{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T19:26:56Z","timestamp":1780342016111,"version":"3.54.1"},"reference-count":58,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3550945","type":"journal-article","created":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T17:55:22Z","timestamp":1741974922000},"page":"47068-47085","source":"Crossref","is-referenced-by-count":3,"title":["LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net Denoising"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9605-2531","authenticated-orcid":false,"given":"Muhammad","family":"Waseem","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6733-2569","authenticated-orcid":false,"given":"Muhammad Usman Ghani","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1818-9115","authenticated-orcid":false,"given":"Syed Khaldoon","family":"Khurshid","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"key":"ref2","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref3","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv:2108.01073"},{"key":"ref4","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"ref7","first-page":"1","article-title":"LLMScore: Unveiling the power of large language models in text-to-image synthesis evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lu"},{"key":"ref8","article-title":"ColorwAI: Generative colorways of textiles through GAN and diffusion disentanglement","author":"Schaerf","year":"2024","journal-title":"arXiv:2407.11514"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref10","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv:1411.1784"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref14","first-page":"45","article-title":"Markov chain concepts related to","volume-title":"Markov Chain Monte Carlo in Practice","author":"Roberts","year":"1995"},{"issue":"5","key":"ref15","doi-asserted-by":"crossref","first-page":"2549","DOI":"10.1007\/s00521-023-09185-6","article-title":"Optimizing and interpreting the latent space of the conditional text-to-image GANs","volume":"36","author":"Zhang","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref17","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref18","article-title":"LAVIE: High-quality video generation with cascaded latent diffusion models","author":"Wang","year":"2023","journal-title":"arXiv:2309.15103"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref20","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref22","first-page":"1","article-title":"Palette: Image-to-image diffusion models","volume-title":"Proc. ACM SIGGRAPH Conf.","author":"Saharia"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS51430.2021.9441804"},{"issue":"3","key":"ref24","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/0040-1625(87)90011-4","article-title":"A diffusion model with application to evolving medical technologies","volume":"31","author":"Homer","year":"1987","journal-title":"Technological Forecasting Social Change"},{"issue":"2","key":"ref25","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1038\/s44222-023-00114-9","article-title":"Diffusion models in bioinformatics and computational biology","volume":"2","author":"Guo","year":"2023","journal-title":"Nature Rev. Bioeng."},{"key":"ref26","first-page":"88","article-title":"Anatomically-controllable medical image generation with segmentation-guided diffusion models","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.","author":"Konz"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref28","article-title":"LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2023","journal-title":"arXiv:2305.13655"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref30","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv:2206.07682"},{"key":"ref31","volume-title":"Runwayml: Text-to-Video, Image-to-Video, and More","author":"Team","year":"2023"},{"key":"ref32","volume-title":"An Honest Review of Pictory: The AI-Powered Video Editing Tool","author":"Agency","year":"2023"},{"key":"ref33","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref35","article-title":"DiffusionGPT: LLM-driven text-to-image generation system","author":"Qin","year":"2024","journal-title":"arXiv:2401.10061"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","article-title":"Mini-DALLE3: Interactive text to image by prompting large language models","author":"Lai","year":"2023","journal-title":"arXiv:2310.07653"},{"key":"ref39","article-title":"ELLA: Equip diffusion models with LLM for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"arXiv:2403.05135"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3338488"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICIPRob54042.2022.9798737"},{"key":"ref42","article-title":"VideoLLM: Modeling video sequence with large language models","author":"Chen","year":"2023","journal-title":"arXiv:2305.13292"},{"key":"ref43","article-title":"MotionFlow: Attention-driven motion transfer in video diffusion models","author":"Han Salih Meral","year":"2024","journal-title":"arXiv:2412.05275"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/wevj15060255"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/NILES63360.2024.10753164"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10282550"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2018.8624022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09242-5"},{"key":"ref49","article-title":"Videodrafter: Content-consistent multi-scene video generation with llm","author":"Long","year":"2024","journal-title":"arXiv:2401.01256"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682386"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-3267-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300575"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.08.037"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01429"},{"key":"ref55","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"},{"key":"ref56","article-title":"Frame-semantic parsing with softmax-margin segmental RNNs and a syntactic scaffold","author":"Swayamdipta","year":"2017","journal-title":"arXiv:1706.09528"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00295-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3334019"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10925377.pdf?arnumber=10925377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:50:21Z","timestamp":1742842221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10925377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3550945","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}