{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:04:44Z","timestamp":1766124284055,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819698554"},{"type":"electronic","value":"9789819698561"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-9856-1_31","type":"book-chapter","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T12:39:14Z","timestamp":1753187954000},"page":"368-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Catching Inter-Modal Artifacts: A Cross-Modal Framework for Temporal Forgery Localization"],"prefix":"10.1007","author":[{"given":"Yuhan","family":"Cai","sequence":"first","affiliation":[]},{"given":"Yang","family":"Hua","sequence":"additional","affiliation":[]},{"given":"Wenjie","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiaoning","family":"Song","sequence":"additional","affiliation":[]},{"given":"Zhenhua","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,23]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Yamamoto, R., Song, E., Kim, J.M.: Parallel WaveGAN: a fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6199\u20136203. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. In: IEEE\/CVF International Conference on Computer Vision, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Yan, Z., Zhang, Y., Fan, Y., Wu, B.: UCF: uncovering common features for generalizable deepfake detection. In: IEEE\/CVF International Conference on Computer Vision, pp. 22412\u201322423 (2023)","DOI":"10.1109\/ICCV51070.2023.02048"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Dong, S., Wang, J., Ji, R., Liang, J., Fan, H., Ge, Z.: Implicit identity leakage: the stumbling block to improving deepfake detection generalization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3994\u20134004 (2023)","DOI":"10.1109\/CVPR52729.2023.00389"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., Stefanov, K., Dhall, A., Hayat, M.: Do you really mean that? Content driven audiovisual deepfake dataset and multimodal method for temporal forgery localization. In: 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1\u201310. IEEE (2022)","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, H., Du, M., Liu, H., Zhou, Y., Zeng, Q.: UMMAFormer: a universal multimodal-adaptive transformer framework for temporal forgery localization. In: 31st ACM International Conference on Multimedia. pp. 8749\u20138759 (2023)","DOI":"10.1145\/3581783.3613767"},{"key":"31_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103818","volume":"236","author":"Z Cai","year":"2023","unstructured":"Cai, Z., Ghosh, S., Dhall, A., Gedeon, T., Stefanov, K., Hayat, M.: Glitch in the matrix: a large scale benchmark for content driven audio\u2013visual forgery detection and localization. Comput. Vis. Image Underst. 236, 103818 (2023)","journal-title":"Comput. Vis. Image Underst."},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: IEEE International Conference on Computer Vision, pp. 609\u2013617 (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Afouras, T., Asano, Y.M., Fagan, F., Vedaldi, A., Metze, F.: Self-supervised object detection from audio-visual correspondence. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10575\u201310586 (2022)","DOI":"10.1109\/CVPR52688.2022.01032"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., Wu, J., Nie, L., Liu, Z.: Detecting and grounding multi-modal media manipulation and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"31_CR12","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS\u2013improving object detection with one line of code. In: IEEE International Conference on Computer Vision, pp. 5561\u20135569 (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Chugh, K., Gupta, P., Dhall, A., Subramanian, R.: Not made for each other-audio-visual dissonance-based deepfake detection and localization. In: The 28th ACM International Conference on Multimedia, pp. 439\u2013447 (2020)","DOI":"10.1145\/3394171.3413700"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: IEEE\/CVF International Conference on Computer Vision, pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"31_CR16","unstructured":"Nawhal, M., Mori, G.: Activity graph transformer for temporal action localization. arXiv preprint arXiv:2101.08540 (2021)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Bagchi, A., Mahmood, J., Fernandes, D., Sarvadevabhatla, R.K.: Hear me out: Fusional approaches for audio augmented temporal action localization. arXiv preprint arXiv:2106.14118 (2021)","DOI":"10.5220\/0010832700003124"},{"key":"31_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"31_CR19","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9856-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:00:46Z","timestamp":1766124046000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9856-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698554","9789819698561"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9856-1_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}