{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:35:28Z","timestamp":1790012128790,"version":"4.0.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376268","type":"print"},{"value":"9783032376275","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\/978-3-032-37627-5_33","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:06:31Z","timestamp":1788984391000},"page":"607-623","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["OpenVE-3M: A Large-Scale High-Quality Dataset for\u00a0Instruction-Guided Video Editing Supplementary Material"],"prefix":"10.1007","author":[{"given":"Haoyang","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhucun","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyuan","family":"Bu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiangpeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilei","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"33_CR1","unstructured":"Creating anything (2025). https:\/\/runwayml.com\/"},{"key":"33_CR2","unstructured":"Bai, Q., et al.: Scaling instruction-based video editing with a high-quality synthetic dataset (2025). https:\/\/arxiv.org\/abs\/2510.15742"},{"key":"33_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"33_CR4","unstructured":"Bradski, G.: The OpenCV library. Dr. Dobb\u2019s J. Softw. Tools Prof. Program. 25(11), 120\u2013123 (2000)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Video depth anything: consistent depth estimation for super-long videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22831\u201322840 (2025)","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"33_CR7","unstructured":"Cheng, J., Xiao, T., He, T.: Consistent video-to-video transfer using synthetic dataset. arXiv preprint arXiv:2311.00213 (2023)"},{"key":"33_CR8","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"33_CR9","unstructured":"Dao, T.: Flashattention-2: faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)"},{"key":"33_CR10","unstructured":"Gao, Y., et\u00a0al.: Seedance 1.0: exploring the boundaries of video generation models. arXiv preprint arXiv:2506.09113 (2025)"},{"key":"33_CR11","unstructured":"Hu, J., et al.: Vivid-10m: a dataset and baseline for versatile and interactive video local editing. arXiv preprint arXiv:2411.15260 (2024)"},{"key":"33_CR12","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":"33_CR13","unstructured":"Ku, M., Wei, C., Ren, W., Yang, H., Chen, W.: Anyv2v: a tuning-free framework for any video-to-video editing tasks. arXiv preprint arXiv:2403.14468 (2024)"},{"key":"33_CR14","unstructured":"Labs, B.F., et\u00a0al.: Flux. 1 kontext: flow matching for in-context image generation and editing in latent space. arXiv preprint arXiv:2506.15742 (2025)"},{"key":"33_CR15","unstructured":"Li, X., Xue, H., Ren, P., Bo, L.: Diffueraser: a diffusion model for video inpainting. arXiv preprint arXiv:2501.10018 (2025)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Lian, L., et\u00a0al.: Describe anything: detailed localized image and video captioning. arXiv preprint arXiv:2504.16072 (2025)","DOI":"10.1109\/ICCV51701.2025.02021"},{"key":"33_CR17","unstructured":"Liao, X., Zeng, X., Song, Z., Fu, Z., Yu, G., Lin, G.: In-context learning with unpaired clips for instruction-based video editing (2025). https:\/\/arxiv.org\/abs\/2510.14648"},{"key":"33_CR18","unstructured":"Lin, B., et al.: Open-sora plan: open-source large video generation model. arXiv preprint arXiv:2412.00131 (2024)"},{"key":"33_CR19","unstructured":"Liu, S., et\u00a0al.: Step1x-edit: a practical framework for general image editing. arXiv preprint arXiv:2504.17761 (2025)"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Ma, J., et al.: X2edit: revisiting arbitrary-instruction image editing through self-constructed data and task-aware representation learning. arXiv preprint arXiv:2508.07607 (2025)","DOI":"10.1609\/aaai.v40i10.37719"},{"key":"33_CR21","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":"33_CR22","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":"33_CR23","unstructured":"Ravi, N., et al.: SAM 2: segment anything in images and videos (2024). https:\/\/arxiv.org\/abs\/2408.00714"},{"key":"33_CR24","unstructured":"Tan, Z., Yang, H., Qin, L., Gong, J., Yang, M., Li, H.: Omni-video: democratizing unified video understanding and generation. arXiv preprint arXiv:2507.06119 (2025)"},{"key":"33_CR25","unstructured":"Team, B.S.: Seed1.5-vl technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"key":"33_CR26","unstructured":"Team, D.: Lucy edit: open-weight text-guided video editing (2025). https:\/\/d2drjpuinn46lb.cloudfront.net\/Lucy_Edit__High_Fidelity_Text_Guided_Video_Editing.pdf"},{"key":"33_CR27","unstructured":"Wan, T., et al.: WAN: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"33_CR28","unstructured":"Wang, W., et al.: InternVL3. 5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"33_CR29","unstructured":"Wu, C., et\u00a0al.: Qwen-image Technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Insvie-1m: effective instruction-based video editing with elaborate dataset construction. arXiv preprint arXiv:2503.20287 (2025)","DOI":"10.1109\/ICCV51701.2025.01550"},{"key":"33_CR31","unstructured":"Xue, Z., et\u00a0al.: Ultravideo: high-quality UHD video dataset with comprehensive captions. arXiv preprint arXiv:2506.13691 (2025)"},{"key":"33_CR32","unstructured":"Yang, S., Hui, M., Zhao, B., Zhou, Y., Ruiz, N., Xie, C.: Complex-edit: cot-like instruction generation for complexity-controllable image editing benchmark. arXiv preprint arXiv:2504.13143 (2025)"},{"key":"33_CR33","unstructured":"Yang, X., et al.: VideoCOF: unified video editing with temporal reasoner. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 37940\u201337949 (2026)"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Ye, Y., et al.: ImgeDIT: a unified image editing dataset and benchmark. arXiv preprint arXiv:2505.20275 (2025)","DOI":"10.52202\/085713-4387"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Yu, Q., et al.: Anyedit: mastering unified high-quality image editing for any idea. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26125\u201326135 (2025)","DOI":"10.1109\/CVPR52734.2025.02433"},{"key":"33_CR36","unstructured":"Zhang, J., Huang, H., Zhang, P., Wei, J., Zhu, J., Chen, J.: Sageattention2: efficient attention with thorough outlier smoothing and per-thread int4 quantization. arXiv preprint arXiv:2411.10958 (2024)"},{"key":"33_CR37","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":"33_CR38","unstructured":"Zhang, Z., Dai, Z., Qin, L., Wang, W.: Effived: efficient video editing via text-instruction diffusion models. arXiv preprint arXiv:2403.11568 (2024)"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Zi, B., et al.: Minimax-remover: taming bad noise helps video object removal. arXiv preprint arXiv:2505.24873 (2025)","DOI":"10.52202\/085713-2536"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Zi, B., et al.: Senorita-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\/978-3-032-37627-5_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:06:37Z","timestamp":1788984397000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37627-5_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376268","9783032376275"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37627-5_33","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"}}]}}