{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:50:01Z","timestamp":1761929401074,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819537280","type":"print"},{"value":"9789819537297","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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\/978-981-95-3729-7_24","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:44:24Z","timestamp":1761929064000},"page":"289-300","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting Feature Gating and\u00a0Injection For Multi-modal Manipulation Detection and\u00a0Grounding"],"prefix":"10.1007","author":[{"given":"Jiazhen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changtao","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nenghai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Afchar, D., Nozick, V., Yamagishi, J., Echizen, I.: Mesonet: a compact facial video forgery detection network. In: WIFS, pp.\u00a01\u20137. IEEE (2018)","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"24_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B.: Flamingo: a visual language model for few-shot learning. NeurIPS 35, 23716\u201323736 (2022)","journal-title":"NeurIPS"},{"key":"24_CR3","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Dou, Z.Y., et\u00a0al.: An empirical study of training end-to-end vision-and-language transformers. In: CVPR, pp. 18166\u201318176 (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Gehrmann, S., Strobelt, H., Rush, A.M.: GLTR: statistical detection and visualization of generated text. In: ACL, pp. 111\u2013116 (2019)","DOI":"10.18653\/v1\/P19-3019"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Khattar, D., Goud, J.S., Gupta, M., Varma, V.: MVAE: multimodal variational autoencoder for fake news detection. In: WWW, pp. 2915\u20132921 (2019)","DOI":"10.1145\/3308558.3313552"},{"key":"24_CR7","unstructured":"Kim, W., Son, B., Kim, I.: VILT: Vision-and-language transformer without convolution or region supervision. In: ICML, pp. 5583\u20135594. PMLR (2021)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Face x-ray for more general face forgery detection. In: CVPR, pp. 5001\u20135010 (2020)","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"24_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102037","volume":"102","author":"Q Li","year":"2024","unstructured":"Li, Q., et al.: Towards multimodal disinformation detection by vision-language knowledge interaction. Inf. Fusion 102, 102037 (2024)","journal-title":"Inf. Fusion"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Liu, F., Wang, Y., Wang, T., Ordonez, V.: Visual news: benchmark and challenges in news image captioning. In: EMNLP, pp. 6761\u20136771 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.542"},{"key":"24_CR11","unstructured":"Liu, H., et al.: Unified frequency-assisted transformer framework for detecting and grounding multi-modal manipulation. arXiv preprint arXiv:2309.09667 (2023)"},{"key":"24_CR12","unstructured":"Liu, Y.: Roberta: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 364 (2019)"},{"key":"24_CR13","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, Y., Yan, J., Liu, W.: Generalizing face forgery detection with high-frequency features. In: CVPR, pp. 16317\u201316326 (2021)","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Miao, C., et al.: Towards generalizable and robust face manipulation detection via bag-of-feature. In: VCIP, pp.\u00a01\u20135. IEEE (2021)","DOI":"10.1109\/VCIP53242.2021.9675331"},{"issue":"1","key":"24_CR16","first-page":"71","volume":"4","author":"C Miao","year":"2021","unstructured":"Miao, C.: Learning forgery region-aware and id-independent features for face manipulation detection. T-BIOM 4(1), 71\u201384 (2021)","journal-title":"T-BIOM"},{"key":"24_CR17","first-page":"1039","volume":"18","author":"C Miao","year":"2023","unstructured":"Miao, C.: F 2 trans: High-frequency fine-grained transformer for face forgery detection. TIFS 18, 1039\u20131051 (2023)","journal-title":"TIFS"},{"key":"24_CR18","first-page":"3008","volume":"17","author":"C Miao","year":"2022","unstructured":"Miao, C., Tan, Z., Chu, Q., Yu, N., Guo, G.: Hierarchical frequency-assisted interactive networks for face manipulation detection. TIFS 17, 3008\u20133021 (2022)","journal-title":"TIFS"},{"key":"24_CR19","unstructured":"Nakamura, K., Levy, S., Wang, W.Y.: Fakeddit: a new multimodal benchmark dataset for fine-grained fake news detection. In: LREC, pp. 6149\u20136157 (2020)"},{"key":"24_CR20","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: ECCV, pp. 86\u2013103. Springer (2020)","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"24_CR21","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"24_CR22","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? NeurIPS 34, 12116\u201312128 (2021)","journal-title":"NeurIPS"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., et al.: Generalized intersection over union: a metric and a loss for bounding box regression. In: CVPR, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Rossler, A., et al.: Faceforensics++: learning to detect manipulated facial images. In: ICCV, pp. 1\u201311 (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., Liu, Z.: Detecting and grounding multi-modal media manipulation. In: CVPR, pp. 6904\u20136913 (2023)","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., Wu, J., Nie, L., Liu, Z.: Detecting and grounding multi-modal media manipulation and beyond. TPAMI (2024)","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Singhal, S., et al.: Spotfake+: a multimodal framework for fake news detection via transfer learning (student abstract). In: AAAI, vol.\u00a034, pp. 13915\u201313916 (2020)","DOI":"10.1609\/aaai.v34i10.7230"},{"key":"24_CR28","first-page":"2183","volume":"29","author":"Z Tan","year":"2022","unstructured":"Tan, Z., Yang, Z., Miao, C., Guo, G.: Transformer-based feature compensation and aggregation for deepfake detection. SPL 29, 2183\u20132187 (2022)","journal-title":"SPL"},{"key":"24_CR29","unstructured":"Wang, J., et al.: Exploiting modality-specific features for multi-modal manipulation detection and grounding. arXiv preprint arXiv:2309.12657 (2023)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: EANN: event adversarial neural networks for multi-modal fake news detection. In: KDD, pp. 849\u2013857 (2018)","DOI":"10.1145\/3219819.3219903"},{"key":"24_CR31","unstructured":"Zellers, R., et al.: Defending against neural fake news. NeurIPS 32 (2019)"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Zhuang, W., et al.: UIA-ViT: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection. In: ECCV, pp. 391\u2013407. Springer (2022)","DOI":"10.1007\/978-3-031-20065-6_23"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Zhuang, W., et al.: Towards intrinsic common discriminative features learning for face forgery detection using adversarial learning. In: ICME, pp.\u00a01\u20136. IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859586"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3729-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:44:41Z","timestamp":1761929081000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3729-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819537280","9789819537297"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3729-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xuzhou","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":"31 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icig.csig.org.cn\/2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}