all AI news
Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors
Feb. 26, 2024, 5:46 a.m. | Peter Gr\"onquist, Yufan Ren, Qingyi He, Alessio Verardo, Sabine S\"usstrunk
cs.CV updates on arXiv.org arxiv.org
Abstract: Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person's expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Some newer methods employ optical flow models to capture this temporal aspect, but they are computationally expensive. In contrast, we propose using the related but often ignored Motion Vectors (MVs) and Information Masks (IMs) from the H.264 video codec, to detect temporal …
abstract analyze arxiv cs.ai cs.cv current deepfake deepfakes deep learning detection detection methods fake flow identity media movements optical optical flow person temporal type vectors video
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote