Melumian, Z., Farbman, Z.: LTX-2: efficient joint audio-visual foundation model (2026). https:\/\/arxiv.org\/abs\/2601.03233"},{"key":"6_CR13","unstructured":"Hu, T., Yu, Z., Zhang, G., Su, Z., Zhou, Z., Zhang, Y., Zhou, Y., Lu, Q., Yi, R.: Harmony: Harmonizing audio and video generation through cross-task synergy (2025). arXiv:2511.21579"},{"key":"6_CR14","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 (2025). https:\/\/arxiv.org\/abs\/2506.08009","DOI":"10.52202\/085713-5576"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Iashin, V., Xie, W., Rahtu, E., Zisserman, A.: Synchformer: efficient synchronization from sparse cues. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5325\u20135329. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10448489"},{"issue":"1","key":"6_CR16","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":"6_CR17","doi-asserted-by":"crossref","unstructured":"Li, H., Xu, M., Zhan, Y., Mu, S., Li, J., Cheng, K., Chen, Y., Chen, T., Ye, M., Wang, J., Zhu, S.: Openhumanvid: a large-scale high-quality dataset for enhancing human-centric video generation (2025). https:\/\/arxiv.org\/abs\/2412.00115","DOI":"10.1109\/CVPR52734.2025.00726"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Li, X., Wang, S., Zeng, S., et\u00a0al.: A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth 1(9) (2024). https:\/\/doi.org\/10.1007\/s44336-024-00009-2","DOI":"10.1007\/s44336-024-00009-2"},{"issue":"6","key":"6_CR19","doi-asserted-by":"publisher","first-page":"8708","DOI":"10.1109\/TNNLS.2022.3224577","volume":"35","author":"X Li","year":"2024","unstructured":"Li, X.: Positive-incentive noise. IEEE Trans. Neural Netw. Learn. Syst. 35(6), 8708\u20138714 (2024). https:\/\/doi.org\/10.1109\/TNNLS.2022.3224577","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"6_CR20","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling (2023). https:\/\/arxiv.org\/abs\/2210.02747"},{"key":"6_CR21","unstructured":"Liu, H., Lan, G.L., Mei, X., Ni, Z., Kumar, A., Nagaraja, V., Wang, W., Plumbley, M.D., Shi, Y., Chandra, V.: SyncFlow: toward temporally aligned joint audio-video generation from text (2024). https:\/\/arxiv.org\/abs\/2412.15220"},{"key":"6_CR22","unstructured":"Liu, K., Li, W., Chen, L., Wu, S., Zheng, Y., Ji, J., Zhou, F., Jiang, R., Luo, J., Fei, H., et\u00a0al.: JavisDiT: joint audio-video diffusion transformer with hierarchical spatio-temporal prior synchronization (2025). arXiv:2503.23377"},{"key":"6_CR23","unstructured":"Liu, K., Hu, W., Xu, J., Shan, Y., Lu, S.: Rolling forcing: autoregressive long video diffusion in real time (2025). https:\/\/arxiv.org\/abs\/2509.25161"},{"key":"6_CR24","unstructured":"Low, C., Wang, W., Katyal, C.: Ovi: twin backbone cross-modal fusion for audio-video generation (2025). arXiv:2510.01284"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Mei, X., Meng, C., Liu, H., Kong, Q., Ko, T., Zhao, C., Plumbley, M.D., Zou, Y., Wang, W.: WavCaps: a ChatGPT-assisted weakly-labelled audio captioning dataset for audio-language multimodal research. In: IEEE\/ACM Transactions on Audio, Speech, and Language Processing, pp. 1\u201315 (2024)","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"6_CR26","unstructured":"OpenAI: Sora 2 system card (2025). https:\/\/cdn.openai.com\/pdf\/50d5973c-c4ff-4c2d-986f-c72b5d0ff069\/ sora_2_system_card.pdf"},{"key":"6_CR27","doi-asserted-by":"publisher","unstructured":"Prajwal, K.R., 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. MM \u201820, ACM (2020). https:\/\/doi.org\/10.1145\/3394171.3413532","DOI":"10.1145\/3394171.3413532"},{"key":"6_CR28","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning. pp. 28492\u201328518. PMLR (2023)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Ruan, L., Ma, Y., Yang, H., He, H., Liu, B., Fu, J., Yuan, N.J., Jin, Q., Guo, B.: Mm-diffusion: learning multi-modal diffusion models for joint audio and video generation. CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"6_CR30","doi-asserted-by":"publisher","first-page":"25278","DOI":"10.52202\/068431-1833","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al.: LAION-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR31","doi-asserted-by":"publisher","unstructured":"Shen, Y., Zhang, D.: A survey of language-guided video object segmentation: from referring to reasoning. Vicinagearth 2(9) (2025). https:\/\/doi.org\/10.1007\/s44336-025-00018-9","DOI":"10.1007\/s44336-025-00018-9"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"SII-OpenMOSS Team, Yu, D., Chen, M., Chen, Q., Luo, Q., Wu, Q., Cheng, Q., Li, R., Liang, T., Zhang, W., Tu, W., Peng, X., Gao, Y., Huo, Y., Zhu, Y., Luo, Y., Zhang, Y., Song, Y., Xu, Z., Zhang, Z., Yang, C., Chang, C., Zhou, C., Chen, H., Ma, H., Li, J., Tong, J., Liu, J., Chen, K., Li, S., Wang, S., Jiang, W., Fei, Z., Ning, Z., Li, C., Li, C., He, Z., Huang, Z., Chen, X., Qiu, X.: Mova: Towards scalable and synchronized video-audio generation (2026) (Technical report. Corresponding authors: Xie Chen and Xipeng Qiu. Project leaders: Qinyuan Cheng and Tianyi Liang). https:\/\/doi.org\/10.48550\/arXiv.2602.08794","DOI":"10.48550\/arXiv.2602.08794"},{"key":"6_CR33","unstructured":"Sim\u00e9oni, O., Vo, H.V., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., Khalidov, V., Szafraniec, M., Yi, S., Ramamonjisoa, M., et\u00a0al.: Dinov3 (2025). arXiv:2508.10104"},{"key":"6_CR34","unstructured":"Song, K., Chen, B., Simchowitz, M., Du, Y., Tedrake, R., Sitzmann, V.: History-guided video diffusion (2025). https:\/\/arxiv.org\/abs\/2502.06764"},{"key":"6_CR35","unstructured":"Song, Q., He, Y., Zhang, Y., Cheng, S., He, Z., Guo, Z., Zhang, C., Li, X., Jiang, C.: InteractiveAvatar: real-time streaming video generation for consistent and intent-aware avatars (2026). https:\/\/arxiv.org\/abs\/2606.22905"},{"key":"6_CR36","unstructured":"Team, O., Yu, D., Chen, M., Chen, Q., Luo, Q., Wu, Q., Cheng, Q., Li, R., Liang, T., Zhang, W., Tu, W., Peng, X., Gao, Y., Huo, Y., Zhu, Y., Luo, Y., Zhang, Y., Song, Y., Xu, Z., Zhang, Z., Yang, C., Chang, C., Zhou, C., Chen, H., Ma, H., Li, J., Tong, J., Liu, J., Chen, K., Li, S., Jiang, S., Wang, S., Jiang, W., Fei, Z., Ning, Z., Li, C., Li, C., He, Z., Huang, Z., Chen, X., Qiu, X.: MOVA: towards scalable and synchronized video-audio generation (2026). https:\/\/arxiv.org\/abs\/2602.08794"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Tian, Z., Liu, Z., Yuan, R., Pan, J., Liu, Q., Tan, X., Chen, Q., Xue, W., Guo, Y.: VidMuse: a simple video-to-music generation framework with long-short-term modeling. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 18782\u201318793 (2025)","DOI":"10.1109\/CVPR52734.2025.01750"},{"key":"6_CR38","unstructured":"Vyas, A., Shi, B., Le, M., Tjandra, A., Wu, Y.C., Guo, B., Zhang, J., Zhang, X., Adkins, R., Ngan, W., et\u00a0al.: Audiobox: Unified audio generation with natural language prompts (2023). arXiv:2312.15821"},{"key":"6_CR39","unstructured":"Wan, T., Wang, A., Ai, B., Wen, B., Mao, C., Xie, C.W., Chen, D., Yu, F., Zhao, H., Yang, J., et\u00a0al.: Wan: open and advanced large-scale video generative models (2025). arXiv:2503.20314"},{"key":"6_CR40","unstructured":"Wang, D., Zuo, W., Li, A., Chen, L.H., Liao, X., Zhou, D., Yin, Z., Dai, X., Jiang, D., Yu, G.: Universe-1: unified audio-video generation via stitching of experts (2025). arXiv:2509.06155"},{"key":"6_CR41","unstructured":"Wang, J., Deng, H., Pan, T., Liu, Y., Wang, C., Zhang, F., Qi, Y., Wang, X.: UDM-GRPO: stable and efficient group relative policy optimization for uniform discrete diffusion models (2026). https:\/\/arxiv.org\/abs\/2604.18518"},{"key":"6_CR42","unstructured":"Wang, J.C., Lu, W.T., Chen, J.: Mel-RoFormer for vocal separation and vocal melody transcription (2024). https:\/\/arxiv.org\/abs\/2409.04702"},{"key":"6_CR43","unstructured":"Wang, L.X.X., Zhang, H., Dong, C., Shan, Y.: VFHQ: a high-quality dataset and benchmark for video face super-resolution (2022). https:\/\/arxiv.org\/abs\/2205.03409"},{"key":"6_CR44","doi-asserted-by":"publisher","first-page":"65618","DOI":"10.52202\/079017-2096","volume":"37","author":"W Wang","year":"2024","unstructured":"Wang, W., Yang, Y.: VidProM: a million-scale real prompt-gallery dataset for text-to-video diffusion models. Adv. Neural. Inf. Process. Syst. 37, 65618\u201365642 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR45","unstructured":"Xiao, A., Cheng, S., Xu, Y., Ren, Y., Chen, H., Yokoya, N.: GeoMMBench and GeoMMAgent: toward expert-level multimodal intelligence in geoscience and remote sensing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 34843\u201334853 (2026)"},{"key":"6_CR46","unstructured":"Yao, Z., Guo, L., Yang, X., Kang, W., Kuang, F., Yang, Y., Jin, Z., Lin, L., Povey, D.: Zipformer: A faster and better encoder for automatic speech recognition (2024). https:\/\/arxiv.org\/abs\/2310.11230"},{"key":"6_CR47","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. CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01422"},{"key":"6_CR48","unstructured":"Yuan, R., Lin, H., Guo, S., Zhang, G., Pan, J., Zang, Y., Liu, H., Du, X., Du, X., Ye, Z., Zheng, T., Jiang, Z., Ma, Y., Liu, M., Yu, L., Tian, Z., Zhou, Z., Xue, L., Qu, X., Li, Y., Shen, T., Ma, Z., Wu, S., Zhan, J., Wang, C., Wang, Y., Zhou, X., Chi, X., Zhang, X., Yang, Z., Liang, Y., Wang, X., Liu, S., Mei, L., Li, P., Chen, Y., Lin, C., Chen, X., Xia, G., Zhang, Z., Zhang, C., Chen, W., Zhou, X., Qiu, X., Dannenberg, R., Liu, J., Yang, J., Huang, S., Xue, W., Tan, X., Guo, Y.: Yue: Open music foundation models for full-song generation (2025) (gitHub repository). https:\/\/github.com\/multimodal-art-projection\/YuE"},{"key":"6_CR49","unstructured":"Yuan, R., Lin, H., Guo, S., Zhang, G., Pan, J., Zang, Y., Liu, H., Liang, Y., Ma, W., Du, X., Du, X., Ye, Z., Zheng, T., Jiang, Z., Ma, Y., Liu, M., Tian, Z., Zhou, Z., Xue, L., Qu, X., Li, Y., Wu, S., Shen, T., Ma, Z., Zhan, J., Wang, C., Wang, Y., Chi, X., Zhang, X., Yang, Z., Wang, X., Liu, S., Mei, L., Li, P., Wang, J., Yu, J., Pang, G., Li, X., Wang, Z., Zhou, X., Yu, L., Benetos, E., Chen, Y., Lin, C., Chen, X., Xia, G., Zhang, Z., Zhang, C., Chen, W., Zhou, X., Qiu, X., Dannenberg, R., Liu, J., Yang, J., Huang, W., Xue, W., Tan, X., Guo, Y.: Yue: Scaling open foundation models for long-form music generation (2025). https:\/\/arxiv.org\/abs\/2503.08638"},{"key":"6_CR50","unstructured":"Zhang, G., Zhou, Z., Hu, T., Peng, Z., Zhang, Y., Chen, Y., Zhou, Y., Lu, Q., Wang, L.: UniAVGen: unified audio and video generation with asymmetric cross-modal interactions. arXiv:2511.03334 (2025)"},{"issue":"9","key":"6_CR51","doi-asserted-by":"publisher","first-page":"8313","DOI":"10.1109\/TPAMI.2025.3575295","volume":"47","author":"H Zhang","year":"2025","unstructured":"Zhang, H., Huang, S., Guo, Y., Li, X.: Variational positive-incentive noise: how noise benefits models. IEEE Trans. Pattern Anal. Mach. Intell. 47(9), 8313\u20138320 (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3575295","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR52","unstructured":"Zhang, X., Cai, Y., Li, K., Yang, K., Zhou, Y., Li, Z., Chu, X., Zhang, J., Liu, H.: Personagesture: Single-reference co-speech gesture personalization for unseen speakers (2026). arXiv:2605.06064"},{"key":"6_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, J., Ren, J., Zhang, J.: Mitigating error accumulation in co-speech motion generation via global rotation diffusion and multi-level constraints. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a040, pp. 12834\u201312842 (2026)","DOI":"10.1609\/aaai.v40i15.38281"},{"key":"6_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, J., Zhang, J., Dang, Z., Ren, J., Bo, L., Tu, Z.: SemTalk: holistic co-speech motion generation with frame-level semantic emphasis (2024). arXiv:2412.16563","DOI":"10.1109\/ICCV51701.2025.01277"},{"key":"6_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, J., Zhang, J., Ren, J., Bo, L., Tu, Z.: EchoMask: speech-queried attention-based mask modeling for holistic co-speech motion generation (2025). https:\/\/arxiv.org\/abs\/2504.09209","DOI":"10.1145\/3746027.3754847"},{"key":"6_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Foo, L.G., Rahmani, H., Liu, J., Soh, D.W.: Performing defocus deblurring by modeling its formation process. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5791\u20135801 (2025)","DOI":"10.1109\/ICCV51701.2025.00548"},{"key":"6_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Huang, M.H., Tu, Z., Yang, M.H.: Dart: Difficulty-adaptive routing for zero-shot video temporal grounding. In: European Conference on Computer Vision (2026)","DOI":"10.1007\/978-3-032-37095-2_5"},{"key":"6_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Tu, Z., Yuan, J., Soh, D.W., Du, B.: Leveraging text-to-image diffusion models for unsupervised visual object tracking. IEEE Trans. Pattern Anal. Mach. Intell. (2026)","DOI":"10.1109\/TPAMI.2026.3697145"},{"key":"6_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhou, Y., Peng, D., Lim, J.H., Tu, Z., Soh, D.W., Foo, L.G.: Visual prompting for one-shot controllable video editing without inversion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7784\u20137794 (2025)","DOI":"10.1109\/CVPR52734.2025.00729"},{"key":"6_CR60","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":"6_CR61","unstructured":"Zhao, L., Feng, L., Ge, D., Chen, R., Yi, F., Zhang, C., Zhang, X.L., Li, X.: Uniform: A unified multi-task diffusion transformer for audio-video generation (2025). https:\/\/arxiv.org\/abs\/2502.03897"},{"key":"6_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, H., Kang, W., Yao, Z., Guo, L., Kuang, F., Li, Z., Zhuang, W., Lin, L., Povey, D.: Zipvoice: fast and high-quality zero-shot text-to-speech with flow matching. arXiv:2506.13053 (2025)","DOI":"10.1109\/ASRU65441.2025.11433841"}],"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\/978-3-032-37574-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:26:13Z","timestamp":1789251973000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37574-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375735","9783032375742"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37574-2_6","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":"13 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"}}]}}