{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:12:10Z","timestamp":1777889530940,"version":"3.51.4"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100017567","name":"Apple","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01508","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16249-16259","source":"Crossref","is-referenced-by-count":0,"title":["STIV: Scalable Text and Image Conditioned Video Generation"],"prefix":"10.1109","author":[{"given":"Zongyu","family":"Lin","sequence":"first","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiasen","family":"Lu","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenze","family":"Hu","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsu-Jui","family":"Fu","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesse","family":"Allardice","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengfeng","family":"Lai","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangchen","family":"Song","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cha","family":"Chen","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiran","family":"Fei","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lezhi","family":"Li","sequence":"additional","affiliation":[{"name":"Apple,Cupertino,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinfei","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles,Los Angeles,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhou","family":"Sun","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles,Los Angeles,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai-Wei","family":"Chang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles,Los Angeles,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Videophy: Evaluating physical commonsense for video generation","author":"Bansal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"arXiv preprint","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref10","article-title":"Seine: Short-to-long video diffusion model for generative transition and prediction","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image generation","author":"Cho","year":"2024","journal-title":"ICLR"},{"key":"ref12","article-title":"Sora detector: A unified hallucination detection for large text-to-video models","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"issue":"16","key":"ref13","article-title":"Animateanything: Finegrained open domain image animation with motion guidance","volume":"1","author":"Dai","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref14","article-title":"Fine-grained open domain image animation with motion guidance","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref16","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref18","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01029"},{"key":"ref20","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref23","article-title":"Emu video: Factorizing text-to-video generation by explicit image conditioning","volume-title":"European Conference on Computer Vision","author":"Girdhar"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00301"},{"key":"ref25","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.379"},{"key":"ref28","author":"Heusel","year":"2018","journal-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium"},{"key":"ref29","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref31","article-title":"The Kinetics Human Action Video Dataset","author":"Kay","year":"2014","journal-title":"arXiv"},{"key":"ref32","volume-title":"Kling","year":"2024"},{"key":"ref33","article-title":"Revisit large-scale imagecaption data in pre-training multimodal foundation models","author":"Lai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref35","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"ArXiv e-prints"},{"key":"ref36","article-title":"T2VTurbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Li"},{"key":"ref37","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"ref39","volume-title":"Dream machine","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref42","volume-title":"Sora","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","volume-title":"Pika 1.0","year":"2023"},{"key":"ref45","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref46","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"140","key":"ref48","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref49","article-title":"Consisti2v: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref51","volume-title":"Gen-2","year":"2023"},{"key":"ref52","volume-title":"Gen-3 alpha","year":"2024"},{"key":"ref53","article-title":"Improved Techniques for Training GANs","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Salimans"},{"key":"ref54","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","volume-title":"International Conference on Machine Learning","author":"Shazeer"},{"key":"ref55","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref58","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref62","author":"Xu","year":"2023","journal-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation"},{"key":"ref63","article-title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"ref64","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref66","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref67","article-title":"Direct preference optimization of video large multimodal models from language model reward","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","volume-title":"arXiv preprint","author":"Zhang","year":"2023"},{"key":"ref69","article-title":"Fast training of diffusion models with masked transformers","author":"Zheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref70","author":"Zheng","year":"2024","journal-title":"Open-Sora: Democratizing Efficient Video Production for All"},{"key":"ref71","article-title":"Allegro: Open the black box of commercial-level video generation model","author":"Zhou","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444263.pdf?arnumber=11444263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:30Z","timestamp":1777612350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01508","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}