{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:14:39Z","timestamp":1761894879257,"version":"build-2065373602"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210195","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["2S-DGM\n                    <sup>4<\/sup>\n                    : A Two-Stage Framework for Detecting and Grounding Multi-Modal Media Manipulation"],"prefix":"10.1109","author":[{"given":"Junjie","family":"Wu","sequence":"first","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yumeng","family":"Fu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Yu","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Gong","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohong","family":"Fu","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219903"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679826"},{"key":"ref4","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2022","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00096"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01024"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.36227\/techrxiv.170723324.44685515\/v1","article-title":"Detecting multimedia generated by large ai models: A survey","author":"Lin","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.316"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29618"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681089"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102037"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-024-10316-x"},{"key":"ref15","article-title":"Fast-detectGPT: Efficient zero-shot detection of machine-generated text via conditional probability curvature","author":"Bao","year":"2024","journal-title":"ICLR"},{"key":"ref16","first-page":"24950","article-title":"Detectgpt: Zero-shot machine-generated text detection using probability curvature","author":"Mitchell","year":"2023","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512163"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.311"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512258"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679519"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00389"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511968"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01452"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592271"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25670"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.37"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02245-x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01240"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3625100"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102037"},{"key":"ref34","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref35","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"article-title":"Gaussian error linear units (gelus)","year":"2016","author":"Hendrycks","key":"ref36"},{"key":"ref37","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"CVPR"},{"key":"ref38","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref41","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021","journal-title":"ICML"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref42"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref44","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210195.pdf?arnumber=11210195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:38:18Z","timestamp":1761889098000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210195","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}