{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:56:45Z","timestamp":1777568205845,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":56,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609161","type":"print"},{"value":"9789819609178","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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\/978-981-96-0917-8_7","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:54:42Z","timestamp":1733558082000},"page":"113-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["NewMove: Customizing Text-to-Video Models with\u00a0Novel Motions"],"prefix":"10.1007","author":[{"given":"Joanna","family":"Materzy\u0144ska","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eli","family":"Shechtman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Russell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: A joint video and image encoder for end-to-end retrieval. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S.W., Fidler, S., Kreis, K.: 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":"7_CR3","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":"7_CR4","doi-asserted-by":"crossref","unstructured":"Chai, W., Guo, X., Wang, G., Lu, Y.: Stablevideo: Text-driven consistency-aware diffusion video editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 23040\u201323050 (2023)","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 5933\u20135942 (2019)","DOI":"10.1109\/ICCV.2019.00603"},{"key":"7_CR6","unstructured":"Chen, H., Xia, M., He, Y., Zhang, Y., Cun, X., Yang, S., Xing, J., Liu, Y., Chen, Q., Wang, X., et\u00a0al.: Videocrafter1: Open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512 (2023)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Zhang, Y., Cun, X., Xia, M., Wang, X., Weng, C., Shan, Y.: Videocrafter2: Overcoming data limitations for high-quality video diffusion models. arXiv preprint arXiv:2401.09047 (2024)","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"7_CR8","unstructured":"Chen, W., Wu, J., Xie, P., Wu, H., Li, J., Xia, X., Xiao, X., Lin, L.: Control-a-video: Controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840 (2023)"},{"key":"7_CR9","unstructured":"Chen, W., Hu, H., Li, Y., Ruiz, N., Jia, X., Chang, M.W., Cohen, W.W.: Subject-driven text-to-image generation via apprenticeship learning. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"7_CR11","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A.H., Chechik, G., Cohen-Or, D.: An image is worth one word: Personalizing text-to-image generation using textual inversion. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Encoder-based domain tuning for fast personalization of text-to-image models. ACM Transactions on Graphics (TOG) (2023)","DOI":"10.1145\/3610548.3618173"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Orgad, H., Belinkov, Y., Materzy\u0144ska, J., Bau, D.: Unified concept editing in diffusion models. IEEE\/CVF Winter Conference on Applications of Computer Vision (2024)","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"7_CR14","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., Dekel, T.: Tokenflow: Consistent diffusion features for consistent video editing. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Gleicher, M.: Retargetting motion to new characters. In: Proceedings of the 25th annual conference on Computer graphics and interactive techniques (1998)","DOI":"10.1145\/280814.280820"},{"key":"7_CR16","unstructured":"Guo, Y., Yang, C., Rao, A., Liang, Z., Wang, Y., Qiao, Y., Agrawala, M., Lin, D., Dai, B.: Animatediff: Animate your personalized text-to-image diffusion models without specific tuning (v2) (2024)"},{"key":"7_CR17","unstructured":"Guo, Y., Yang, C., Rao, A., Wang, Y., Qiao, Y., Lin, D., Dai, B.: Animatediff: Animate your personalized text-to-image diffusion models without specific tuning (v1). arXiv preprint arXiv:2307.04725 (2023)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D., Yang, F.: Svdiff: Compact parameter space for diffusion fine-tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"7_CR19","unstructured":"Ho, J., Chan, W., Saharia, C., Whang, J., Gao, R., Gritsenko, A., Kingma, D.P., Poole, B., Norouzi, M., Fleet, D.J., et\u00a0al.: Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"7_CR20","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":"7_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wu, T., Jiang, Y., Chan, K.C., Liu, Z.: ReVersion: Diffusion-based relation inversion from images. arXiv preprint arXiv:2303.13495 (2023)","DOI":"10.1145\/3680528.3687658"},{"key":"7_CR22","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. arXiv preprint arXiv:2312.00845 (2023)","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., Movsisyan, A., Tadevosyan, V., Henschel, R., Wang, Z., Navasardyan, S., Shi, H.: Text2video-zero: Text-to-image diffusion models are zero-shot video generators. In: Proceedings of the International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Lee, J., Cho, K., Kiela, D.: Countering language drift via visual grounding. arXiv preprint arXiv:1909.04499 (2019)","DOI":"10.18653\/v1\/D19-1447"},{"key":"7_CR26","unstructured":"Lu, Y., Singhal, S., Strub, F., Courville, A., Pietquin, O.: Countering language drift with seeded iterated learning. In: International Conference on Machine Learning. PMLR (2020)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Materzynska, J., Berger, G., Bax, I., Memisevic, R.: The jester dataset: A large-scale video dataset of human gestures. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops. pp.\u00a00\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"7_CR28","unstructured":"Molad, E., Horwitz, E., Valevski, D., Acha, A.R., Matias, Y., Pritch, Y., Leviathan, Y., Hoshen, Y.: Dreamix: Video diffusion models are general video editors. arXiv preprint arXiv:2302.01329 (2023)"},{"key":"7_CR29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01413","volume-title":"A self-supervised descriptor for image copy detection","author":"E Pizzi","year":"2022","unstructured":"Pizzi, E., Roy, S.D., Ravindra, S.N., Goyal, P., Douze, M.: A self-supervised descriptor for image copy detection. Proc, CVPR (2022)"},{"key":"7_CR30","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. PMLR (2021)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. 2022 ieee. In: CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 10674\u201310685 (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: Animating arbitrary objects via deep motion transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00248"},{"key":"7_CR35","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. Advances in neural information processing systems (2019)"},{"key":"7_CR36","unstructured":"Singer, U., Polyak, A., Hayes, T., Yin, X., An, J., Zhang, S., Hu, Q., Yang, H., Ashual, O., Gafni, O., et\u00a0al.: Make-a-video: Text-to-video generation without text-video data. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"7_CR37","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Tewel, Y., Gal, R., Chechik, G., Atzmon, Y.: Key-locked rank one editing for text-to-image personalization. In: ACM SIGGRAPH 2023 Conference Proceedings. SIGGRAPH \u201923 (2023)","DOI":"10.1145\/3588432.3591506"},{"key":"7_CR39","unstructured":"Villegas, R., Babaeizadeh, M., Kindermans, P.J., Moraldo, H., Zhang, H., Saffar, M.T., Castro, S., Kunze, J., Erhan, D.: Phenaki: Variable length video generation from open domain textual description. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"7_CR40","unstructured":"Wang, B., Vastola, J.J.: Diffusion models generate images like painters: an analytical theory of outline first, details later. arXiv preprint arXiv:2303.02490 (2023)"},{"key":"7_CR41","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)"},{"key":"7_CR42","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Liu, G., Tao, A., Kautz, J., Catanzaro, B.: Video-to-video synthesis. Advances in Neural Information Processing Systems 31 (2018)"},{"key":"7_CR43","unstructured":"Wang, W., Yang, H., Tuo, Z., He, H., Zhu, J., Fu, J., Liu, J.: Videofactory: Swap attention in spatiotemporal diffusions for text-to-video generation. arXiv preprint arXiv:2305.10874 (2023)"},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, S., Qing, Z., Yuan, H., Liu, Z., Liu, Y., Zhang, Y., Zhou, J., Shan, H.: Dreamvideo: Composing your dream videos with customized subject and motion. arXiv preprint arXiv:2312.04433 (2023)","DOI":"10.1109\/CVPR52733.2024.00625"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Wiles, O., Koepke, A., Zisserman, A.: X2face: A network for controlling face generation using images, audio, and pose codes. In: Proceedings of the European conference on computer vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., Ge, Y., Wang, X., Lei, S.W., Gu, Y., Shi, Y., Hsu, W., Shan, Y., Qie, X., Shou, M.Z.: 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 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Wu, R., Chen, L., Yang, T., Guo, C., Li, C., Zhang, X.: Lamp: Learn a motion pattern for few-shot-based video generation. arXiv preprint arXiv:2310.10769 (2023)","DOI":"10.1109\/CVPR52733.2024.00677"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Yang, C., Wang, Z., Zhu, X., Huang, C., Shi, J., Lin, D.: Pose guided human video generation. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01249-6_13"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Yatim, D., Fridman, R., Tal, O.B., 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 (2024)","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"7_CR51","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: Controlvideo: Training-free controllable text-to-video generation. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"},{"key":"7_CR52","unstructured":"Zhang, Y., Tang, F., Huang, N., Huang, H., Ma, C., Dong, W., Xu, C.: Motioncrafter: One-shot motion customization of diffusion models. arXiv preprint arXiv:2312.05288 (2023)"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Zhao, R., Gu, Y., Wu, J.Z., Zhang, D.J., Liu, J., Wu, W., Keppo, J., Shou, M.Z.: Motiondirector: Motion customization of text-to-video diffusion models. arXiv preprint arXiv:2310.08465 (2023)","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"7_CR55","unstructured":"Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., Feng, J.: Magicvideo: Efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018 (2022)"},{"key":"7_CR56","unstructured":"Zhou, Y., Zhang, R., Sun, T., Xu, J.: Enhancing detail preservation for customized text-to-image generation: A regularization-free approach. arXiv preprint arXiv:2305.13579 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0917-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:25:19Z","timestamp":1733559919000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0917-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609161","9789819609178"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0917-8_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}