{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:47:48Z","timestamp":1787017668864,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"Huazhong University of Science and Technology","doi-asserted-by":"publisher","award":["YCJJ20242219"],"award-info":[{"award-number":["YCJJ20242219"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733435","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:39Z","timestamp":1750876299000},"page":"1823-1830","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SpectraSpan: Zero Fine-Tuning Long Video Generation Framework and Its Frequency Domain Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2006-9279","authenticated-orcid":false,"given":"Wentao","family":"Zhang","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5690-1910","authenticated-orcid":false,"given":"Fen","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4626-4140","authenticated-orcid":false,"given":"Zheng","family":"Cao","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Yogesh Balaji Seungjun Nah Xun Huang Arash Vahdat Jiaming Song Qinsheng Zhang Karsten Kreis Miika Aittala Timo Aila Samuli Laine Bryan Catanzaro Tero Karras and Ming-Yu Liu. 2023. eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers. doi:10.48550\/arXiv.2211.01324 arxiv: 2211.01324 [cs.CV]","DOI":"10.48550\/arXiv.2211.01324"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602573"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang Chao Weng and Ying Shan. 2023. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation. doi:10.48550\/arXiv.2310.19512 arxiv: 2310.19512 [cs.CV]","DOI":"10.48550\/arXiv.2310.19512"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3540261.3540933"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.03025"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"Yuwei Guo Ceyuan Yang Anyi Rao Zhengyang Liang Yaohui Wang Yu Qiao Maneesh Agrawala Dahua Lin and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. doi:10.48550\/arXiv.2307.04725 arxiv: 2307.04725 [cs.CV]","DOI":"10.48550\/arXiv.2307.04725"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602297"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Yingqing He Tianyu Yang Yong Zhang Ying Shan and Qifeng Chen. 2023. Latent Video Diffusion Models for High-Fidelity Long Video Generation. doi:10.48550\/arXiv.2211.13221 arxiv: 2211.13221 [cs.CV]","DOI":"10.48550\/arXiv.2211.13221"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Roberto Henschel Levon Khachatryan Daniil Hayrapetyan Hayk Poghosyan Vahram Tadevosyan Zhangyang Wang Shant Navasardyan and Humphrey Shi. 2024. StreamingT2V: Consistent Dynamic and Extendable Long Video Generation from Text. doi:10.48550\/arXiv.2403.14773 arxiv: 2403.14773 [cs.CV]","DOI":"10.48550\/arXiv.2403.14773"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496298"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. doi:10.48550\/arXiv.2207.12598 arxiv: 2207.12598 [cs.LG]","DOI":"10.48550\/arXiv.2207.12598"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3600898"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Wenyi Hong Ming Ding Wendi Zheng Xinghan Liu and Jie Tang. 2022. CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers. doi:10.48550\/arXiv.2205.15868 arxiv: 2205.15868 [cs.CV]","DOI":"10.48550\/arXiv.2205.15868"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. doi:10.48550\/arXiv.2106.09685 arxiv: 2106.09685 [cs.CL]","DOI":"10.48550\/arXiv.2106.09685"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680849"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02079"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.14818"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Zhifeng Kong and Wei Ping. 2021. On Fast Sampling of Diffusion Probabilistic Models. doi:10.48550\/arXiv.2106.00132 arxiv: 2106.00132 [cs.LG]","DOI":"10.48550\/arXiv.2106.00132"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3666122.3667767"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2011.6190099"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby Mahmoud Assran Nicolas Ballas Wojciech Galuba Russell Howes Po-Yao Huang Shang-Wen Li Ishan Misra Michael Rabbat Vasu Sharma Gabriel Synnaeve Hu Xu Herv\u00e9 Jegou Julien Mairal Patrick Labatut Armand Joulin and Piotr Bojanowski. 2024. DINOv2: Learning Robust Visual Features without Supervision. doi:10.48550\/arXiv.2304.07193 arxiv: 2304.07193 [cs.CV]","DOI":"10.48550\/arXiv.2304.07193"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.15169"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.07685"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. doi:10.48550\/arXiv.2204.06125 arxiv: 2204.06125 [cs.CV]","DOI":"10.48550\/arXiv.2204.06125"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602913"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","unstructured":"Uriel Singer Adam Polyak Thomas Hayes Xi Yin Jie An Songyang Zhang Qiyuan Hu Harry Yang Oron Ashual Oran Gafni Devi Parikh Sonal Gupta and Yaniv Taigman. 2022. Make-A-Video: Text-to-Video Generation without Text-Video Data. doi:10.48550\/arXiv.2209.14792 arxiv: 2209.14792 [cs.CV]","DOI":"10.48550\/arXiv.2209.14792"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045358"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Yu Tian Jian Ren Menglei Chai Kyle Olszewski Xi Peng Dimitris N. Metaxas and Sergey Tulyakov. 2021. A Good Image Generator Is What You Need for High-Resolution Video Synthesis. doi:10.48550\/arXiv.2104.15069 arxiv: 2104.15069 [cs.CV]","DOI":"10.48550\/arXiv.2104.15069"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.02399"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Fu-Yun Wang Wenshuo Chen Guanglu Song Han-Jia Ye Yu Liu and Hongsheng Li. 2023c. Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising. doi:10.48550\/arXiv.2305.18264 arxiv: 2305.18264 [cs.CV]","DOI":"10.48550\/arXiv.2305.18264"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","unstructured":"Jianyi Wang Kelvin C.K. Chan and Chen Change Loy. 2023a. Exploring CLIP for assessing the look and feel of images. In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence (AAAI'23\/IAAI'23\/EAAI'23). AAAI Press Article 284 9 pages. doi:10.1609\/aaai.v37i2.25353","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.15103"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.14806"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--19787--1_41"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271--9"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--72992--8_16"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","unstructured":"Daquan Zhou Weimin Wang Hanshu Yan Weiwei Lv Yizhe Zhu and Jiashi Feng. 2023. MagicVideo: Efficient Video Generation With Latent Diffusion Models. doi:10.48550\/arXiv.2211.11018 arxiv: 2211.11018 [cs.CV]","DOI":"10.48550\/arXiv.2211.11018"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:14:19Z","timestamp":1755749659000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733435"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":50,"alternative-id":["10.1145\/3731715.3733435","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733435","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}