{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:34:08Z","timestamp":1742927648384,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":51,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787944"},{"type":"electronic","value":"9789819787951"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8795-1_29","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T23:03:25Z","timestamp":1730588605000},"page":"429-443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TT-DF: A Large-Scale Diffusion-Based Dataset and Benchmark for Human Body Forgery Detection"],"prefix":"10.1007","author":[{"given":"Wenkui","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhida","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxian","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Afchar, D., Nozick, V., Yamagishi, J., Echizen, I.: Mesonet: a compact facial video forgery detection network. In: IEEE International Workshop on Information Forensics and Security (WIFS), pp.\u00a01\u20137. IEEE (2018)","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Bai, W., Liu, Y., Zhang, Z., Li, B., Hu, W.: Aunet: learning relations between action units for face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24709\u201324719 (2023)","DOI":"10.1109\/CVPR52729.2023.02367"},{"key":"29_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning (ICML), vol.\u00a02, p.\u00a04 (2021)"},{"issue":"7","key":"29_CR4","first-page":"8920","volume":"45","author":"J Cao","year":"2022","unstructured":"Cao, J., Luo, M., Yu, J., Yang, M.H., He, R.: Scoremix: a scalable augmentation strategy for training gans with limited data. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 45(7), 8920\u20138935 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"29_CR6","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600. arXiv preprint arXiv:1808.01340 (2018)"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5933\u20135942 (2019)","DOI":"10.1109\/ICCV.2019.00603"},{"key":"29_CR8","unstructured":"Chang, D., Shi, Y., Gao, Q., Fu, J., Xu, H., Song, G., Yan, Q., Yang, X., Soleymani, M.: Magicdance: realistic human dance video generation with motions & facial expressions transfer. arXiv preprint arXiv:2311.12052 (2023)"},{"key":"29_CR9","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"29_CR11","unstructured":"Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., Ferrer, C.C.: The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397 (2020)"},{"key":"29_CR12","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representation (ICLR) (2021)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Fan, Q., Huang, H., Chen, M., Liu, H., He, R.: Rmt: retentive networks meet vision transformers. arXiv preprint arXiv:2309.11523 (2023)","DOI":"10.1109\/CVPR52733.2024.00539"},{"key":"29_CR14","unstructured":"Frank, J., Eisenhofer, T., Sch\u00f6nherr, L., Fischer, A., Kolossa, D., Holz, T.: Leveraging frequency analysis for deep fake image recognition. In: International Conference on Machine Learning (ICML), pp. 3247\u20133258. PMLR (2020)"},{"key":"29_CR15","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. Adv. Neural Inf. Process. Syste. (NeurIPS) 27 (2014)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R.A., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7297\u20137306 (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"29_CR17","unstructured":"Guo, Y., Yang, C., Rao, A., Wang, Y., Qiao, Y., Lin, D., Dai, B.: Animatediff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"29_CR18","unstructured":"Hu, L., Gao, X., Zhang, P., Sun, K., Zhang, B., Bo, L.: Animate anyone: consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117 (2023)"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Huang, B., Wang, Z., Yang, J., Ai, J., Zou, Q., Wang, Q., Ye, D.: Implicit identity driven deepfake face swapping detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4490\u20134499 (2023)","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Jafarian, Y., Park, H.S.: Learning high fidelity depths of dressed humans by watching social media dance videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12753\u201312762 (2021)","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Karras, J., Holynski, A., Wang, T.C., Kemelmacher-Shlizerman, I.: Dreampose: Fashion image-to-video synthesis via stable diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22623\u201322633. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6399\u20136408 (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Li, J., Xie, H., Li, J., Wang, Z., Zhang, Y.: Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6458\u20136467 (2021)","DOI":"10.1109\/CVPR46437.2021.00639"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Chang, M.C., Lyu, S.: In ictu oculi: exposing ai created fake videos by detecting eye blinking. In: IEEE International Workshop on Information Forensics and Security (WIFS), pp.\u00a01\u20137. IEEE (2018)","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, X., Sun, P., Qi, H., Lyu, S.: Celeb-df: a large-scale challenging dataset for deepfake forensics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3207\u20133216 (2020)","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, Y., Yan, J., Liu, W.: Generalizing face forgery detection with high-frequency features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16317\u201316326 (2021)","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"29_CR27","unstructured":"MooreThreads: moore-animateanyone. https:\/\/github.com\/MooreThreads\/Moore-AnimateAnyone (2023)"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Yamagishi, J., Echizen, I.: Capsule-forensics: using capsule networks to detect forged images and videos. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2307\u20132311. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yin, G., Sheng, L., Chen, Z., Shao, J.: Thinking in frequency: face forgery detection by mining frequency-aware clues. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 86\u2013103. Springer (2020)","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nie\u00dfner, M.: Faceforensics++: learning to detect manipulated facial images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1\u201311 (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"29_CR32","unstructured":"Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., Komatsuzaki, A.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1145\u20131153 (2017)","DOI":"10.1109\/CVPR.2017.494"},{"key":"29_CR34","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning (ICML), pp. 2256\u20132265. PMLR (2015)"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: Raft: recurrent all-pairs field transforms for optical flow. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 402\u2013419. Springer (2020)","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: Mocogan: decomposing motion and content for video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"29_CR37","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. (NeurIPS) 30 (2017)"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Wang, T., Li, L., Lin, K., Zhai, Y., Lin, C.C., Yang, Z., Zhang, H., Liu, Z., Wang, L.: Disco: disentangled control for realistic human dance generation. arXiv preprint arXiv:2307.00040 (2023)","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yu, K., Chen, C., Hu, X., Peng, S.: Dynamic graph learning with content-guided spatial-frequency relation reasoning for deepfake detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7278\u20137287 (2023)","DOI":"10.1109\/CVPR52729.2023.00703"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., Ge, Y., Wang, X., Lei, S.W., Gu, Y., Shi, Y., Hsu, W., Shan, Y., Qie, X., Shou, M.Z.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"29_CR41","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Xu, Y., Liang, J., Jia, G., Yang, Z., Zhang, Y., He, R.: Tall: Thumbnail layout for deepfake video detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22658\u201322668 (2023)","DOI":"10.1109\/ICCV51070.2023.02071"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, J., Liew, J.H., Yan, H., Liu, J.W., Zhang, C., Feng, J., Shou, M.Z.: Magicanimate: temporally consistent human image animation using diffusion model. arXiv preprint arXiv:2311.16498 (2023)","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Yang, X., Li, Y., Lyu, S.: Exposing deep fakes using inconsistent head poses. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8261\u20138265. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zeng, A., Yuan, C., Li, Y.: Effective whole-body pose estimation with two-stages distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4210\u20134220 (2023)","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"29_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, X., Karaman, S., Chang, S.F.: Detecting and simulating artifacts in gan fake images. In: IEEE International Workshop on Information Forensics and Security (WIFS), pp.\u00a01\u20136. IEEE (2019)","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"29_CR48","unstructured":"Zhang, Z., Cao, J., Yang, W., Fan, Q., Zhou, K., He, R.: Band-attention modulated retnet for face forgery detection. arXiv preprint arXiv:2404.06022 (2024)"},{"key":"29_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, W., Liang, Z., Shen, J.: Face forensics in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5778\u20135788 (2021)","DOI":"10.1109\/CVPR46437.2021.00572"},{"key":"29_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, H., Wang, Z., He, R.: Ristra: recursive image super-resolution transformer with relativistic assessment. IEEE Trans. Multimedia (TMM) (2024)","DOI":"10.1109\/TMM.2024.3352400"},{"key":"29_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, X., Li, J., Wang, Z., He, R., Tan, T.: Image inpainting with contrastive relation network. In: International Conference on Pattern Recognition (ICPR), pp. 4420\u20134427. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412640"}],"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\/978-981-97-8795-1_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T23:05:56Z","timestamp":1730588756000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8795-1_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819787944","9789819787951"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8795-1_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}