Trending:

Multi-modal Deepfake Detection and Localization with FPN-Transformer

arXiv — cs.CV•Wednesday, November 12, 2025 at 5:00:00 AM

The introduction of the FPN-Transformer framework marks a significant advancement in the fight against deepfake technology, which poses serious risks to digital trust. Traditional unimodal detection methods have struggled to effectively identify and localize manipulated content due to their inability to utilize cross-modal correlations. The FPN-Transformer addresses these gaps by employing self-supervised models like WavLM for audio and CLIP for video, allowing for a more nuanced analysis of deepfake content. Experimental validation has confirmed the framework's effectiveness, achieving a notable score of 0.7535 in the IJCAI'25 DDL-AV benchmark. This development is crucial as it enhances the reliability of media verification processes, thereby fostering greater trust in digital communications.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

Recommended Readings

arXiv — cs.CV2 days ago

Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning

PositiveArtificial Intelligence

The paper titled 'Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning' addresses the challenges of class-incremental learning (CIL) in vision-language models like CLIP. It introduces a two-stage framework called DMC, which separates the adaptation of the vision encoder from the optimization of textual soft prompts. This approach aims to mitigate classifier bias and maintain cross-modal alignment, enhancing the model's ability to learn new categories without forgetting previously acquired knowledge.

Read full article

via arXiv — cs.CV

arXiv — cs.CV2 days ago

CLIPPan: Adapting CLIP as A Supervisor for Unsupervised Pansharpening

PositiveArtificial Intelligence

The article presents CLIPPan, an unsupervised pansharpening framework that utilizes CLIP, a visual-language model, as a supervisor. This approach addresses the challenges faced by supervised pansharpening methods, particularly the domain adaptation issues arising from the disparity between simulated low-resolution training data and real-world high-resolution scenarios. The framework is designed to improve the understanding of the pansharpening process and enhance the model's ability to recognize various image types, ultimately setting a new state of the art in unsupervised full-resolution pans…

Read full article

via arXiv — cs.CV

arXiv — cs.CV2 days ago

NP-LoRA: Null Space Projection Unifies Subject and Style in LoRA Fusion

PositiveArtificial Intelligence

The article introduces NP-LoRA, a novel framework for Low-Rank Adaptation (LoRA) fusion that addresses the issue of interference in existing methods. Traditional weight-based merging often leads to one LoRA dominating another, resulting in degraded fidelity. NP-LoRA utilizes a projection-based approach to maintain subspace separation, thereby enhancing the quality of fusion by preventing structural interference among principal directions.

Read full article

via arXiv — cs.CV