Video vision-language models (VLMs) have strong semantic understanding, yet remain unreliable at precise temporal grounding. Existing gains from explicitly aligning video frames with absolute time suggest that VLMs may already encode accurate temporal locations internally but lose precision when expressing them as time...
Zi-Xuan Chen, De-Peng Wang, Wei Chen et al.· 0 citations
Red is the first framework to use scale-wise token predictability to guide forensic evidence aggregation across intermediate reconstruction states, and shows strong robustness to common image degradations, supporting the value of reconstruction evolution for generalizable AI-generated image detection.
Wen-Peng Mu, Jun-Shan Jin, Tan-Feng Sun et al.· 0 citations
The proliferation of hyper-realistic AI-generated images poses significant threats to digital information integrity and forensic accountability. Existing detection methodologies, however, face three critical bottlenecks: vulnerability to real-world distortions such as social media compression, inadequate specialization...
Wen-Peng Mu, Qiang Xu, Yi-Ning Zhang et al.· IEEE Transactions on Informa...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.