{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:26Z","timestamp":1778048366429,"version":"3.51.4"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00204","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2052-2062","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr\u00e9chet Distance"],"prefix":"10.1109","author":[{"given":"Jaywon","family":"Koo","sequence":"first","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jefferson","family":"Hernandez","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moayed","family":"Haji-Ali","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyan","family":"Yang","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vicente","family":"Ordonez","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025"},{"key":"ref2","volume-title":"Text to image model arena"},{"key":"ref3","volume-title":"Conditional Fr\u00e9chet inception distance","author":"Biderman"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref5","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref6","author":"Chiang","year":"2024","journal-title":"Chatbot arena: An open platform for evaluating llms by human preference"},{"key":"ref7","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref8","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international Conference on machine learning","author":"Esser"},{"key":"ref9","article-title":"Data filtering networks","author":"Fang","year":"2023"},{"key":"ref10","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","author":"Fu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00631"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02632-y"},{"key":"ref15","article-title":"Av-link: Temporally-aligned diffusion features for cross-modal audio-video generation","author":"Haji-Ali","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01480"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref19","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Advances in neural information processing systems","volume":"30","author":"Heusel"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref21","article-title":"Auto-encoding variational bayes","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref23","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.663"},{"key":"ref26","volume-title":"Kling video model","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref29","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref31","article-title":"Beyond fvd: Enhanced evaluation metrics for video generation quality","author":"Luo","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"ref33","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref34","volume-title":"Parti prompts leaderboard"},{"key":"ref35","article-title":"Dreambench++: A human-aligned benchmark for personalized image generation","author":"Peng","year":"2024"},{"key":"ref36","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref38","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on machine learning","author":"Ramesh"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","volume-title":"Gen-3 alpha","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref42","article-title":"Improved techniques for training gans","volume-title":"Advances in neural information processing systems","volume":"29","author":"Salimans"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref44","author":"Yang","year":"2025","journal-title":"Seaweed-7b: Cost-effective training of video generation foundation model"},{"key":"ref45","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref46","article-title":"Conditional Fr\u00e9chet inception distance","author":"Soloveitchik","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0165"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref49","author":"Unterthiner","year":"2019","journal-title":"Fvd: A new metric for video generation"},{"key":"ref50","article-title":"Fr\\\u2019echet wavelet distance: A domain-agnostic metric for image generation","author":"Veeramacheneni","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref56","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"issue":"3","key":"ref57","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Yu","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00766"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00766"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492577.pdf?arnumber=11492577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:58:25Z","timestamp":1778047105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00204","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}