{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:45:39Z","timestamp":1791913539275,"version":"4.3.4"},"reference-count":242,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["CRPO"],"award-info":[{"award-number":["CRPO"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1007\/s11263-026-03040-6","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T21:14:31Z","timestamp":1789766071000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Diffusion Model-Based Video Editing: A Survey"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7351-8967","authenticated-orcid":false,"given":"Wenhao","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9567-159X","authenticated-orcid":false,"given":"Rong-Cheng","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3975-3675","authenticated-orcid":false,"given":"Jingyi","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"3040_CR1","unstructured":"An, J., Zhang, S., Yang, H., Gupta, S., Huang, J., Luo, J., & Yin, X. (2023). Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation. CoRR arXiv:abs\/2304.08477"},{"issue":"4","key":"3040_CR2","doi-asserted-by":"publisher","first-page":"149:1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., & Lischinski, D. (2023). Blended latent diffusion. ACM Trans. Graph., 42(4), 149:1-149:11.","journal-title":"ACM Trans. Graph."},{"key":"3040_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., & Fried, O. (2022). Blended diffusion for text-driven editing of natural images. In: CVPR, pp. 18187\u201318197. IEEE.","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"3040_CR4","unstructured":"Bai, J., He, T., Wang, Y., Guo, J., Hu, H., Liu, Z., & Bian, J. (2024). Uniedit: A unified tuning-free framework for video motion and appearance editing. CoRR arXiv:abs\/2402.13185."},{"key":"3040_CR5","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., & Zisserman, A. (2021). Frozen in time: A joint video and image encoder for end-to-end retrieval. ICCV (pp. 1708\u20131718). IEEE.","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"3040_CR6","unstructured":"Balaji, Y., Nah, S., Huang, X., Vahdat, A., Song, J., Kreis, K., Aittala, M., Aila, T., Laine, S., Catanzaro, B., Karras, T., & Liu, M. (2022). ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers. CoRR arXiv:abs\/2211.01324."},{"key":"3040_CR7","doi-asserted-by":"crossref","unstructured":"Bian, W., Huang, Z., Shi, X., Dong, Y., Li, Y., & Li, H. (2023). Context-pips: Persistent independent particles demands spatial context features. CoRR arXiv:abs\/2306.02000.","DOI":"10.52202\/075280-2413"},{"key":"3040_CR8","unstructured":"Blattmann, A., Dockhorn, T., Kulal, S., Mendelevitch, D., Kilian, M., Lorenz, D., Levi, Y., English, Z., Voleti, V., Letts, A., Jampani, V., & Rombach, R. (2023). Stable video diffusion: Scaling latent video diffusion models to large datasets. CoRR arXiv:abs\/2311.15127."},{"key":"3040_CR9","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S.W., Fidler, S., & Kreis, K. (2023). Align your latents: High-resolution video synthesis with latent diffusion models. In: CVPR, pp. 22563\u201322575. IEEE.","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"3040_CR10","unstructured":"Bolya, D., Fu, C., Dai, X., Zhang, P., Feichtenhofer, C., & Hoffman, J. (2023). Token merging: Your vit but faster (p. ICLR)"},{"key":"3040_CR11","doi-asserted-by":"crossref","unstructured":"Bolya, D., & Hoffman, J. (2023). Token merging for fast stable diffusion. CVPR Workshops (pp. 4599\u20134603). IEEE.","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"3040_CR12","doi-asserted-by":"crossref","unstructured":"Brack, M., Friedrich, F., Kornmeier, K., Tsaban, L., Schramowski, P., Kersting, K., Passos, A.: LEDITS++: limitless image editing using text-to-image models. CoRR arXiv:abs\/2311.16711 (2023)","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"3040_CR13","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., & Efros, A. A. (2023). Instructpix2pix: Learning to follow image editing instructions. In: CVPR, pp. 18392\u201318402. IEEE","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"3040_CR14","doi-asserted-by":"crossref","unstructured":"Butler, D. J., Wulff, J., Stanley, G. B., & Black, M.J. (2012). A naturalistic open source movie for optical flow evaluation. In: ECCV, vol. 7577, pp. 611\u2013625. Springer","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"3040_CR15","unstructured":"Cao, H., Tan, C., Gao, Z., Chen, G., Heng, P., & Li, S. Z. (2022). A survey on generative diffusion model. CoRR arXiv:abs\/2209.02646"},{"key":"3040_CR16","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., & Zheng, Y. (2023). Masactrl: Tuning-free mutual self-attention control for consistent image synthesis and editing. In: ICCV, pp. 22503\u201322513. IEEE","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"3040_CR17","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. ICCV (pp. 9630\u20139640). IEEE.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"3040_CR18","doi-asserted-by":"crossref","unstructured":"Ceylan, D., Huang, C. P., & Mitra, N. J. (2023). Pix2video: Video editing using image diffusion. In: ICCV, pp. 23149\u201323160. IEEE","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"3040_CR19","doi-asserted-by":"crossref","unstructured":"Chai, W., Guo, X., Wang, G., & Lu, Y. (2023). Stablevideo: Text-driven consistency-aware diffusion video editing. In: ICCV, pp. 22983\u201322993. IEEE","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"3040_CR20","unstructured":"Chang, D., Shi, Y., Gao, Q., Fu, J., Xu, H., Song, G., Yan, Q., Zhu, Y., Yang, X., & Soleymani, M. (2024). Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion. CoRR arXiv:abs\/2311.12052"},{"key":"3040_CR21","unstructured":"Chang, S., Chen, H., & Liu, T. (2023). Diffusionatlas: High-fidelity consistent diffusion video editing. CoRR arXiv:abs\/2312.03772"},{"key":"3040_CR22","unstructured":"Chang, Z., Koulieris, G. A., & Shum, H. P. H. (2023). On the design fundamentals of diffusion models: A survey. CoRR arXiv:abs\/2306.04542"},{"key":"3040_CR23","unstructured":"Chen, H., Xia, M., He, Y., Zhang, Y., Cun, X., Yang, S., Xing, J., Liu, Y., Chen, Q., Wang, X., Weng, C., & Shan, Y. (2023). Videocrafter1: Open diffusion models for high-quality video generation. CoRR arXiv:abs\/2310.19512"},{"key":"3040_CR24","doi-asserted-by":"crossref","unstructured":"Chen, H., Zhang, Y., Cun, X., Xia, M., Wang, X., Weng, C., & Shan, Y. (2024). Videocrafter2: Overcoming data limitations for high-quality video diffusion models. CoRR arXiv:abs\/2401.09047","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"3040_CR25","unstructured":"Chen, H., Zhang, Y., Wang, X., Duan, X., Zhou, Y., & Zhu, W. (2023). Disenbooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation. CoRR arXiv:abs\/2305.03374"},{"key":"3040_CR26","unstructured":"Chen, S., Xu, M., Ren, J., Cong, Y., He, S., Xie, Y., Sinha, A., Luo, P., Xiang, T., & P\u00e9rez-R\u00faa, J. (2023). Gentron: Delving deep into diffusion transformers for image and video generation. CoRR arXiv:abs\/2312.04557"},{"key":"3040_CR27","unstructured":"Chen, T., Lin, C. H., Tseng, H., Lin, T., & Yang, M. (2023). Motion-conditioned diffusion model for controllable video synthesis. CoRR arXiv:abs\/2304.14404"},{"key":"3040_CR28","doi-asserted-by":"crossref","unstructured":"Chen, T., Siarohin, A., Menapace, W., Deyneka, E., Chao, H., Jeon, B.E., Fang, Y., Lee, H., Ren, J., Yang, M., & Tulyakov, S. (2024). Panda-70m: Captioning 70m videos with multiple cross-modality teachers. CoRR arXiv:abs\/2402.19479","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"3040_CR29","doi-asserted-by":"crossref","unstructured":"Chen, W., Hu, H., Li, Y., Ruiz, N., Jia, X., Chang, M., & Cohen, W. W. (2023). Subject-driven text-to-image generation via apprenticeship learning. NeurIPS.","DOI":"10.52202\/075280-1318"},{"key":"3040_CR30","unstructured":"Chen, W., Wu, J., Xie, P., Wu, H., Li, J., Xia, X., Xiao, X., & Lin, L. (2023). Control-a-video: Controllable text-to-video generation with diffusion models. CoRR arXiv:abs\/2305.13840"},{"key":"3040_CR31","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., & Zhao, H. (2023). Anydoor: Zero-shot object-level image customization. CoRR arXiv:abs\/2307.09481"},{"key":"3040_CR32","unstructured":"Chen, X., Wang, Y., Zhang, L., Zhuang, S., Ma, X., Yu, J., Wang, Y., Lin, D., Qiao, Y., & Liu, Z. (2023). SEINE: short-to-long video diffusion model for generative transition and prediction. CoRR arXiv:abs\/2310.20700"},{"key":"3040_CR33","doi-asserted-by":"crossref","unstructured":"Chen, Z., Qing, J., & Zhou, J. H. (2023). Cinematic mindscapes: High-quality video reconstruction from brain activity. In: NeurIPS","DOI":"10.52202\/075280-1079"},{"key":"3040_CR34","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., & Girdhar, R. (2022). Masked-attention mask transformer for universal image segmentation. In: CVPR, pp. 1280\u20131289. IEEE","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"3040_CR35","doi-asserted-by":"crossref","unstructured":"Cheng, H. K., & Schwing, A. G. (2022). Xmem: Long-term video object segmentation with an atkinson-shiffrin memory model. In: ECCV, vol. 13688, pp. 640\u2013658. Springer","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"3040_CR36","unstructured":"Cheng, J., Xiao, T., & He, T. (2023). Consistent video-to-video transfer using synthetic dataset. CoRR arXiv:abs\/2311.00213"},{"key":"3040_CR37","unstructured":"Cheng, Y., Li, L., Xu, Y., Li, X., Yang, Z., Wang, W., & Yang, Y. (2023). Segment and track anything. CoRR arXiv:abs\/2305.06558"},{"key":"3040_CR38","unstructured":"Chivileva, I., Lynch, P., Ward, T. E., & Smeaton, A. F. (2023). Measuring the quality of text-to-video model outputs: Metrics and dataset. CoRR arXiv:abs\/2309.08009"},{"key":"3040_CR39","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, T., Jeong, Y., Baek, S., & Choi, J. (2024). Exploiting style latent flows for generalizing deepfake video detection. In: CVPR, pp. 1133\u20131143. IEEE","DOI":"10.1109\/CVPR52733.2024.00114"},{"key":"3040_CR40","unstructured":"Chu, E., Lin, S., & Chen, J. (2023). Video controlnet: Towards temporally consistent synthetic-to-real video translation using conditional image diffusion models. CoRR arXiv:abs\/2305.19193"},{"key":"3040_CR41","unstructured":"Cong, Y., Xu, M., Simon, C., Chen, S., Ren, J., Xie, Y., P\u00e9rez-R\u00faa, J., Rosenhahn, B., Xiang, T., & He, S. (2023). FLATTEN: optical flow-guided attention for consistent text-to-video editing. CoRR arXiv:abs\/2310.05922"},{"key":"3040_CR42","unstructured":"Couairon, P., Rambour, C., Haugeard, J., & Thome, N. (2023). Videdit: Zero-shot and spatially aware text-driven video editing. CoRR arXiv:abs\/2306.08707"},{"key":"3040_CR43","unstructured":"Dai, X., Hou, J., Ma, C., Tsai, S. S., Wang, J., Wang, R., Zhang, P., Vandenhende, S., Wang, X., Dubey, A., Yu, M., Kadian, A., Radenovic, F., Mahajan, D., Li, K., Zhao, Y., Petrovic, V., Singh, M.K., Motwani, S., Wen, Y., Song, Y., Sumbaly, R., Ramanathan, V., He, Z., Vajda, P., & Parikh, D. (2023). Emu: Enhancing image generation models using photogenic needles in a haystack. CoRR arXiv:abs\/2309.15807"},{"key":"3040_CR44","unstructured":"Deng, Y., Wang, R., Zhang, Y., Tai, Y., & Tang, C. (2023). Dragvideo: Interactive drag-style video editing. CoRR arXiv:abs\/2312.02216"},{"key":"3040_CR45","unstructured":"Dhariwal, P., & Nichol, A. Q. (2021). Diffusion models beat gans on image synthesis (pp. 8780\u20138794). NeurIPS."},{"key":"3040_CR46","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale (p. ICLR)"},{"key":"3040_CR47","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., H\u00e4usser, P., Hazirbas, C., Golkov, V., van\u00a0der Smagt, P., Cremers, D., & Brox, T. (2015). Flownet: Learning optical flow with convolutional networks. In: ICCV, pp. 2758\u20132766. IEEE Computer Society","DOI":"10.1109\/ICCV.2015.316"},{"key":"3040_CR48","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., & Germanidis, A. (2023). Structure and content-guided video synthesis with diffusion models. ICCV (pp. 7312\u20137322). IEEE.","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"3040_CR49","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., & Ommer, B. (2021). Taming transformers for high-resolution image synthesis. In: CVPR, pp. 12873\u201312883. IEEE.","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"3040_CR50","unstructured":"Feng, R., Weng, W., Wang, Y., Yuan, Y., Bao, J., Luo, C., Chen, Z., & Guo, B. (2023). Ccedit: Creative and controllable video editing via diffusion models. CoRR arXiv:abs\/2309.16496."},{"key":"3040_CR51","doi-asserted-by":"crossref","unstructured":"Feng, Z., Zhang, Z., Yu, X., Fang, Y., Li, L., Chen, X., Lu, Y., Liu, J., Yin, W., Feng, S., Sun, Y., Chen, L., Tian, H., Wu, H., & Wang, H. (2023). Ernie-vilg 2.0: Improving text-to-image diffusion model with knowledge-enhanced mixture-of-denoising-experts. In: CVPR, pp. 10135\u201310145. IEEE.","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"3040_CR52","doi-asserted-by":"crossref","unstructured":"Fu, J., Li, S., Jiang, Y., Lin, K., Qian, C., Loy, C.C., Wu, W., & Liu, Z. (2022). Stylegan-human: A data-centric odyssey of human generation. In: ECCV, vol. 13676, pp. 1\u201319. Springer.","DOI":"10.1007\/978-3-031-19787-1_1"},{"key":"3040_CR53","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., & Vig, E. (2016). Virtual worlds as proxy for multi-object tracking analysis. CoRR arXiv:abs\/1605.06457.","DOI":"10.1109\/CVPR.2016.470"},{"key":"3040_CR54","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A. H., Chechik, G., & Cohen-Or, D. (2023). An image is worth one word: Personalizing text-to-image generation using textual inversion (p. ICLR)."},{"key":"3040_CR55","unstructured":"Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). A neural algorithm of artistic style. CoRR arXiv:abs\/1508.06576."},{"key":"3040_CR56","doi-asserted-by":"crossref","unstructured":"Ge, S., Nah, S., Liu, G., Poon, T., Tao, A., Catanzaro, B., Jacobs, D., Huang, J., Liu, M., & Balaji, Y. (2023). Preserve your own correlation: A noise prior for video diffusion models. In: ICCV, pp. 22873\u201322884. IEEE.","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"3040_CR57","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, R., Wang, X., Tang, X., & Luo, P. (2019). Deepfashion2: A versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: CVPR, pp. 5337\u20135345. IEEE.","DOI":"10.1109\/CVPR.2019.00548"},{"key":"3040_CR58","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., & Dekel, T. (2023). Tokenflow: Consistent diffusion features for consistent video editing. CoRR arXiv:abs\/2307.10373"},{"key":"3040_CR59","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Singh, M., Brown, A., Duval, Q., Azadi, S., Rambhatla, S. S., Shah, A., Yin, X., Parikh, D., & Misra, I. (2023). Emu video: Factorizing text-to-video generation by explicit image conditioning. CoRR arXiv:abs\/2311.10709.","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"3040_CR60","unstructured":"Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. C., & Bengio, Y. (2014). Generative adversarial nets. NIPS (pp. 2672\u20132680)."},{"key":"3040_CR61","doi-asserted-by":"crossref","unstructured":"Gu, J., Wang, Y., Zhao, N., Fu, T., Xiong, W., Liu, Q., Zhang, Z., Zhang, H., Zhang, J., Jung, H., & Wang, X. E. (2023). PHOTOSWAP: personalized subject swapping in images. In: NeurIPS.","DOI":"10.52202\/075280-1529"},{"key":"3040_CR62","doi-asserted-by":"crossref","unstructured":"Gu, S., Chen, D., Bao, J., Wen, F., Zhang, B., Chen, D., Yuan, L., & Guo, B. (2022). Vector quantized diffusion model for text-to-image synthesis. In: CVPR, pp. 10686\u201310696. IEEE.","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"3040_CR63","unstructured":"Gu, X., Wen, C., Song, J., & Gao, Y. (2023). Seer: Language instructed video prediction with latent diffusion models. CoRR arXiv:abs\/2303.14897."},{"key":"3040_CR64","unstructured":"Gu, Y., Zhou, Y., Wu, B., Yu, L., Liu, J., Zhao, R., Wu, J. Z., Zhang, D. J., Shou, M. Z., & Tang, K. (2023). Videoswap: Customized video subject swapping with interactive semantic point correspondence. CoRR arXiv:abs\/2312.02087."},{"key":"3040_CR65","unstructured":"Guo, Y., Yang, C., Rao, A., Wang, Y., Qiao, Y., Lin, D., & Dai, B. (2023). Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. CoRR arXiv:abs\/2307.04725."},{"key":"3040_CR66","doi-asserted-by":"crossref","unstructured":"Guo, Y., Zhen, C., & Yan, P. (2023). Controllable guide-space for generalizable face forgery detection. In: ICCV, pp. 20761\u201320770. IEEE.","DOI":"10.1109\/ICCV51070.2023.01903"},{"key":"3040_CR67","doi-asserted-by":"crossref","unstructured":"Harley, A. W., Fang, Z., & Fragkiadaki, K. (2022). Particle video revisited: Tracking through occlusions using point trajectories. In: ECCV, vol. 13682, pp. 59\u201375. Springer.","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"3040_CR68","doi-asserted-by":"crossref","unstructured":"Harvey, W., Naderiparizi, S., Masrani, V., Weilbach, C., & Wood, F. (2022). Flexible diffusion modeling of long videos. NeurIPS,","DOI":"10.52202\/068431-2027"},{"key":"3040_CR69","unstructured":"Hendrycks, D., & Gimpel, K. (2016). Gaussian error linear units (gelus). CoRR arXiv:abs\/1606.08415."},{"key":"3040_CR70","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., & Cohen-Or, D. (2023). Prompt-to-prompt image editing with cross-attention control (p. ICLR)"},{"key":"3040_CR71","doi-asserted-by":"crossref","unstructured":"Ho, J., Chan, W., Saharia, C., Whang, J., Gao, R., Gritsenko, A. A., Kingma, D. P., Poole, B., Norouzi, M., Fleet, D. J., & Salimans, T. (2022). Imagen video: High definition video generation with diffusion models. CoRR arXiv:abs\/2210.02303.","DOI":"10.52202\/068431-0628"},{"key":"3040_CR72","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. NeurIPS,"},{"key":"3040_CR73","first-page":"47:1","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D. J., Norouzi, M., & Salimans, T. (2022). Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res., 23, 47:1-47:33.","journal-title":"J. Mach. Learn. Res."},{"key":"3040_CR74","unstructured":"Ho, J., & Salimans, T. (2022). Classifier-free diffusion guidance. CoRR arXiv:abs\/2207.12598."},{"key":"3040_CR75","doi-asserted-by":"crossref","unstructured":"Ho, J., Salimans, T., Gritsenko, A. A., Chan, W., Norouzi, M., & Fleet, D. J. (2022). Video diffusion models. NeurIPS,","DOI":"10.52202\/068431-0628"},{"issue":"1\u20133","key":"3040_CR76","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"BKP Horn","year":"1981","unstructured":"Horn, B. K. P., & Schunck, B. G. (1981). Determining optical flow. Artif. Intell., 17(1\u20133), 185\u2013203.","journal-title":"Artif. Intell."},{"key":"3040_CR77","unstructured":"Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). Lora: Low-rank adaptation of large language models. In: ICLR."},{"key":"3040_CR78","unstructured":"Hu, L., Gao, X., Zhang, P., Sun, K., Zhang, B., & Bo, L. (2023). Animate anyone: Consistent and controllable image-to-video synthesis for character animation. CoRR arXiv:abs\/2311.17117."},{"key":"3040_CR79","unstructured":"Hu, Z., & Xu, D. (2023). Videocontrolnet: A motion-guided video-to-video translation framework by using diffusion model with controlnet. CoRR arXiv:abs\/2307.14073."},{"key":"3040_CR80","doi-asserted-by":"crossref","unstructured":"Huang, X., & Belongie, S. J. (2017). Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV, pp. 1510\u20131519. IEEE Computer Society","DOI":"10.1109\/ICCV.2017.167"},{"key":"3040_CR81","unstructured":"Huang, Y., Huang, J., Liu, Y., Yan, M., Lv, J., Liu, J., Xiong, W., Zhang, H., Chen, S., & Cao, L. (2024). Diffusion model-based image editing: A survey. CoRR arXiv:abs\/2402.17525."},{"key":"3040_CR82","doi-asserted-by":"crossref","unstructured":"Huang, Z., He, Y., Yu, J., Zhang, F., Si, C., Jiang, Y., Zhang, Y., Wu, T., Jin, Q., Chanpaisit, N., Wang, Y., Chen, X., Wang, L., Lin, D., Qiao, Y., & Liu, Z. (2023). Vbench: Comprehensive benchmark suite for video generative models. CoRR arXiv:abs\/2311.17982.","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"3040_CR83","first-page":"695","volume":"6","author":"A Hyv\u00e4rinen","year":"2005","unstructured":"Hyv\u00e4rinen, A. (2005). Estimation of non-normalized statistical models by score matching. JMLR, 6, 695\u2013709.","journal-title":"JMLR"},{"key":"3040_CR84","doi-asserted-by":"crossref","unstructured":"Jafarian, Y., & Park, H. S. (2021). Learning high fidelity depths of dressed humans by watching social media dance videos. In: CVPR, pp. 12753\u201312762. IEEE.","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"3040_CR85","doi-asserted-by":"crossref","unstructured":"Jeong, H., Park, G. Y., & Ye, J. C. (2023). VMC: video motion customization using temporal attention adaption for text-to-video diffusion models. CoRR arXiv:abs\/2312.00845.","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"3040_CR86","unstructured":"Jeong, H., & Ye, J. C. (2023). Ground-a-video: Zero-shot grounded video editing using text-to-image diffusion models. CoRR arXiv:abs\/2310.01107."},{"key":"3040_CR87","doi-asserted-by":"crossref","unstructured":"Jeong, Y., Kim, D., Ro, Y., & Choi, J. (2022). Frepgan: Robust deepfake detection using frequency-level perturbations. In: AAAI, pp. 1060\u20131068. AAAI Press","DOI":"10.1609\/aaai.v36i1.19990"},{"key":"3040_CR88","doi-asserted-by":"crossref","unstructured":"Jeong, Y., Ryoo, W., Lee, S., Seo, D., Byeon, W., Kim, S., & Kim, J. (2023). The power of sound (tpos): Audio reactive video generation with stable diffusion. In: ICCV, pp. 7788\u20137798. IEEE.","DOI":"10.1109\/ICCV51070.2023.00719"},{"key":"3040_CR89","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Han, Z., Mao, C., Zhang, J., Pan, Y., & Liu, Y. (2025). VACE: all-in-one video creation and editing. CoRR arXiv:abs\/2503.07598.","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"3040_CR90","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Mao, C., Huang, Z., Ma, A., Lv, Y., Shen, Y., Zhao, D., & Zhou, J. (2023). Res-tuning: A flexible and efficient tuning paradigm via unbinding tuner from backbone. NeurIPS.","DOI":"10.52202\/075280-1850"},{"key":"3040_CR91","doi-asserted-by":"crossref","unstructured":"Kara, O., Kurtkaya, B., Yesiltepe, H., Rehg, J. M., & Yanardag, P. (2023). RAVE: randomized noise shuffling for fast and consistent video editing with diffusion models. CoRR arXiv:abs\/2312.04524.","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"3040_CR92","doi-asserted-by":"crossref","unstructured":"Karras, J., Holynski, A., Wang, T., & Kemelmacher-Shlizerman, I. (2023). Dreampose: Fashion image-to-video synthesis via stable diffusion. ICCV (pp. 22623\u201322633). IEEE.","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"3040_CR93","doi-asserted-by":"crossref","unstructured":"Karras, T., Aittala, M., Aila, T., & Laine, S. (2022). Elucidating the design space of diffusion-based generative models. NeurIPS,","DOI":"10.52202\/068431-1926"},{"key":"3040_CR94","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020). Analyzing and improving the image quality of stylegan. In: CVPR, pp. 8107\u20138116. IEEE.","DOI":"10.1109\/CVPR42600.2020.00813"},{"issue":"6","key":"3040_CR95","doi-asserted-by":"publisher","first-page":"210:1","DOI":"10.1145\/3478513.3480546","volume":"40","author":"Y Kasten","year":"2021","unstructured":"Kasten, Y., Ofri, D., Wang, O., & Dekel, T. (2021). Layered neural atlases for consistent video editing. ACM Trans. Graph., 40(6), 210:1-210:12.","journal-title":"ACM Trans. Graph."},{"key":"3040_CR96","doi-asserted-by":"crossref","unstructured":"Kawar, B., Zada, S., Lang, O., Tov, O., Chang, H., Dekel, T., Mosseri, I., & Irani, M. (2023). Imagic: Text-based real image editing with diffusion models. In: CVPR, pp. 6007\u20136017. IEEE.","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"3040_CR97","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., Movsisyan, A., Tadevosyan, V., Henschel, R., Wang, Z., Navasardyan, S., & Shi, H. (2023). Text2video-zero: Text-to-image diffusion models are zero-shot video generators. ICCV (pp. 15908\u201315918). IEEE.","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"3040_CR98","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., & Ye, J. C. (2022). Diffusionclip: Text-guided diffusion models for robust image manipulation. In: CVPR, pp. 2416\u20132425. IEEE.","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"3040_CR99","unstructured":"Kingma, D. P., & Welling, M. (2014). Auto-encoding variational bayes (p. ICLR)"},{"key":"3040_CR100","doi-asserted-by":"crossref","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., & Levy, O. (2023). Pick-a-pic: An open dataset of user preferences for text-to-image generation. NeurIPS.","DOI":"10.52202\/075280-1594"},{"key":"3040_CR101","unstructured":"Korshunov, P., & Marcel, S. (2018). Deepfakes: a new threat to face recognition? assessment and detection. CoRR arXiv:abs\/1812.08685."},{"key":"3040_CR102","doi-asserted-by":"crossref","unstructured":"Kou, T., Liu, X., Zhang, Z., Li, C., Wu, H., Min, X., Zhai, G., & Liu, N. (2024). Subjective-aligned dataset and metric for text-to-video quality assessment. CoRR arXiv:abs\/2403.11956.","DOI":"10.1145\/3664647.3680868"},{"key":"3040_CR103","unstructured":"Ku, M., Wei, C., Ren, W., Yang, H., & Chen, W. (2024). Anyv2v: A plug-and-play framework for any video-to-video editing tasks. CoRR arXiv:abs\/2403.14468."},{"key":"3040_CR104","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., & Zhu, J. (2023). Multi-concept customization of text-to-image diffusion. In: CVPR, pp. 1931\u20131941. IEEE.","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"3040_CR105","doi-asserted-by":"crossref","unstructured":"Lai, W., Huang, J., Wang, O., Shechtman, E., Yumer, E., & Yang, M. (2018). Learning blind video temporal consistency. In: ECCV, vol. 11219, pp. 179\u2013195. Springer.","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"3040_CR106","unstructured":"Lee, S., Kong, C., Jeon, D., & Kwak, N. (2023). Aadiff: Audio-aligned video synthesis with text-to-image diffusion. CoRR arXiv:abs\/2305.04001."},{"key":"3040_CR107","doi-asserted-by":"crossref","unstructured":"Lee, Y., Jang, J.G., Chen, Y., Qiu, E., & Huang, J. (2023). Shape-aware text-driven layered video editing. In: CVPR, pp. 14317\u201314326. IEEE.","DOI":"10.1109\/CVPR52729.2023.01376"},{"key":"3040_CR108","unstructured":"Lefaudeux, B., Massa, F., Liskovich, D., Xiong, W., Caggiano, V., Naren, S., Xu, M., Hu, J., Tintore, M., Zhang, S., Labatut, P., Haziza, D., Wehrstedt, L., Reizenstein, J., & Sizov, G. (2022). xFormers: A modular and hackable transformer modelling library. https:\/\/github.com\/facebookresearch\/xformers."},{"key":"3040_CR109","unstructured":"Li, J., Li, D., Xiong, C., & Hoi, S. C. H. (2022). BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, vol. 162, pp. 12888\u201312900. PMLR."},{"key":"3040_CR110","doi-asserted-by":"crossref","unstructured":"Li, L.H., Zhang, P., Zhang, H., Yang, J., Li, C., Zhong, Y., Wang, L., Yuan, L., Zhang, L., Hwang, J., Chang, K., & Gao, J. (2022). Grounded language-image pre-training. In: CVPR, pp. 10955\u201310965. IEEE.","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"3040_CR111","unstructured":"Li, W., Xu, X., Xiao, X., Liu, J., Yang, H., Li, G., Wang, Z., Feng, Z., She, Q., Lyu, Y., & Wu, H. (2022). Upainting: Unified text-to-image diffusion generation with cross-modal guidance. CoRR arXiv:abs\/2210.16031."},{"key":"3040_CR112","doi-asserted-by":"crossref","unstructured":"Li, X., Ma, C., Yang, X., & Yang, M. (2023). Vidtome: Video token merging for zero-shot video editing. CoRR arXiv:abs\/2312.10656.","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"3040_CR113","unstructured":"Li, Z., Tucker, R., Snavely, N., & Holynski, A. (2023). Generative image dynamics. CoRR arXiv:abs\/2309.07906."},{"key":"3040_CR114","doi-asserted-by":"crossref","unstructured":"Liang, F., Wu, B., Wang, J., Yu, L., Li, K., Zhao, Y., Misra, I., Huang, J., Zhang, P., Vajda, P., & Marculescu, D. (2023). Flowvid: Taming imperfect optical flows for consistent video-to-video synthesis. CoRR arXiv:abs\/2312.17681.","DOI":"10.1109\/CVPR52733.2024.00784"},{"key":"3040_CR115","doi-asserted-by":"crossref","unstructured":"Liao, M., Lu, H., Zhang, X., Wan, F., Wang, T., Zhao, Y., Zuo, W., Ye, Q., & Wang, J. (2024). Evaluation of text-to-video generation models: A dynamics perspective. CoRR arXiv:abs\/2407.01094.","DOI":"10.52202\/079017-3483"},{"key":"3040_CR116","unstructured":"Liew, J.H., Yan, H., Zhang, J., Xu, Z., & Feng, J. (2023). Magicedit: High-fidelity and temporally coherent video editing. CoRR arXiv:abs\/2308.14749."},{"key":"3040_CR117","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., & Han, S. (2019). TSM: temporal shift module for efficient video understanding. In: ICCV, pp. 7082\u20137092. IEEE.","DOI":"10.1109\/ICCV.2019.00718"},{"key":"3040_CR118","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S. J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft COCO: common objects in context. In: ECCV (Vol. 8693, pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3040_CR119","doi-asserted-by":"crossref","unstructured":"Ling, P., Chen, L., Zhang, P., Chen, H., Jin, Y., & Zheng, J. (2024). Freedrag: Feature dragging for reliable point-based image editing. In: CVPR, pp. 6860\u20136870. IEEE.","DOI":"10.1109\/CVPR52733.2024.00655"},{"key":"3040_CR120","unstructured":"Liu, J., Huang, X., Huang, T., Chen, L., Hou, Y., Tang, S., Liu, Z., Ouyang, W., Zuo, W., Jiang, J., & Liu, X. (2024). A comprehensive survey on 3d content generation. CoRR arXiv:abs\/2402.01166"},{"key":"3040_CR121","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, Y., Li, W., Lin, Z., & Jia, J. (2023). Video-p2p: Video editing with cross-attention control.","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"3040_CR122","unstructured":"Liu, V., Long, T., Raw, N., & Chilton, L. B. (2023). Generative disco: Text-to-video generation for music visualization. CoRR arXiv:abs\/2304.08551."},{"key":"3040_CR123","doi-asserted-by":"crossref","unstructured":"Liu, W., She, T., Liu, J., Li, B., Yao, D., Liang, Z., & Wang, R. (2024). Lips are lying: Spotting the temporal inconsistency between audio and visual in lip-syncing deepfakes. In: NeurIPS.","DOI":"10.52202\/079017-2892"},{"key":"3040_CR124","unstructured":"Liu, Y., Cun, X., Liu, X., Wang, X., Zhang, Y., Chen, H., Liu, Y., Zeng, T., Chan, R. H., & Shan, Y. (2023). Evalcrafter: Benchmarking and evaluating large video generation models. CoRR arXiv:abs\/2310.11440."},{"key":"3040_CR125","unstructured":"Luma: Luma. https:\/\/lumalabs.ai\/dream-machineg (2024)"},{"key":"3040_CR126","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., & Zhao, H. (2023). Latent consistency models: Synthesizing high-resolution images with few-step inference. CoRR arXiv:abs\/2310.04378."},{"key":"3040_CR127","doi-asserted-by":"crossref","unstructured":"Ma, H., Mahdizadehaghdam, S., Wu, B., Fan, Z., Gu, Y., Zhao, W., Shapira, L., & Xie, X. (2023). Maskint: Video editing via interpolative non-autoregressive masked transformers. CoRR arXiv:abs\/2312.12468.","DOI":"10.1109\/CVPR52733.2024.00707"},{"key":"3040_CR128","unstructured":"Ma, X., Wang, Y., Jia, G., Chen, X., Liu, Z., Li, Y., Chen, C., & Qiao, Y. (2024). Latte: Latent diffusion transformer for video generation. CoRR arXiv:abs\/2401.03048."},{"key":"3040_CR129","doi-asserted-by":"crossref","unstructured":"Ma, Y., He, Y., Cun, X., Wang, X., Chen, S., Li, X., & Chen, Q. (2024). Follow your pose: Pose-guided text-to-video generation using pose-free videos. In: AAAI, pp. 4117\u20134125. AAAI Press.","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"3040_CR130","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., H\u00e4usser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016) A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: CVPR, pp. 4040\u20134048. IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.438"},{"key":"3040_CR131","unstructured":"Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J., & Ermon, S. (2022). Sdedit: Guided image synthesis and editing with stochastic differential equations. In: ICLR. OpenReview.net."},{"key":"3040_CR132","doi-asserted-by":"crossref","unstructured":"Meng, C., Rombach, R., Gao, R., Kingma, D.P., Ermon, S., Ho, J., & Salimans, T. (2023). On distillation of guided diffusion models. In: CVPR, pp. 14297\u201314306. IEEE.","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"3040_CR133","unstructured":"Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018). Spectral normalization for generative adversarial networks (p. ICLR)"},{"key":"3040_CR134","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., & Cohen-Or, D. (2023). Null-text inversion for editing real images using guided diffusion models. In: CVPR, pp. 6038\u20136047..IEEE","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"3040_CR135","unstructured":"Molad, E., Horwitz, E., Valevski, D., Rav-Acha, A., Matias, Y., Pritch, Y., Leviathan, Y., & Hoshen, Y. (2023). Dreamix: Video diffusion models are general video editors. CoRR arXiv:abs\/2302.01329."},{"key":"3040_CR136","unstructured":"Mou, C., Wang, X., Song, J., Shan, Y., & Zhang, J. (2023). Dragondiffusion: Enabling drag-style manipulation on diffusion models. CoRR arXiv:abs\/2307.02421."},{"key":"3040_CR137","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Wu, Y., Zhang, J., Qi, Z., & Shan, Y. (2024). T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. In: AAAI, pp. 4296\u20134304. AAAI Press.","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"3040_CR138","unstructured":"Nichol, A. Q., & Dhariwal, P. (2021). Improved denoising diffusion probabilistic models. ICML (Vol. 139, pp. 8162\u20138171) PMLR."},{"key":"3040_CR139","unstructured":"Nichol, A.Q., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2022). GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML, vol. 162, pp. 16784\u201316804. PMLR."},{"key":"3040_CR140","unstructured":"van\u00a0den Oord, A., Vinyals, O., & Kavukcuoglu, K. (2017). Neural discrete representation learning. In: NIPS, pp. 6306\u20136315."},{"key":"3040_CR141","unstructured":"OpenAI: ChatGPT. https:\/\/openai.com\/chatgpt\/ (2022)"},{"key":"3040_CR142","unstructured":"OpenAI: GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/ (2024)"},{"key":"3040_CR143","unstructured":"OpenAI: Sora. https:\/\/openai.com\/index\/video-generation-models-as-world-simulators\/ (2024)"},{"key":"3040_CR144","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., Assran, M., Ballas, N., Galuba, W., Howes, R., Huang, P., Li, S., Misra, I., Rabbat, M.G., Sharma, V., Synnaeve, G., Xu, H., J\u00e9gou, H., Mairal, J., Labatut, P., Joulin, A., & Bojanowski, P. (2023). Dinov2: Learning robust visual features without supervision. CoRR arXiv:abs\/2304.07193."},{"key":"3040_CR145","unstructured":"Ouyang, H., Wang, Q., Xiao, Y., Bai, Q., Zhang, J., Zheng, K., Zhou, X., Chen, Q., & Shen, Y. (2023). Codef: Content deformation fields for temporally consistent video processing. CoRR arXiv:abs\/2308.07926."},{"key":"3040_CR146","doi-asserted-by":"crossref","unstructured":"Pan, X., Tewari, A., Leimk\u00fchler, T., Liu, L., Meka, A., & Theobalt, C. (2023). Drag your GAN: interactive point-based manipulation on the generative image manifold. In: SIGGRAPH, pp. 78:1\u201378:11. ACM.","DOI":"10.1145\/3588432.3591500"},{"key":"3040_CR147","doi-asserted-by":"crossref","unstructured":"Peebles, W., & Xie, S. (2023). Scalable diffusion models with transformers. ICCV (pp. 4172\u20134182). IEEE.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"3040_CR148","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de\u00a0Vries, H., Dumoulin, V., & Courville, A. C. (2018). Film: Visual reasoning with a general conditioning layer. In: AAAI, pp. 3942\u20133951. AAAI Press.","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"3040_CR149","unstructured":"Pika: Pika. https:\/\/pika.art\/home (2024)"},{"key":"3040_CR150","doi-asserted-by":"crossref","unstructured":"Po, R., Yifan, W., Golyanik, V., Aberman, K., Barron, J. T., Bermano, A. H., Chan, E. R., Dekel, T., Holynski, A., Kanazawa, A., Liu, C.K., Liu, L., Mildenhall, B., Nie\u00dfner, M., Ommer, B., Theobalt, C., Wonka, P., & Wetzstein, G. (2023). State of the art on diffusion models for visual computing. CoRR arXiv:abs\/2310.07204.","DOI":"10.1111\/cgf.15063"},{"key":"3040_CR151","unstructured":"Poole, B., Jain, A., Barron, J. T., & Mildenhall, B. (2023). Dreamfusion: Text-to-3d using 2d diffusion (p. ICLR)"},{"key":"3040_CR152","doi-asserted-by":"crossref","unstructured":"Qi, C., Cun, X., Zhang, Y., Lei, C., Wang, X., Shan, Y., & Chen, Q. (2023). Fatezero: Fusing attentions for zero-shot text-based video editing. ICCV (pp. 15886\u201315896). IEEE.","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"3040_CR153","doi-asserted-by":"crossref","unstructured":"Qin, B., Li, J., Tang, S., Chua, T., & Zhuang, Y. (2023). Instructvid2vid: Controllable video editing with natural language instructions. CoRR arXiv:abs\/2305.12328.","DOI":"10.1109\/ICME57554.2024.10687529"},{"key":"3040_CR154","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In: ICML, 139, 8748\u20138763. PMLR."},{"key":"3040_CR155","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with CLIP latents. CoRR arXiv:abs\/2204.06125."},{"issue":"3","key":"3040_CR156","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2022","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., & Koltun, V. (2022). Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell., 44(3), 1623\u20131637.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3040_CR157","unstructured":"Ren, T., Liu, S., Zeng, A., Lin, J., Li, K., Cao, H., Chen, J., Huang, X., Chen, Y., Yan, F., Zeng, Z., Zhang, H., Li, F., Yang, J., Li, H., Jiang, Q., & Zhang, L. (2024). Grounded SAM: assembling open-world models for diverse visual tasks. CoRR arXiv:abs\/2401.14159."},{"key":"3040_CR158","unstructured":"Ren, W., Yang, H., Zhang, G., Wei, C., Du, X., Huang, S., & Chen, W. (2024). Consisti2v: Enhancing visual consistency for image-to-video generation. CoRR arXiv:abs\/2402.04324."},{"key":"3040_CR159","unstructured":"Rezende, D. J., & Mohamed, S. (2015). Variational inference with normalizing flows. In: ICML, vol.\u00a037, pp. 1530\u20131538. JMLR.org."},{"key":"3040_CR160","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10674\u201310685. IEEE.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3040_CR161","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023). Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR, pp. 22500\u201322510. IEEE.","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"3040_CR162","unstructured":"Runway: Gen-3. https:\/\/runwayml.com\/research\/introducing-gen-3-alpha (2024)"},{"key":"3040_CR163","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C. A., Ho, J., Salimans, T., Fleet, D. J., & Norouzi, M. (2022). Palette: Image-to-image diffusion models. In: SIGGRAPH, pp. 15:1\u201315:10. ACM.","DOI":"10.1145\/3528233.3530757"},{"key":"3040_CR164","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, S. K. S., Lopes, R. G., Ayan, B. K., Salimans, T., Ho, J., Fleet, D. J., & Norouzi, M. (2022). Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS.","DOI":"10.52202\/068431-2643"},{"key":"3040_CR165","doi-asserted-by":"crossref","unstructured":"Sand, P., & Teller, S. J. (2006). Particle video: Long-range motion estimation using point trajectories. In: CVPR (2), pp. 2195\u20132202. IEEE Computer Society.","DOI":"10.1109\/CVPR.2006.219"},{"key":"3040_CR166","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., & Rombach, R. (2023). Adversarial diffusion distillation. CoRR arXiv:abs\/2311.17042."},{"key":"3040_CR167","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., & Rombach, R. (2023). Adversarial diffusion distillation. CoRR arXiv:abs\/2311.17042."},{"key":"3040_CR168","unstructured":"Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., & Komatsuzaki, A. (2021). LAION-400M: open dataset of clip-filtered 400 million image-text pairs. CoRR arXiv:abs\/2111.02114."},{"key":"3040_CR169","doi-asserted-by":"crossref","unstructured":"Sheynin, S., Polyak, A., Singer, U., Kirstain, Y., Zohar, A., Ashual, O., Parikh, D., & Taigman, Y. (2023). Emu edit: Precise image editing via recognition and generation tasks. CoRR arXiv:abs\/2311.10089.","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"3040_CR170","unstructured":"Shi, J., Xiong, W., Lin, Z., & Jung, H. J. (2023). Instantbooth: Personalized text-to-image generation without test-time finetuning. CoRR arXiv:abs\/2304.03411."},{"key":"3040_CR171","unstructured":"Shi, Y., Xue, C., Pan, J., Zhang, W., Tan, V. Y. F., & Bai, S. (2023). Dragdiffusion: Harnessing diffusion models for interactive point-based image editing. CoRR arXiv:abs\/2306.14435."},{"key":"3040_CR172","unstructured":"Shin, C., Kim, H., Lee, C.H., Lee, S., & Yoon, S. (2023). Edit-a-video: Single video editing with object-aware consistency. In: ACML, vol. 222, pp. 1215\u20131230. PMLR."},{"key":"3040_CR173","doi-asserted-by":"crossref","unstructured":"Singer, U., Zohar, A., Kirstain, Y., Sheynin, S., Polyak, A., Parikh, D., & Taigman, Y. (2024). Video editing via factorized diffusion distillation. CoRR arXiv:abs\/2403.09334.","DOI":"10.1007\/978-3-031-73116-7_26"},{"key":"3040_CR174","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Tulyakov, S., & Elhoseiny, M. (2022). Stylegan-v: A continuous video generator with the price, image quality and perks of stylegan2. In: CVPR, pp. 3616\u20133626. IEEE.","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"3040_CR175","unstructured":"Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML, vol.\u00a037, pp. 2256\u20132265. JMLR.org."},{"key":"3040_CR176","unstructured":"Song, J., Meng, C., & Ermon, S. (2021). Denoising diffusion implicit models (p. ICLR)"},{"key":"3040_CR177","unstructured":"Song, Y., Dhariwal, P., Chen, M., & Sutskever, I. (2023). Consistency models. In: ICML (Vol. 202, pp. 32211\u201332252) PMLR."},{"key":"3040_CR178","unstructured":"Song, Y., & Ermon, S. (2019). Generative modeling by estimating gradients of the data distribution (pp. 11895\u201311907). NeurIPS."},{"key":"3040_CR179","unstructured":"Song, Y., Shin, W., Lee, J., Kim, J., & Kwak, N. (2023). SAVE: protagonist diversification with structure agnostic video editing. CoRR arXiv:abs\/2312.02503."},{"key":"3040_CR180","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2021). Score-based generative modeling through stochastic differential equations (p. ICLR)"},{"key":"3040_CR181","doi-asserted-by":"crossref","unstructured":"Su, Z., Liu, W., Yu, Z., Hu, D., Liao, Q., Tian, Q., Pietik\u00e4inen, M., & Liu, L. (2021). Pixel difference networks for efficient edge detection. In: ICCV, pp. 5097\u20135107. IEEE.","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"3040_CR182","doi-asserted-by":"crossref","unstructured":"Sun, K., Huang, K., Liu, X., Wu, Y., Xu, Z., Li, Z., & Liu, X. (2024). T2v-compbench: A comprehensive benchmark for compositional text-to-video generation. CoRR arXiv:abs\/2407.14505.","DOI":"10.1109\/CVPR52734.2025.00787"},{"key":"3040_CR183","doi-asserted-by":"crossref","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C. P., & Hariharan, B. (2023). Emergent correspondence from image diffusion. NeurIPS,","DOI":"10.52202\/075280-0068"},{"key":"3040_CR184","doi-asserted-by":"crossref","unstructured":"Tang, Z., Yang, Z., Zhu, C., Zeng, M., & Bansal, M. (2023). Any-to-any generation via composable diffusion. NeurIPS,","DOI":"10.52202\/075280-0707"},{"key":"3040_CR185","doi-asserted-by":"crossref","unstructured":"Teed, Z., & Deng, J. (2020). RAFT: recurrent all-pairs field transforms for optical flow. In: ECCV, vol. 12347, pp. 402\u2013419. Springer.","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"3040_CR186","unstructured":"Teng, Y., Xie, E., Wu, Y., Han, H., Li, Z., & Liu, X. (2023). Drag-a-video: Non-rigid video editing with point-based interaction. CoRR arXiv:abs\/2312.02936."},{"key":"3040_CR187","doi-asserted-by":"crossref","unstructured":"Truong, P., Danelljan, M., Yu, F., & Gool, L. V. (2022). Probabilistic warp consistency for weakly-supervised semantic correspondences. In: CVPR, pp. 8698\u20138708. IEEE.","DOI":"10.1109\/CVPR52688.2022.00851"},{"key":"3040_CR188","unstructured":"Tu, S., Dai, Q., Cheng, Z., Hu, H., Han, X., Wu, Z., & Jiang, Y. (2023). Motioneditor: Editing video motion via content-aware diffusion. CoRR arXiv:abs\/2311.18830."},{"key":"3040_CR189","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., & Dekel, T. (2023). Plug-and-play diffusion features for text-driven image-to-image translation. In: CVPR, pp. 1921\u20131930. IEEE.","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"3040_CR190","unstructured":"Ulhaq, A., Akhtar, N., & Pogrebna, G. (2022). Efficient diffusion models for vision: A survey. CoRR arXiv:abs\/2210.09292."},{"key":"3040_CR191","unstructured":"Ulyanov, D., Vedaldi, A., & Lempitsky, V. S. (2016) Instance normalization: The missing ingredient for fast stylization. CoRR arXiv:abs\/1607.08022."},{"issue":"3","key":"3040_CR192","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/MMUL.2022.3175654","volume":"29","author":"VKM Vadakital","year":"2022","unstructured":"Vadakital, V. K. M., Dziembowski, A., Lafruit, G., Thudor, F., Lee, G., & Rondao-Alface, P. (2022). The MPEG immersive video standard - current status and future outlook. IEEE Multim., 29(3), 101\u2013111.","journal-title":"IEEE Multim."},{"key":"3040_CR193","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. NIPS (pp. 5998\u20136008)"},{"key":"3040_CR194","doi-asserted-by":"crossref","unstructured":"Voleti, V., Jolicoeur-Martineau, A., & Pal, C. (2022). MCVD - masked conditional video diffusion for prediction, generation, and interpolation. NeurIPS,","DOI":"10.52202\/068431-1698"},{"key":"3040_CR195","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., & Zhang, S. (2023). Modelscope text-to-video technical report. CoRR arXiv:abs\/2308.06571."},{"key":"3040_CR196","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., & Zhang, S. (2023). Modelscope text-to-video technical report. CoRR arXiv:abs\/2308.06571."},{"key":"3040_CR197","unstructured":"Wang, Q., Bai, X., Wang, H., Qin, Z., & Chen, A. (2024). Instantid: Zero-shot identity-preserving generation in seconds. CoRR arXiv:abs\/2401.07519."},{"key":"3040_CR198","unstructured":"Wang, T., Li, L., Lin, K., Zhai, Y., Lin, C. C., Yang, Z., Zhang, H., Liu, Z., & Wang, L. (2023). Disco: Disentangled control for realistic human dance generation. CoRR arXiv:abs\/2307.00040."},{"issue":"6","key":"3040_CR199","doi-asserted-by":"publisher","first-page":"3239","DOI":"10.1109\/TPAMI.2021.3051099","volume":"44","author":"W Wang","year":"2022","unstructured":"Wang, W., Lai, Q., Fu, H., Shen, J., Ling, H., & Yang, R. (2022). Salient object detection in the deep learning era: An in-depth survey. IEEE Trans. Pattern Anal. Mach. Intell., 44(6), 3239\u20133259.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3040_CR200","unstructured":"Wang, W., Xie, K., Liu, Z., Chen, H., Cao, Y., Wang, X., & Shen, C. (2023). Zero-shot video editing using off-the-shelf image diffusion models. CoRR arXiv:abs\/2303.17599."},{"key":"3040_CR201","doi-asserted-by":"crossref","unstructured":"Wang, W., & Yang, Y. (2024). Vidprom: A million-scale real prompt-gallery dataset for text-to-video diffusion models. CoRR arXiv:abs\/2403.06098.","DOI":"10.52202\/079017-2096"},{"key":"3040_CR202","doi-asserted-by":"crossref","unstructured":"Wang, X., Yuan, H., Zhang, S., Chen, D., Wang, J., Zhang, Y., Shen, Y., Zhao, D., & Zhou, J. (2023). Videocomposer: Compositional video synthesis with motion controllability. In: NeurIPS.","DOI":"10.52202\/075280-0334"},{"key":"3040_CR203","unstructured":"Wang, Y., Chen, X., Ma, X., Zhou, S., Huang, Z., Wang, Y., Yang, C., He, Y., Yu, J., Yang, P., Guo, Y., Wu, T., Si, C., Jiang, Y., Chen, C., Loy, C. C., Dai, B., Lin, D., Qiao, Y., & Liu, Z. (2023). LAVIE: high-quality video generation with cascaded latent diffusion models. CoRR arXiv:abs\/2309.15103."},{"key":"3040_CR204","unstructured":"Wang, Y., He, Y., Li, Y., Li, K., Yu, J., Ma, X., Chen, X., Wang, Y., Luo, P., Liu, Z., Wang, Y., Wang, L., & Qiao, Y. (2023). Internvid: A large-scale video-text dataset for multimodal understanding and generation. CoRR arXiv:abs\/2307.06942."},{"key":"3040_CR205","unstructured":"Watson, D., Chan, W., Ho, J., & Norouzi, M. (2022). Learning fast samplers for diffusion models by differentiating through sample quality (p. ICLR)"},{"key":"3040_CR206","unstructured":"Watson, D., Ho, J., Norouzi, M., & Chan, W. (2021). Learning to efficiently sample from diffusion probabilistic models. CoRR arXiv:abs\/2106.03802."},{"key":"3040_CR207","doi-asserted-by":"crossref","unstructured":"Wu, B., Chuang, C., Wang, X., Jia, Y., Krishnakumar, K., Xiao, T., Liang, F., Yu, L., & Vajda, P. (2023). Fairy: Fast parallelized instruction-guided video-to-video synthesis. CoRR arXiv:abs\/2312.13834.","DOI":"10.1109\/CVPR52733.2024.00789"},{"key":"3040_CR208","unstructured":"Wu, C., Huang, L., Zhang, Q., Li, B., Ji, L., Yang, F., Sapiro, G., & Duan, N. (2021). GODIVA: generating open-domain videos from natural descriptions. CoRR arXiv:abs\/2104.14806."},{"key":"3040_CR209","doi-asserted-by":"crossref","unstructured":"Wu, H., Zhang, E., Liao, L., Chen, C., Hou, J., Wang, A., Sun, W., Yan, Q., & Lin, W. (2023). Exploring video quality assessment on user generated contents from aesthetic and technical perspectives. In: ICCV, pp. 20087\u201320097. IEEE.","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"3040_CR210","unstructured":"Wu, J.Z., Fang, G., Wu, H., Wang, X., Ge, Y., Cun, X., Zhang, D.J., Liu, J., Gu, Y., Zhao, R., Lin, W., Hsu, W., Shan, Y., & Shou, M. Z. (2024). Towards A better metric for text-to-video generation. CoRR arXiv:abs\/2401.07781."},{"key":"3040_CR211","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. (2023). Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In: ICCV, pp. 7589\u20137599. IEEE.","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"3040_CR212","unstructured":"Wu, J. Z., Li, X., Gao, D., Dong, Z., Bai, J., Singh, A., Xiang, X., Li, Y., Huang, Z., Sun, Y., He, R., Hu, F., Hu, J., Huang, H., Zhu, H., Cheng, X., Tang, J., Shou, M. Z., Keutzer, K., & Iandola, F. N. (2023). CVPR 2023 text guided video editing competition. CoRR arXiv:abs\/2310.16003."},{"key":"3040_CR213","unstructured":"Wu, R., Chen, L., Yang, T., Guo, C., Li, C., & Zhang, X. (2023). LAMP: learn A motion pattern for few-shot-based video generation. CoRR arXiv:abs\/2310.10769."},{"key":"3040_CR214","unstructured":"Wu, S., Fei, H., Qu, L., Ji, W., & Chua, T. (2023). Next-gpt: Any-to-any multimodal LLM. CoRR arXiv:abs\/2309.05519."},{"key":"3040_CR215","doi-asserted-by":"crossref","unstructured":"Wu, Y., & He, K. (2018). Group normalization. ECCV (13) (Vol. 11217, pp. 3\u201319). Springer.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"3040_CR216","doi-asserted-by":"crossref","unstructured":"Xie, S., & Tu, Z. (2015). Holistically-nested edge detection. ICCV (pp. 1395\u20131403). IEEE Computer Society.","DOI":"10.1109\/ICCV.2015.164"},{"key":"3040_CR217","unstructured":"Xing, J., Xia, M., Liu, Y., Zhang, Y., Zhang, Y., He, Y., Liu, H., Chen, H., Cun, X., Wang, X., Shan, Y., & Wong, T. (2023). Make-your-video: Customized video generation using textual and structural guidance. CoRR arXiv:abs\/2306.00943."},{"key":"3040_CR218","unstructured":"Xing, Z., Dai, Q., Hu, H., Wu, Z., & Jiang, Y. (2023). Simda: Simple diffusion adapter for efficient video generation. CoRR arXiv:abs\/2308.09710."},{"key":"3040_CR219","unstructured":"Xing, Z., Feng, Q., Chen, H., Dai, Q., Hu, H., Xu, H., Wu, Z., & Jiang, Y. (2023). A survey on video diffusion models. CoRR arXiv:abs\/2310.10647."},{"key":"3040_CR220","doi-asserted-by":"crossref","unstructured":"Xu, C., Song, T., Feng, W., Li, X., Ge, T., Zheng, B., & Wang, L. (2024). Accelerating image generation with sub-path linear approximation model. CoRR arXiv:abs\/2404.13903.","DOI":"10.1007\/978-3-031-73668-1_19"},{"key":"3040_CR221","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., & Tao, D. (2022). Gmflow: Learning optical flow via global matching. In: CVPR, pp. 8111\u20138120. IEEE.","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"3040_CR222","unstructured":"Xu, Z., Zhang, J., Liew, J.H., Yan, H., Liu, J., Zhang, C., Feng, J., & Shou, M. Z. (2023). Magicanimate: Temporally consistent human image animation using diffusion model. CoRR arXiv:abs\/2311.16498."},{"key":"3040_CR223","doi-asserted-by":"crossref","unstructured":"Xue, H., Hang, T., Zeng, Y., Sun, Y., Liu, B., Yang, H., Fu, J., & Guo, B. (2022). Advancing high-resolution video-language representation with large-scale video transcriptions. In: CVPR, pp. 5026\u20135035. IEEE.","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"3040_CR224","unstructured":"Yan, W., Brown, A., Abbeel, P., Girdhar, R., & Azadi, S. (2023). Motion-conditioned image animation for video editing. CoRR arXiv:abs\/2311.18827."},{"key":"3040_CR225","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., & Zheng, F. (2023). Track anything: Segment anything meets videos. CoRR arXiv:abs\/2304.11968."},{"issue":"4","key":"3040_CR226","doi-asserted-by":"publisher","first-page":"105:1","DOI":"10.1145\/3626235","volume":"56","author":"L Yang","year":"2024","unstructured":"Yang, L., Zhang, Z., Song, Y., Hong, S., Xu, R., Zhao, Y., Zhang, W., Cui, B., & Yang, M. (2024). Diffusion models: A comprehensive survey of methods and applications. ACM Comput. Surv., 56(4), 105:1-105:39.","journal-title":"ACM Comput. Surv."},{"key":"3040_CR227","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhou, Y., Liu, Z., & Loy, C. C. (2023). Rerender A video: Zero-shot text-guided video-to-video translation. In: SIGGRAPH, pp. 95:1\u201395:11. ACM.","DOI":"10.1145\/3610548.3618160"},{"key":"3040_CR228","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhou, Y., Liu, Z., & Loy, C. C. (2024). FRESCO: spatial-temporal correspondence for zero-shot video translation. CoRR arXiv:abs\/2403.12962.","DOI":"10.1109\/CVPR52733.2024.00831"},{"key":"3040_CR229","doi-asserted-by":"crossref","unstructured":"Yatim, D., Fridman, R., Bar-Tal, O., Kasten, Y., & Dekel, T. (2023). Space-time diffusion features for zero-shot text-driven motion transfer. CoRR arXiv:abs\/2311.17009.","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"3040_CR230","unstructured":"Yin, T., Gharbi, M., Zhang, R., Shechtman, E., Durand, F., Freeman, W.T., & Park, T. (2023). One-step diffusion with distribution matching distillation. CoRR arXiv:abs\/2311.18828."},{"key":"3040_CR231","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., & Wu, Y. (2022). Coca: Contrastive captioners are image-text foundation models. Trans. Mach. Learn. Res, 2022."},{"key":"3040_CR232","unstructured":"Yu, K.P., Zhang, Z., Hu, F., & Chai, J. (2023). Efficient in-context learning in vision-language models for egocentric videos. CoRR arXiv:abs\/2311.17041."},{"key":"3040_CR233","unstructured":"Zhang, C., Zhang, C., Zhang, M., & Kweon, I. S. (2023). Text-to-image diffusion models in generative AI: A survey. CoRR arXiv:abs\/2303.07909."},{"key":"3040_CR234","doi-asserted-by":"crossref","unstructured":"Zhang, D.J., Wu, J.Z., Liu, J., Zhao, R., Ran, L., Gu, Y., Gao, D., & Shou, M. Z. (2023). Show-1: Marrying pixel and latent diffusion models for text-to-video generation. CoRR arXiv:abs\/2309.15818.","DOI":"10.1007\/s11263-024-02271-9"},{"key":"3040_CR235","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In: ICCV, pp. 3813\u20133824. IEEE.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3040_CR236","unstructured":"Zhang, S., Wang, J., Zhang, Y., Zhao, K., Yuan, H., Qin, Z., Wang, X., Zhao, D., & Zhou, J. (2023). I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models. CoRR arXiv:abs\/2311.04145."},{"key":"3040_CR237","unstructured":"Zhang, T., Wang, Z., Huang, J., Mohiuddin, M. T., & Shi, W. (2023). A survey of diffusion based image generation models: Issues and their solutions. CoRR arXiv:abs\/2308.13142."},{"key":"3040_CR238","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., & Tian, Q. (2023). Controlvideo: Training-free controllable text-to-video generation. CoRR arXiv:abs\/2305.13077."},{"key":"3040_CR239","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, B., Nie, X., Han, C., Guo, T., & Liu, L. (2023). Towards consistent video editing with text-to-image diffusion models. In: NeurIPS.","DOI":"10.52202\/075280-2550"},{"key":"3040_CR240","doi-asserted-by":"crossref","unstructured":"Zhao, R., Gu, Y., Wu, J. Z., Zhang, D. J., Liu, J., Wu, W., Keppo, J., & Shou, M. Z. (2023). Motiondirector: Motion customization of text-to-video diffusion models. CoRR arXiv:abs\/2310.08465.","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"3040_CR241","unstructured":"Zhao, Y., Xie, E., Hong, L., Li, Z., & Lee, G. H. (2023). Make-a-protagonist: Generic video editing with an ensemble of experts. CoRR arXiv:abs\/2305.08850."},{"key":"3040_CR242","doi-asserted-by":"crossref","unstructured":"Zhu, J., Yang, H., He, H., Wang, W., Tuo, Z., Cheng, W., Gao, L., Song, J., & Fu, J. (2023). Moviefactory: Automatic movie creation from text using large generative models for language and images. ACM Multimedia (pp. 9313\u20139319). ACM.","DOI":"10.1145\/3581783.3612707"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-03040-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-03040-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-03040-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T21:16:00Z","timestamp":1789766160000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-03040-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":242,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["3040"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-03040-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"assertion":[{"value":"27 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no conflict of interest to declare relevant to this article\u2019s content.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"440"}}