{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:03:20Z","timestamp":1789459400239,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373236","type":"print"},{"value":"9783032373243","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\/978-3-032-37324-3_5","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T07:13:25Z","timestamp":1789456405000},"page":"75-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-turn Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2622-5595","authenticated-orcid":false,"given":"Dohun","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1268-6527","authenticated-orcid":false,"given":"Chun-Hao Paul","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0158-9469","authenticated-orcid":false,"given":"Xuelin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-9609","authenticated-orcid":false,"given":"Jong Chul","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2307-9052","authenticated-orcid":false,"given":"Duygu","family":"Ceylan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6864-4190","authenticated-orcid":false,"given":"Hyeonho","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"5_CR1","unstructured":"AI, D.: Open-weight text-guided video editing (2025). https:\/\/platform.decart.ai\/"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Bai, J., et al.: ReCamMaster: camera-controlled generative rendering from a single video. arXiv preprint arXiv:2503.11647 (2025)","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"5_CR3","unstructured":"Cai, S., et al.: Mixture of contexts for long video generation. arXiv preprint arXiv:2508.21058 (2025)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Ceylan, D., Huang, C.H.P., Mitra, N.J.: Pix2Video: video editing using image diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23206\u201323217 (2023)","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chen, B., Mart\u00ed Mons\u00f3, D., Du, Y., Simchowitz, M., Tedrake, R., Sitzmann, V.: Diffusion forcing: next-token prediction meets full-sequence diffusion. In: Advances in Neural Information Processing Systems, vol. 37, pp. 24081\u201324125 (2024)","DOI":"10.52202\/079017-0759"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chen, N., Huang, M., Meng, Y., Mao, Z.: LongAnimation: long animation generation with dynamic global-local memory. arXiv preprint arXiv:2507.01945 (2025)","DOI":"10.1109\/ICCV51701.2025.00935"},{"key":"5_CR7","unstructured":"Chen, W., et al.: Control-a-video: controllable text-to-video generation with diffusion models. arXiv e-prints arXiv:2305.13840 (2023)"},{"key":"5_CR8","unstructured":"Cong, Y., et al.: Flatten: optical flow-guided attention for consistent text-to-video editing. arXiv preprint arXiv:2310.05922 (2023)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Dalal, K., et al.: One-minute video generation with test-time training. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17702\u201317711 (2025)","DOI":"10.1109\/CVPR52734.2025.01649"},{"key":"5_CR10","unstructured":"Engine, U.: Unreal engine (2018). https:\/\/wwwunrealengine.com\/en-US\/what-is-unreal-engine-4"},{"key":"5_CR11","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Feng, R., et al.: CCEdit: creative and controllable video editing via diffusion models. arXiv preprint arXiv:2309.16496 (2023)","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"5_CR13","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., Dekel, T.: TokenFlow: consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373 (2023)"},{"key":"5_CR14","unstructured":"Greff, K., et al.: Kubric: a scalable dataset generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3749\u20133761 (2022)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Gu, Y., et al.: VideoSwap: customized video subject swapping with interactive semantic point correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7621\u20137630 (2024)","DOI":"10.1109\/CVPR52733.2024.00728"},{"key":"5_CR16","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":"5_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: 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":"5_CR18","doi-asserted-by":"publisher","unstructured":"Jeong, H., Chang, J., Park, G.Y., Ye, J.C.: DreamMotion: space-time self-similar score distillation for zero-shot video editing. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 358\u2013376. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73404-5_21","DOI":"10.1007\/978-3-031-73404-5_21"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Jeong, H., Lee, S., Ye, J.C.: Reangle-a-video: 4D video generation as video-to-video translation. arXiv preprint arXiv:2503.09151 (2025)","DOI":"10.1109\/ICCV51701.2025.01039"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Jeong, H., Park, G.Y., Ye, J.C.: VMC: video motion customization using temporal attention adaption for text-to-video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9212\u20139221 (2024)","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"5_CR21","unstructured":"Jeong, H., Ye, J.C.: Ground-a-video: zero-shot grounded video editing using text-to-image diffusion models. arXiv preprint arXiv:2310.01107 (2023)"},{"key":"5_CR22","unstructured":"Jiang, J., et al.: LoViC: efficient long video generation with context compression. arXiv preprint arXiv:2507.12952 (2025)"},{"key":"5_CR23","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. arXiv preprint arXiv:2503.07598 (2025)","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"5_CR24","unstructured":"Ju, X., et al.: EditVerse: unifying image and video editing and generation with in-context learning. arXiv preprint arXiv:2509.20360 (2025)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Kara, O., Kurtkaya, B., Yesiltepe, H., Rehg, J.M., Yanardag, P.: RAVE: randomized noise shuffling for fast and consistent video editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Kim, J., Kang, J., Choi, J., Han, B.: FIFO-diffusion: generating infinite videos from text without training. In: Advances in Neural Information Processing Systems, vol. 37, pp. 89834\u201389868 (2024)","DOI":"10.52202\/079017-2853"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Kulikov, V., Kleiner, M., Huberman-Spiegelglas, I., Michaeli, T.: FlowEdit: inversion-free text-based editing using pre-trained flow models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19721\u201319730 (2025)","DOI":"10.1109\/ICCV51701.2025.01834"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Li, R., Torr, P., Vedaldi, A., Jakab, T.: VMem: consistent interactive video scene generation with surfel-indexed view memory. arXiv preprint arXiv:2506.18903 (2025)","DOI":"10.1109\/ICCV51701.2025.02383"},{"key":"5_CR29","unstructured":"Meng, Y., Zhu, Z., Hui, L., Hou, J.: NVS-solver: video diffusion model as zero-shot novel view synthesizer. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"5_CR30","unstructured":"Nan, K., et al.: OpenVid-1M: a large-scale high-quality dataset for text-to-video generation. arXiv preprint arXiv:2407.02371 (2024)"},{"key":"5_CR31","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Ouyang, W., et al.: TokensGen: harnessing condensed tokens for long video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18197\u201318206 (2025)","DOI":"10.1109\/ICCV51701.2025.01691"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Po, R., et al.: Long-context state-space video world models. arXiv preprint arXiv:2505.20171 (2025)","DOI":"10.1109\/ICCV51701.2025.00817"},{"key":"5_CR34","unstructured":"Polyak, A., et al.: Movie Gen: a cast of media foundation models. arXiv preprint arXiv:2410.13720 (2024)"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Qin, B., Li, J., Tang, S., Chua, T.S., Zhuang, Y.: InstructVid2Vid: controllable video editing with natural language instructions. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10687529"},{"key":"5_CR36","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":"5_CR37","doi-asserted-by":"crossref","unstructured":"Ren, X., et al.: GEN3C: 3D-informed world-consistent video generation with precise camera control. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6121\u20136132 (2025)","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"5_CR38","unstructured":"Ruhe, D., Heek, J., Salimans, T., Hoogeboom, E.: Rolling diffusion models. arXiv:2402.09470 (2024)"},{"key":"5_CR39","unstructured":"Team, H., et al.: HunyuanWorld 1.0: generating immersive, explorable, and interactive 3D worlds from words or pixels. arXiv preprint arXiv:2507.21809 (2025)"},{"key":"5_CR40","doi-asserted-by":"publisher","unstructured":"Van Hoorick, B., et al.: Generative camera dolly: extreme monocular dynamic novel view synthesis. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 313\u2013331. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72691-0_18","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"5_CR41","unstructured":"Wang, Z., et al.: Epic: efficient video camera control learning with precise anchor-video guidance. arXiv preprint arXiv:2505.21876 (2025)"},{"key":"5_CR42","unstructured":"Wiedemer, T., et al.: Video models are zero-shot learners and reasoners. arXiv preprint arXiv:2509.20328 (2025)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"5_CR44","unstructured":"Xi, H., et al.: Sparse VideoGen: accelerating video diffusion transformers with spatial-temporal sparsity. arXiv preprint arXiv:2502.01776 (2025)"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Xiao, Z., et al.: WorldMem: long-term consistent world simulation with memory. arXiv preprint arXiv:2504.12369 (2025)","DOI":"10.52202\/085713-1659"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Yatim, D., Fridman, R., Bar-Tal, O., Dekel, T.: DynVFX: augmenting real videos with dynamic content. arXiv:2502.03621 (2025)","DOI":"10.1145\/3757377.3764008"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Yatim, D., Fridman, R., Bar-Tal, O., Kasten, Y., Dekel, T.: Space-time diffusion features for zero-shot text-driven motion transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8466\u20138476 (2024)","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"5_CR48","unstructured":"Yin, T., et al.: From slow bidirectional to fast causal video generators. arXiv e-prints arXiv:2412.07772 (2024)"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Context as memory: scene-consistent interactive long video generation with memory retrieval. arXiv preprint arXiv:2506.03141 (2025)","DOI":"10.1145\/3757377.3763833"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"YU, M., Hu, W., Xing, J., Shan, Y.: TrajectoryCrafter: redirecting camera trajectory for monocular videos via diffusion models. arXiv preprint arXiv:2503.05638 (2025)","DOI":"10.1109\/ICCV51701.2025.00017"},{"key":"5_CR51","unstructured":"Yu, S., et al.: Malt diffusion: memory-augmented latent transformers for any-length video generation. arXiv preprint arXiv:2502.12632 (2025)"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: ViewCrafter: taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:2409.02048 (2024)","DOI":"10.1109\/TPAMI.2025.3613256"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, D.J., et al.: Recapture: generative video camera controls for user-provided videos using masked video fine-tuning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2050\u20132062 (2025)","DOI":"10.1109\/CVPR52734.2025.00197"},{"key":"5_CR54","unstructured":"Zhang, J., et al.: SpargeAttention: accurate sparse attention accelerating any model inference. arXiv preprint arXiv:2502.18137 (2025)"},{"key":"5_CR55","unstructured":"Zhang, L., Agrawala, M.: Packing input frame context in next-frame prediction models for video generation. arXiv preprint arXiv:2504.126262(3), 5 (2025)"},{"key":"5_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VSA: faster video diffusion with trainable sparse attention. arXiv preprint arXiv:2505.13389 (2025)","DOI":"10.52202\/085713-5099"},{"key":"5_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Faster video diffusion with trainable sparse attention. arXiv e-prints arXiv:2505.13389v3 (2025)","DOI":"10.52202\/085713-5099"},{"key":"5_CR58","unstructured":"Zhang, T., et al.: Test-time training done right. arXiv preprint arXiv:2505.23884 (2025)"},{"key":"5_CR59","doi-asserted-by":"crossref","unstructured":"Zi, B., et al.: Se\u00f1orita-2M: a high-quality instruction-based dataset for general video editing by video specialists. arXiv preprint arXiv:2502.06734 (2025)","DOI":"10.52202\/085713-0506"}],"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\/978-3-032-37324-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T07:13:58Z","timestamp":1789456438000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37324-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373236","9783032373243"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37324-3_5","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":"16 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"}}]}}