{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:52:28Z","timestamp":1770976348185,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698110","type":"print"},{"value":"9789819698127","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9812-7_3","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T07:26:57Z","timestamp":1753428417000},"page":"27-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MOTION: Multi-object Video Editing with Training-Free Attention Guidance"],"prefix":"10.1007","author":[{"given":"Qitong","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minfeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linchao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"3_CR1","unstructured":"Cong, Y., Xu, M., Christian, S., Chen, S., et al.: FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"3_CR2","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., Dekel, T.: Tokenflow: consistent diffusion features for consistent video editing. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"3_CR3","unstructured":"Jeong, H., Ye, J.C.: Ground-a-video: Zero-shot grounded video editing using text-to-image diffusion models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"3_CR4","unstructured":"Zhao, M., Wang, R., Bao, F., et al.: Controlvideo: Adding conditional control for one shot text-to-video editing 2(3) (2023). arXiv preprint arXiv:2305.17098"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Qi, C., Cun, X., Zhang, Y., et al.: Fatezero: fusing attentions for zero-shot text-based video editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15932\u201315942 (2023)","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, Y., Li, W., et al.: Video-p2p: Video editing with cross-attention control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8599\u20138608 (2024)","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et al.: 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":"3_CR8","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., et al.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"3_CR10","unstructured":"Wu, J.Z., Li, X., Gao, D., et al.: Cvpr 2023 text guided video editing competition (2023). arXiv preprint arXiv:2310.16003"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., Ge, Y., Wang, X., 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":"3_CR12","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., et al.: Prompt-to-prompt image editing with cross-attention control. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"3_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2022","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graphics (TOG) 42, 1\u201311 (2022)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Feng, R., Weng, W., Wang, Y., et al.: Ccedit: Creative and controllable video editing via diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6712\u20136722 (2024)","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"3_CR15","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":"3_CR16","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-031-72992-8_16","volume-title":"Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part LVI","author":"R Zhao","year":"2025","unstructured":"Zhao, R., Gu, Y., Wu, J.Z., et al.: MotionDirector: motion customization of\u00a0text-to-video diffusion models. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024: 18th European Conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part LVI, pp. 273\u2013290. Springer Nature Switzerland, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72992-8_16"},{"key":"3_CR17","unstructured":"Wang, J., Ma, Y., Guo, J., et al.: Cove: Unleashing the diffusion feature correspondence for consistent video editing (2024). arXiv preprint arXiv:2406.08850"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhou, Y., Liu, Z., Loy, C.C.: Fresco: Spatial-temporal correspondence for zero-shot video translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8703\u20138712 (2024)","DOI":"10.1109\/CVPR52733.2024.00831"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., et al.: Gligen: Open- set grounded text-to-image generation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"3_CR20","unstructured":"Yang, X., Zhu, L., Fan, H., Yang, Y.: Eva: Zero-shot accurate attributes and multi- object video editing (2024). arXiv preprint arXiv:2403.16111"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5\u20139, 2015, proceedings, part III 18, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3_CR22","unstructured":"Guo, Y., Yang, C., Rao, A., et al.: Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"3_CR23","unstructured":"Ren, T., Liu, S., Zeng, A., et al.: Grounded sam: Assembling open-world models for diverse visual tasks (2024). arXiv preprint arXiv:2401.14159"},{"key":"3_CR24","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., et al.: Zoedepth: Zero-shot transfer by combining relative and metric depth (2023). arXiv preprint arXiv:2302.12288"},{"key":"3_CR25","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":"3_CR26","doi-asserted-by":"crossref","unstructured":"Fan, H., Lin, L., Yang, F., et al.: Lasot: A high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"3_CR27","unstructured":"Achiam, J., Adler, S., et al.: Gpt-4 technical report (2023). arXiv preprint arXiv:2303.08774"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Sun, Z., Fang, Y., Wu, T., et al.: Alpha-clip: A clip model focusing on wherever you want. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13019\u201313029 (2024)","DOI":"10.1109\/CVPR52733.2024.01237"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9812-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T08:57:21Z","timestamp":1770973041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9812-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698110","9789819698127"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9812-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}