{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:01:25Z","timestamp":1778083285942,"version":"3.51.4"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730122","type":"print"},{"value":"9783031730139","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-73013-9_3","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:48:15Z","timestamp":1732607295000},"page":"35-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Pix2Gif: Motion-Guided Diffusion for\u00a0GIF Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6761-3368","authenticated-orcid":false,"given":"Hitesh","family":"Kandala","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2167-2880","authenticated-orcid":false,"given":"Jianwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Aigner, S., K\u00f6rner, M.: FutureGAN: anticipating the future frames of video sequences using spatio-temporal 3D convolutions in progressively growing GANs (2018)","DOI":"10.5194\/isprs-archives-XLII-2-W16-3-2019"},{"issue":"4","key":"3_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graph. 42(4), 1\u201311 (2023). https:\/\/doi.org\/10.1145\/3592450","journal-title":"ACM Trans. Graph."},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Baradaran, M., Bergevin, R.: Future video prediction from a single frame for video anomaly detection (2023)","DOI":"10.1007\/978-3-031-47969-4_37"},{"key":"3_CR4","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"3_CR6","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":"3_CR7","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers (2023)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MaskGIT: masked generative image transformer (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, S., Jeong, Y., Gwon, Y., Yoon, S.: ILVR: conditioning method for denoising diffusion probabilistic models (2021)","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"3_CR10","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. Adv. Neural. Inf. Process. Syst. 34, 19822\u201319835 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR11","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, pp. 7346\u20137356 (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"3_CR13","unstructured":"Fu, T.J., Hu, W., Du, X., Wang, W.Y., Yang, Y., Gan, Z.: Guiding instruction-based image editing via multimodal large language models (2023)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Fujitake, M., Sugimoto, A.: Video representation learning through prediction for online object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 530\u2013539 (2022)","DOI":"10.1109\/WACVW54805.2022.00059"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Ge, S., et al.: Preserve your own correlation: a noise prior for video diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"3_CR16","unstructured":"Girdhar, R., Ramanan, D.: CATER: a diagnostic dataset for compositional actions and temporal reasoning (2020)"},{"issue":"11","key":"3_CR17","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"3_CR18","unstructured":"Gu, Y., et al.: BiomedJourney: counterfactual biomedical image generation by instruction-learning from multimodal patient journeys. arXiv preprint arXiv:2310.10765 (2023)"},{"key":"3_CR19","unstructured":"He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity long video generation (2023)"},{"key":"3_CR20","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control (2022)"},{"key":"3_CR21","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020)"},{"key":"3_CR22","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"3_CR23","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models (2022)"},{"key":"3_CR24","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: CogVideo: large-scale pretraining for text-to-video generation via transformers (2022)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Hu, Y., Luo, C., Chen, Z.: Make it move: controllable image-to-video generation with text descriptions (2022)","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"3_CR29","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2022)"},{"key":"3_CR30","unstructured":"Lee, J., Lee, J., Lee, S., Yoon, S.: Mutual suppression network for video prediction using disentangled features (2019)"},{"key":"3_CR31","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neucom.2022.01.029","volume":"479","author":"H Li","year":"2022","unstructured":"Li, H., et al.: SRDiff: single image super-resolution with diffusion probabilistic models. Neurocomputing 479, 47\u201359 (2022)","journal-title":"Neurocomputing"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: TGIF: a new dataset and benchmark on animated gif description (2016)","DOI":"10.1109\/CVPR.2016.502"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Liu, W., Luo, W., Lian, D., Gao, S.: Future frame prediction for anomaly detection \u2013 a new baseline (2018)","DOI":"10.1109\/CVPR.2018.00684"},{"key":"3_CR35","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver: a fast ODE solver for diffusion probabilistic model sampling in around 10 steps (2022)"},{"key":"3_CR36","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations (2022)"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Ni, B., et al.: Expanding language-image pretrained models for general video recognition (2022)","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Ni, H., Shi, C., Li, K., Huang, S.X., Min, M.R.: Conditional image-to-video generation with latent flow diffusion models (2023)","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"3_CR39","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R., Singh, S.: Action-conditional video prediction using deep networks in Atari games (2015)"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Oliu, M., Selva, J., Escalera, S.: Folded recurrent neural networks for future video prediction (2018)","DOI":"10.1007\/978-3-030-01264-9_44"},{"key":"3_CR41","unstructured":"van\u00a0den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks (2016)"},{"key":"3_CR42","unstructured":"van\u00a0den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., Kavukcuoglu, K.: Conditional image generation with PixelCNN decoders (2016)"},{"key":"3_CR43","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning (2018)"},{"key":"3_CR44","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR46","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 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"3_CR47","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR48","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Kin Wong, W., Chun Woo, W.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting (2015)"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"3_CR50","unstructured":"Singer, U., et al.: Make-a-video: text-to-video generation without text-video data (2022)"},{"key":"3_CR51","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2022)"},{"key":"3_CR52","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A dataset of 101 human actions classes from videos in the wild (2012)"},{"key":"3_CR53","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs (2016)"},{"key":"3_CR54","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: FVD: a new metric for video generation (2019)"},{"key":"3_CR55","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual description (2022)"},{"key":"3_CR56","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction (2018)"},{"key":"3_CR57","unstructured":"Voleti, V., Jolicoeur-Martineau, A., Pal, C.: MCVD: masked conditional video diffusion for prediction, generation, and interpolation (2022)"},{"key":"3_CR58","unstructured":"Wang, C., Gu, J., Hu, P., Xu, S., Xu, H., Liang, X.: DreamVideo: high-fidelity image-to-video generation with image retention and text guidance. arXiv preprint arXiv:2312.03018 (2023)"},{"key":"3_CR59","unstructured":"Wang, Y., et\u00a0al.: LAVIE: high-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103 (2023)"},{"key":"3_CR60","unstructured":"Weissenborn, D., T\u00e4ckstr\u00f6m, O., Uszkoreit, J.: Scaling autoregressive video models (2020)"},{"key":"3_CR61","unstructured":"Wu, C., et al.: GODIVA: generating open-domain videos from natural descriptions (2021)"},{"key":"3_CR62","doi-asserted-by":"crossref","unstructured":"Wu, C., et al.: N\u00fcwa: visual synthesis pre-training for neural visual world creation (2021)","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"3_CR63","doi-asserted-by":"crossref","unstructured":"Xing, J., et al.: DynamicRafter: animating open-domain images with video diffusion priors. arXiv preprint arXiv:2310.12190 (2023)","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"3_CR64","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"3_CR65","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: ReCo: region-controlled text-to-image generation (2022)","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"3_CR66","unstructured":"Yu, J., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789, vol. 2, no. 3, p. 5 (2022)"},{"key":"3_CR67","doi-asserted-by":"crossref","unstructured":"Yu, L., et\u00a0al.: MAGVIT: masked generative video transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10459\u201310469 (2023)","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"3_CR68","unstructured":"Yu, L., et al.: Scaling autoregressive multi-modal models: pretraining and instruction tuning (2023)"},{"key":"3_CR69","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_CR70","unstructured":"Zhang, S., et al.: I2VGen-XL: high-quality image-to-video synthesis via cascaded diffusion models. arXiv preprint arXiv:2311.04145 (2023)"},{"key":"3_CR71","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-net: learning dense volumetric segmentation from sparse annotation (2016)","DOI":"10.1007\/978-3-319-46723-8_49"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73013-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:25:40Z","timestamp":1732609540000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73013-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031730122","9783031730139"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73013-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}