Score: 0

Next-Frame Feature Prediction for Multimodal Deepfake Detection and Temporal Localization

Published: November 13, 2025 | arXiv ID: 2511.10212v1

By: Ashutosh Anshul , Shreyas Gopal , Deepu Rajan and more

Potential Business Impact:

Finds fake videos by predicting what happens next.

Business Areas:
Image Recognition Data and Analytics, Software

Recent multimodal deepfake detection methods designed for generalization conjecture that single-stage supervised training struggles to generalize across unseen manipulations and datasets. However, such approaches that target generalization require pretraining over real samples. Additionally, these methods primarily focus on detecting audio-visual inconsistencies and may overlook intra-modal artifacts causing them to fail against manipulations that preserve audio-visual alignment. To address these limitations, we propose a single-stage training framework that enhances generalization by incorporating next-frame prediction for both uni-modal and cross-modal features. Additionally, we introduce a window-level attention mechanism to capture discrepancies between predicted and actual frames, enabling the model to detect local artifacts around every frame, which is crucial for accurately classifying fully manipulated videos and effectively localizing deepfake segments in partially spoofed samples. Our model, evaluated on multiple benchmark datasets, demonstrates strong generalization and precise temporal localization.

Page Count
12 pages

Category
Computer Science:
CV and Pattern Recognition