Transaction

jmetaB032b2f773980a1daae1e0fbab2422a2299b07e94d569bae877551d092b77da3150@104e04f4dc7bbb58b675a0be8ec8a2392cd828cadc0c1b85347e2d4ab003150erss.itemmetarss.netMH<item> <title>Video Inpainting Localization with Contrastive Learning</title> <link>https://arxiv.org/abs/2406.17628</link> <description>arXiv:2406.17628v1 Announce Type: cross Abstract: Deep video inpainting is typically used as malicious manipulation to remove important objects for creating fake videos. It is significant to identify the inpainted regions blindly. This letter proposes a simple yet effective forensic scheme for Video Inpainting LOcalization with ContrAstive Learning (ViLocal). Specifically, a 3D Uniformer encoder is applied to the video noise residual for learning effective spatiotemporal forensic features. To enhance the discriminative power, supervised contrastive learning is adopted to capture the local inconsistency of inpainted videos through attracting/repelling the positive/negative pristine and forged pixel pairs. A pixel-wise inpainting localization map is yielded by a lightweight convolution decoder with a specialized two-stage training strategy. To prepare enough training samples, we build a video object segmentation dataset of 2500 videos with pixel-level annotations per frame. Extensive experimental results validate the superiority of ViLocal over state-of-the-arts. Code and dataset will be available at https://github.com/multimediaFor/ViLocal.</description> <guid isPermaLink="false">oai:arXiv.org:2406.17628v1</guid> <category>cs.CV</category> <category>cs.CR</category> <arxiv:announce_type>cross</arxiv:announce_type> <dc:rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0/</dc:rights> <dc:creator>Zijie Lou, Gang Cao, Man Lin</dc:creator> </item>