{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:26:38Z","timestamp":1761895598773,"version":"build-2065373602"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209997","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Tell and Show: A Multimodal Guidance Method for Instructional Video Planning"],"prefix":"10.1109","author":[{"given":"Mingzhe","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Normal University,School of Artificial Intelligence,Beijing,China"}]},{"given":"Yinghui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Normal University,College of Education for the Future,Zhuhai,China"}]},{"given":"Fengxiang","family":"Ge","sequence":"additional","affiliation":[{"name":"Beijing Normal University,School of Artificial Intelligence,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01404"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01425"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01424"},{"article-title":"Video diffusion models","year":"2022","author":"Ho","key":"ref4"},{"article-title":"Latte: Latent diffusion transformer for video generation","year":"2024","author":"Ma","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00945"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01033"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00295"},{"article-title":"Schema: State changes matter for procedure planning in instructional videos","year":"2024","author":"Niu","key":"ref13"},{"article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","year":"2015","author":"Sohl-Dickstein","key":"ref14"},{"article-title":"Improved techniques for training score-based generative models","year":"2020","author":"Song","key":"ref15"},{"article-title":"Large scale gan training for high fidelity natural image synthesis","year":"2019","author":"Brock","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"article-title":"Make-a-video: Text-to-video generation without text-video data","year":"2022","author":"Singer","key":"ref18"},{"article-title":"Mcvd: Masked conditional video diffusion for prediction, generation, and interpolation","year":"2022","author":"Voleti","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/e25101469"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2018.2808685"},{"article-title":"Towards accurate generative models of video: A new metric challenges","year":"2019","author":"Unterthiner","key":"ref25"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209997.pdf?arnumber=11209997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:54:13Z","timestamp":1761890053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209997","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}