{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T03:22:49Z","timestamp":1782444169456,"version":"3.54.5"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Australian Government through the Australian Research Council","award":["DP210101682"],"award-info":[{"award-number":["DP210101682"]}]},{"name":"Australian Government through the Australian Research Council","award":["DP220102197"],"award-info":[{"award-number":["DP220102197"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3595822","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:01:44Z","timestamp":1754503304000},"page":"141313-141327","source":"Crossref","is-referenced-by-count":2,"title":["Faster Image2Video Generation: A Closer Look at CLIP Image Embedding\u2019s Impact on Spatio-Temporal Cross-Attentions"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1950-5143","authenticated-orcid":false,"given":"Ashkan","family":"Taghipour","sequence":"first","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6423-6475","authenticated-orcid":false,"given":"Morteza","family":"Ghahremani","sequence":"additional","affiliation":[{"name":"Munich Center for Machine Learning (MCML), Technical University of Munich (TUM), Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aref","family":"Miri Rekavandi","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, The University of Melbourne, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0945-6621","authenticated-orcid":false,"given":"Zinuo","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4758-7510","authenticated-orcid":false,"given":"Hamid","family":"Laga","sequence":"additional","affiliation":[{"name":"School of Information Technology, Murdoch University, Murdoch, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7250-7407","authenticated-orcid":false,"given":"Farid","family":"Boussaid","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic, and Computer Engineering, The University of Western Australia, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3424662"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939654"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3287854"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3387402"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687590"},{"key":"ref6","article-title":"Stable-pose: Leveraging transformers for pose-guided text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv:2406.02485"},{"key":"ref7","article-title":"Box it to bind it: Unified layout control and attribute binding in T2I diffusion models","author":"Taghipour","year":"2024","journal-title":"arXiv:2402.17910"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3169782"},{"key":"ref9","article-title":"Text-guided 3D human motion generation with keyframe-based parallel skip transformer","author":"Geng","year":"2024","journal-title":"arXiv:2405.15439"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3210543"},{"key":"ref11","article-title":"LatentMove: Towards complex human movement video generation","author":"Taghipour","year":"2025","journal-title":"arXiv:2505.22046"},{"key":"ref12","article-title":"Video as the new language for real-world decision making","author":"Yang","year":"2024","journal-title":"arXiv:2402.17139"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3315272"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref17","article-title":"VDT: General-purpose video diffusion transformers via mask modeling","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Lu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01462"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref20","volume-title":"Generative Models","year":"2024"},{"key":"ref21","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref22","article-title":"Faster diffusion via temporal attention decomposition","author":"Liu","year":"2024","journal-title":"arXiv:2404.02747"},{"key":"ref23","first-page":"1","article-title":"R&b: Region and boundary aware zero-shot grounded text-to-image generation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xiao"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref25","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv:2211.13221"},{"key":"ref26","article-title":"ModelScope text-to-video technical report","volume-title":"arXiv:2308.06571","author":"Wang","year":"2023"},{"key":"ref27","article-title":"Swap attention in spatiotemporal diffusions for Text-to-Video generation","author":"Wang","year":"2023","journal-title":"arXiv:2305.10874"},{"key":"ref28","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02079"},{"key":"ref30","article-title":"VSTAR: Generative temporal nursing for longer dynamic video synthesis","author":"Li","year":"2024","journal-title":"arXiv:2403.13501"},{"key":"ref31","article-title":"Mora: Enabling generalist video generation via a multi-agent framework","author":"Yuan","year":"2024","journal-title":"arXiv:2403.13248"},{"key":"ref32","article-title":"TokenCompose: Text-to-image diffusion with token-level supervision","author":"Wang","year":"2023","journal-title":"arXiv:2312.03626"},{"key":"ref33","article-title":"Grounded text-to-image synthesis with attention refocusing","author":"Phung","year":"2023","journal-title":"arXiv:2306.05427"},{"key":"ref34","article-title":"PIXART-\u1e9f: Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024","journal-title":"arXiv:2401.05252"},{"key":"ref35","volume-title":"Mochi 1","author":"Team","year":"2024"},{"issue":"70","key":"ref36","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","article-title":"Open-sora 2.0: Training a commercial-level video generation model in 200k","author":"Peng","year":"2025","journal-title":"arXiv:2503.09642"},{"key":"ref38","article-title":"HunyuanVideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv:2412.03603"},{"key":"ref39","article-title":"LTX-video: Realtime video latent diffusion","author":"HaCohen","year":"2024","journal-title":"arXiv:2501.00103"},{"key":"ref40","article-title":"Allegro: Open the black box of commercial-level video generation model","author":"Zhou","year":"2024","journal-title":"arXiv:2410.15458"},{"key":"ref41","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv:2310.19512"},{"key":"ref42","article-title":"ConsistI2 V: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024","journal-title":"arXiv:2402.04324"},{"key":"ref43","article-title":"I2 V-adapter: A general Image-to-Video adapter for diffusion models","author":"Guo","year":"2023","journal-title":"arXiv:2312.16693"},{"key":"ref44","article-title":"SEINE: Short-to-long video diffusion model for generative transition and prediction","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref45","article-title":"I2 VGen-XL: High-quality Image-to-Video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv:2311.04145"},{"key":"ref46","article-title":"DynamiCrafter: Animating open-domain images with video diffusion priors","author":"Xing","year":"2023","journal-title":"arXiv:2310.12190"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref48","article-title":"MotionCtrl: A unified and flexible motion controller for video generation","author":"Wang","year":"2023","journal-title":"arXiv:2312.03641"},{"key":"ref49","article-title":"Follow-Your-click: Open-domain regional image animation via short prompts","author":"Ma","year":"2024","journal-title":"arXiv:2403.08268"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref51","article-title":"Motion-I2 V: Consistent and controllable Image-to-Video generation with explicit motion modeling","author":"Shi","year":"2024","journal-title":"arXiv:2401.15977"},{"key":"ref52","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00572"},{"key":"ref55","first-page":"110315","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref56","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref58","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref59","article-title":"LLM blueprint: Enabling text-to-image generation with complex and detailed prompts","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Gani"},{"key":"ref60","volume-title":"Thop: Pytorch-opcounter","author":"Dong","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3758090"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3530678"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref64","article-title":"MagicDistillation: Weak-to-strong video distillation for large-scale few-step synthesis","author":"Shao","year":"2025","journal-title":"arXiv:2503.13319"},{"key":"ref65","article-title":"Long context tuning for video generation","author":"Guo","year":"2025","journal-title":"arXiv:2503.10589"},{"key":"ref66","article-title":"Vchitect-2.0: Parallel transformer for scaling up video diffusion models","author":"Fan","year":"2025","journal-title":"arXiv:2501.08453"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref69","volume-title":"Aesthetic Predictor","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00373"},{"key":"ref72","first-page":"597","article-title":"On the computational complexity of self-attention","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Keles"},{"key":"ref73","article-title":"MimicMotion: High-quality human motion video generation with confidence-aware pose guidance","author":"Zhang","year":"2024","journal-title":"arXiv:2406.19680"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3034233"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3261659"},{"key":"ref76","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv:1812.01717"},{"key":"ref77","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zhang"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11114950.pdf?arnumber=11114950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:46:13Z","timestamp":1755546373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11114950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3595822","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}