English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The emergence of artificial intelligence-generated content (AIGC) has raisedconcerns about the authenticity of multimedia content in various fields.However, existing research for forgery content detection has focused mainly onbinary classification tasks of complete videos, which has limited applicabilityin industrial settings. To address this gap, we propose UMMAFormer, a noveluniversal transformer framework for temporal forgery localization (TFL) thatpredicts forgery segments with multimodal adaptation. Our approach introduces aTemporal Feature Abnormal Attention (TFAA) module based on temporal featurereconstruction to enhance the detection of temporal differences. We also designa Parallel Cross-Attention Feature Pyramid Network (PCA-FPN) to optimize theFeature Pyramid Network (FPN) for subtle feature enhancement. To evaluate theproposed method, we contribute a novel Temporal Video Inpainting Localization(TVIL) dataset specifically tailored for video inpainting scenes. Ourexperiments show that our approach achieves state-of-the-art performance onbenchmark datasets, including Lav-DF, TVIL, and Psynd, significantlyoutperforming previous methods. The code and data are available athttps://github.com/ymhzyj/UMMAFormer/.

UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization