{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T20:05:57Z","timestamp":1784318757125,"version":"3.55.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0115500"],"award-info":[{"award-number":["2024YFE0115500"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302297"],"award-info":[{"award-number":["62302297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72192821"],"award-info":[{"award-number":["72192821"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3700881","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:38:27Z","timestamp":1782934707000},"page":"7460-7474","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Frame Interpolation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2776-0488","authenticated-orcid":false,"given":"Yijia","family":"Hong","sequence":"first","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8891-6766","authenticated-orcid":false,"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1858-3358","authenticated-orcid":false,"given":"Ran","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijian","family":"Cao","sequence":"additional","affiliation":[{"name":"Youtu Laboratory, Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5764-3096","authenticated-orcid":false,"given":"Xiaobin","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3387690"},{"key":"ref3","first-page":"1","article-title":"Video frame interpolation using real-time intermediate flow estimation","volume-title":"Proc. Int. Conf. Knowl. Eng. Commun. Syst. (ICKECS)","author":"Prasanna"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3100714"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591497"},{"key":"ref6","first-page":"51601","article-title":"Framer: Interactive frame interpolation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref7","article-title":"Generative inbetweening: Adapting image-to-video models for keyframe interpolation","author":"Wang","year":"2024","journal-title":"arXiv:2408.15239"},{"key":"ref8","article-title":"Generative inbetweening through frame-wise conditions-driven video generation","author":"Zhu","year":"2024","journal-title":"arXiv:2412.11755"},{"key":"ref9","first-page":"3441","article-title":"ViBiDSampler: Enhancing video interpolation using bidirectional diffusion sampler","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref10","volume-title":"Kling AI: Next-Generative AI Creative Studio","year":"2025"},{"key":"ref11","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv:2503.20314"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3556544"},{"key":"ref13","article-title":"Benchmarking video frame interpolation","author":"Kiefhaber","year":"2024","journal-title":"arXiv:2403.17128"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.244"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/188"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00343"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00352"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01696"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6693"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.37"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC54071.2022.9722682"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00550"},{"key":"ref24","article-title":"BiM-VFI: Directional motion field-guided frame interpolation for video with non-uniform motions","author":"Seo","year":"2024","journal-title":"arXiv:2412.11365"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680846"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32404"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00701"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_22"},{"key":"ref34","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref35","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv:2307.04725"},{"key":"ref36","volume-title":"Video Generation Models as World Simulators","author":"Brooks et al","year":"2024"},{"key":"ref37","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv:2408.06072"},{"key":"ref38","article-title":"HunyuanVideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv:2412.03603"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref40","first-page":"1","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shazeer"},{"issue":"120","key":"ref41","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"issue":"2","key":"ref43","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","volume":"1","author":"Hu"},{"key":"ref44","article-title":"LoraHub: Efficient cross-task generalization via dynamic LoRA composition","author":"Huang","year":"2023","journal-title":"arXiv:2307.13269"},{"key":"ref45","article-title":"Mixture of LoRA experts","author":"Wu","year":"2024","journal-title":"arXiv:2404.13628"},{"key":"ref46","article-title":"LoRA-switch: Boosting the efficiency of dynamic LLM adapters via system-algorithm co-design","author":"Kong","year":"2024","journal-title":"arXiv:2405.17741"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3227503"},{"key":"ref50","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv:2412.00131"},{"key":"ref51","first-page":"1","article-title":"UltraVideo: High-quality UHD video dataset with comprehensive captions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Zhang"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref54","article-title":"Koala-36M: A large-scale video dataset improving consistency between fine-grained conditions and video content","author":"Wang","year":"2024","journal-title":"arXiv:2410.08260"},{"key":"ref55","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref56","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref57","article-title":"IVEBench: Modern benchmark suite for instruction-guided video editing assessment","author":"Chen","year":"2025","journal-title":"arXiv:2510.11647"},{"key":"ref58","article-title":"HumanVideo-MME: Benchmarking MLLMs for human-centric video understanding","author":"Cai","year":"2025","journal-title":"arXiv:2507.04909"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"ref60","article-title":"GLM-4.5V and GLM-4.1V-thinking: Towards versatile multimodal reasoning with scalable reinforcement learning","author":"Hong","year":"2025","journal-title":"arXiv:2507.01006"},{"key":"ref61","article-title":"Qwen3 technical report","volume-title":"arXiv:2505.09388","author":"Yang","year":"2025"},{"key":"ref62","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref65","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref66","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv:1812.01717"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11592753.pdf?arnumber=11592753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T19:47:06Z","timestamp":1784317626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11592753\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3700881","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}