{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T11:25:14Z","timestamp":1768994714076,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":49,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556335","type":"print"},{"value":"9789819556342","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5634-2_9","type":"book-chapter","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T21:23:32Z","timestamp":1768944212000},"page":"121-134","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-Vision Embedding for\u00a0Generalized Diffusion Generated Videos Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4588-7798","authenticated-orcid":false,"given":"Jinchuan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3047-6520","authenticated-orcid":false,"given":"Jinlin","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3433-0764","authenticated-orcid":false,"given":"Yun","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8580-6493","authenticated-orcid":false,"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-6025","authenticated-orcid":false,"given":"Kangwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,21]]},"reference":[{"key":"9_CR1","unstructured":"Zeroscope_v2_XL, https:\/\/huggingface.co\/cerspense\/zeroscope_v2_XL (2023)"},{"key":"9_CR2","unstructured":"Pika. https:\/\/pika.art\/ (2023)"},{"key":"9_CR3","unstructured":"OpenAI Sora. https:\/\/openai.com\/sora\/ (2024)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Guo, X., Liu, X., Ren, Z., Grosz, S., Masi, I., Liu, X.: Hierarchical fine-grained image forgery detection and localization. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 3155\u20133165 (2023)","DOI":"10.1109\/CVPR52729.2023.00308"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Dire for diffusion-generated image detection. In: IEEE International Conference on Computer Vision, pp. 22445\u201322455 (2023)","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Ricker J, Lukovnikov D, Fischer A.: Aeroblade: training-free detection of latent diffusion images using autoencoder reconstruction error. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9130\u20139140 (2024)","DOI":"10.1109\/CVPR52733.2024.00872"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Cozzolino, D., Poggi, G., Corvi, R., Nie\u00dfner, M., Verdoliva, L.: Raising the bar of diffusion generated image detection with CLIP. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4356\u20134366 (2024)","DOI":"10.1109\/CVPRW63382.2024.00439"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Lin, L., Amerini, I., Wang, X., Hu, S.: Robust CLIP-based detector for exposing diffusion model-generated images. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 1\u20137 (2024)","DOI":"10.1109\/AVSS61716.2024.10672612"},{"key":"9_CR9","unstructured":"Yan, S., et al.: A sanity check for diffusion generated image detection (2024). arXiv:2406.19435"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Ojha, U., Li, Y., Lee, Y. J.: Towards universal fake image detectors that generalize across generative models. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 24480\u201324489 (2023)","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Bai, J., Lin, M., Cao, G., Lou, Z.: AI-Generated video detection via spatial-temporal anomaly learning. In: Chinese Conference on Pattern Recognition and Computer Vision, pp. 460\u2013470 (2024)","DOI":"10.1007\/978-981-97-8792-0_32"},{"key":"9_CR12","unstructured":"Chang, C., Liu, Z., Lyu, X., Qi, X.: What matters in detecting AI-generated videos like sora? (2024). arXiv:2406.19568"},{"key":"9_CR13","unstructured":"Ji, L., et al.: Distinguish any fake videos: unleashing the power of large-scale data and motion features (2024). arXiv:2405.15343"},{"key":"9_CR14","unstructured":"Song, X., et al.: On learning multi-modal forgery representation for diffusion generated video detection. In: Advances in Conference on Neural Information Processing Systems (2024)"},{"key":"9_CR15","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Ni, B., et al.: Expanding language-image pretrained models for general video recognition. In: European Conference on Computer Vision, pp. 1\u201318 (2022)","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"9_CR17","unstructured":"Wang, Y., et al.: Internvid: a large-scale video-text dataset for multimodal understanding and generation (2023). arXiv:2307.06942"},{"key":"9_CR18","unstructured":"Chen, H., et al.: Demamba: ai-generated video detection on million-scale genvideo benchmark (2024) arXiv:2405.19707"},{"key":"9_CR19","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023). arXiv:2311.15127"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Videocrafter2: overcoming data limitations for high-quality video diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7310-7320 (2024)","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"9_CR21","unstructured":"Zhang, S., et al.: I2vgen-xl: high-quality image-to-video synthesis via cascaded diffusion models (2023) arXiv:2311.04145"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Xing, J., et al.: Dynamicrafter: animating open-domain images with video diffusion priors. In: European Conference on Computer Vision, pp. 399\u2013417 (2024)","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"9_CR23","unstructured":"Chen, X., Wang, Y., Zhang, L., Zhuang, S., Ma, X., Yu, J., Liu, Z.: Seine: short-to-long video diffusion model for generative transition and prediction. In: International Conference on Learning Representations (2023)"},{"key":"9_CR24","unstructured":"Ma, X., Wang, Y., Chen, X., Jia, G., Liu, Z., Li, Y. F., Qiao, Y.: Latte: latent diffusion transformer for video generation. Trans. Mach. Learn. Rese. (2025)"},{"key":"9_CR25","unstructured":"Peng, X., et al.: Open-sora 2.0: training a commercial-level video generation model in \\$200 k (2025) arXiv:2503.09642"},{"key":"9_CR26","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: Modelscope text-to-video technical report (2023). arXiv:2308.06571"},{"key":"9_CR27","unstructured":"Morphstudio https:\/\/www.morphstudio.com\/ (2023)"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models. In: IEEE International Conference on Computer Vision, pp. 7346\u20137356 (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"9_CR29","unstructured":"Moonvalley https:\/\/www.moonvalley.com\/ (2023)"},{"key":"9_CR30","unstructured":"Liu, Q., Shi, P., Tsai, Y.Y., Mao, C., Yang, J.: Turns out i\u2019m not real: towards robust detection of AI-generated videos (2024). arXiv:2406.09601"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Vahdati, D.S., Nguyen, T.D., Azizpour, A., Stamm, M.C.: Beyond deepfake images: detecting ai-generated videos. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4397\u20134408 (2024)","DOI":"10.1109\/CVPRW63382.2024.00443"},{"key":"9_CR32","unstructured":"Ma, L., Zhang, J., Deng, H., Zhang, N., Liao, Y., Yu, H.: DeCoF: generated video detection via frame consistency (2024). arxiv:2402.02085"},{"key":"9_CR33","unstructured":"He, P., Zhu, L., Li, J., Wang, S., Li, H.: Exposing AI-generated videos: a benchmark dataset and a local-and-global temporal defect based detection method (2024). arXiv:2405.04133"},{"key":"9_CR34","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems, vol. 35, pp. 10078\u201310093 (2022)"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Mvitv2: improved multiscale vision transformers for classification and detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"9_CR36","unstructured":"Xu, H., et la.: Youku-mplug: a 10 million large-scale chinese video-language dataset for pre-training and benchmarks (2023). arXiv:2306.04362"},{"key":"9_CR37","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017). arXiv:1705.06950"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xing, Z., Zeng, Y., Fang, Y., Chen, K.: Pia: Your personalized image animator via plug-and-play modules in text-to-image models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7747-7756 (2024)","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"9_CR39","unstructured":"Hotshot https:\/\/huggingface.co\/hotshotco\/Hotshot-XL (2023)"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, D.J., et al.: Show-1: marrying pixel and latent diffusion models for text-to-video generation. Int. J. Comput. Vis. 1\u201315 (2024)","DOI":"10.1007\/s11263-024-02271-9"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Videocrafter1: open diffusion models for high-quality video generation (2023) arXiv:2310.19512","DOI":"10.1109\/CVPR52729.2023.10308948"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Lavie: high-quality video generation with cascaded latent diffusion models. Int. J. Comput. Vis. 133(5), 3059\u20133078 (2025)","DOI":"10.1007\/s11263-024-02295-1"},{"key":"9_CR43","unstructured":"Chen, B., Zeng, J., Yang, J., Yang, R.: Drct: diffusion reconstruction contrastive training towards universal detection of diffusion generated images. In: International Conference on Machine Learning (2024)"},{"key":"9_CR44","unstructured":"Nie, Y., et al.: Lightclip: learning multi-level interaction for lightweight vision-language models (2023) arXiv:2312.00674"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 23390\u201323400 (2023)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"9_CR46","unstructured":"Zhang, S., et al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs (2023) arXiv:2303.00915"},{"key":"9_CR47","doi-asserted-by":"crossref","unstructured":"Chia, P.J., et al.: Contrastive language and vision learning of general fashion concepts. Sci. Rep. 12(1), 18958 (2022)","DOI":"10.1038\/s41598-022-23052-9"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Guzhov, A., Raue, F., Hees, J., Dengel, A.: Audioclip: extending clip to image, text and audio. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 976\u2013980 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: Msr-vtt: a large video description dataset for bridging video and language. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5634-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T21:23:38Z","timestamp":1768944218000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5634-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556335","9789819556342"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5634-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"21 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}