{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:56:52Z","timestamp":1778605012546,"version":"3.51.4"},"reference-count":75,"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":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CyberSG R&D Programme Office (``CRPO''), under the National Cybersecurity R&D Programme (``NCRP''), RIE2025 NCRP Funding Initiative","award":["CRPO-GC1-NTU-002"],"award-info":[{"award-number":["CRPO-GC1-NTU-002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3673949","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:09:39Z","timestamp":1773950979000},"page":"3085-3098","source":"Crossref","is-referenced-by-count":2,"title":["SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9567-159X","authenticated-orcid":false,"given":"Rong-Cheng","family":"Tu","sequence":"first","affiliation":[{"name":"Nanyang Technological University, 50 Nanyang Avenue, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, 50 Nanyang Avenue, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Jin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, 50 Nanyang Avenue, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyi","family":"Liao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, 50 Nanyang Avenue, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8681-0471","authenticated-orcid":false,"given":"Jiaxing","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, 50 Nanyang Avenue, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, 50 Nanyang Avenue, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"ref4","volume-title":"Video Generation Models As World Simulators","author":"Brooks","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv:2310.19512"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","article-title":"GenTron: Diffusion transformers for image and video generation","author":"Chen","year":"2023","journal-title":"arXiv:2312.04557"},{"key":"ref9","article-title":"LLaVA-interactive: An all-in-one demo for image chat, segmentation, generation and editing","author":"Chen","year":"2023","journal-title":"arXiv:2311.00571"},{"key":"ref10","article-title":"SEINE: Short-to-long video diffusion model for generative transition and prediction","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"ref13","article-title":"FLATTEN: Optical FLow-guided ATTENtion for consistent text-to-video editing","author":"Cong","year":"2023","journal-title":"arXiv:2310.05922"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref15","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Forty-first Int. Conf. Mach. Learn.","author":"Esser"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref17","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"arXiv:2307.10373"},{"key":"ref18","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv:2307.04725"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref20","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Ho"},{"key":"ref23","article-title":"VideoControlNet: A motion-guided video-to-video translation framework by using diffusion model with ControlNet","author":"Hu","year":"2023","journal-title":"arXiv:2307.14073"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref25","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref26","article-title":"Ground-A-video: Zero-shot grounded video editing using text-to-image diffusion models","author":"Jeong","year":"2023","journal-title":"arXiv:2310.01107"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3773279"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"ref30","article-title":"MuLan: Multimodal-LLM agent for progressive and interactive multi-object diffusion","author":"Li","year":"2024","journal-title":"arXiv:2402.12741"},{"key":"ref31","article-title":"CogVLA: Cognition-aligned vision-language-action model via instruction-driven routing & sparsification","author":"Li","year":"2025","journal-title":"arXiv:2508.21046"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref33","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Liu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3617827"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref36","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv:2401.03048"},{"key":"ref37","volume-title":"Chatgpt"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref42","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref44","article-title":"A survey of multimodal-guided image editing with text-to-image diffusion models","author":"Shuai","year":"2024","journal-title":"arXiv:2406.14555"},{"key":"ref45","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref46","article-title":"VORTA: Efficient video diffusion via routing sparse attention","author":"Sun","year":"2025","journal-title":"arXiv:2505.18809"},{"key":"ref47","article-title":"AsymRnR: Video diffusion transformers acceleration with asymmetric reduction and restoration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref48","article-title":"Diffusion model-based video editing: A survey","author":"Sun","year":"2024","journal-title":"arXiv:2407.07111"},{"key":"ref49","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref50","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3596394"},{"key":"ref52","article-title":"MLLM-guided VLM fine-tuning with joint inference for zero-shot composed image retrieval","author":"Tu","year":"2025","journal-title":"arXiv:2505.19707"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref54","article-title":"Mobile-agent: Autonomous multi-modal mobile device agent with visual perception","author":"Wang","year":"2024","journal-title":"arXiv:2401.16158"},{"key":"ref55","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023","journal-title":"arXiv:2303.17599"},{"key":"ref56","article-title":"VideoComposer: Compositional video synthesis with motion controllability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref57","article-title":"LAVIE: High-quality video generation with cascaded latent diffusion models","author":"Wang","year":"2023","journal-title":"arXiv:2309.15103"},{"key":"ref58","article-title":"InternVid: A large-scale video-text dataset for multimodal understanding and generation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref59","article-title":"Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents","author":"Wang","year":"2023","journal-title":"arXiv:2302.01560"},{"key":"ref60","article-title":"GenArtist: Multimodal LLM as an agent for unified image generation and editing","author":"Wang","year":"2024","journal-title":"arXiv:2407.05600"},{"key":"ref61","article-title":"Divide and conquer: Language models can plan and self-correct for compositional text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv:2401.15688"},{"key":"ref62","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv:2206.07682"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref65","article-title":"SmartPlay: A benchmark for LLMs as intelligent agents","author":"Wu","year":"2023","journal-title":"arXiv:2310.01557"},{"key":"ref66","article-title":"DynamiCrafter: Animating open-domain images with video diffusion priors","author":"Xing","year":"2023","journal-title":"arXiv:2310.12190"},{"key":"ref67","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal LLMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02482"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713600"},{"key":"ref70","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv:2408.06072"},{"key":"ref71","article-title":"Mora: Enabling generalist video generation via a multi-agent framework","author":"Yuan","year":"2024","journal-title":"arXiv:2403.13248"},{"key":"ref72","article-title":"InternLM-XComposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024","journal-title":"arXiv:2407.03320"},{"key":"ref73","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":"ref74","volume-title":"Open-Sora: Democratizing Efficient Video Production for All","author":"Zheng"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00841"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11448590.pdf?arnumber=11448590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:52:48Z","timestamp":1774554768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11448590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3673949","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}