arXiv Computer Vision
MOTIF: Person-of-Interest Deepfake Detection Beyond 3DMM Coefficients
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 9
Stop My Dancing! Understanding, Detecting and Attributing Motion-Aware Deepfake Videos
The paper introduces Motion‑Aware Deepfake (MAD) videos, a new class of deepfakes generated by pose‑guided diffusion models that can animate entire human figures. To study this threat, the authors build the first MAD‑specific benchmark with 1.5 million frames from 1,363 real and 30,122 synthetic videos, and analyze the subtle high‑frequency artifacts and spectral fingerprints that arise from limited input frames. Leveraging these insights, they propose MoDA, a defense framework that combines spatial semantics with steganalysis‑rich frequency features, achieving high detection and attribution accuracy across in‑distribution, cross‑dataset, and zero‑shot scenarios, and demonstrating robustness against adaptive attacks.
arXiv AI
Jul 14
On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
arXiv:2410. 19553v2 Announce Type: replace-cross Abstract: This paper explores the impact of occlusions in video action detection.
arXiv Computer Vision
Oct 5
Interpretable Deepfake Detection in Videos via Explicit Forensic Features and Temporal Modeling
This paper presents an interpretable deepfake detection framework that explicitly encodes physically grounded forensic cues to analyze spatially and temporally coherent facial features in video sequences. The method transforms videos into identity-consistent facial trajectories, segments them into fixed-length temporal windows, and represents each frame with 68 structured descriptors across photometric, textural, geometric, and compression domains. These descriptors are processed by an LSTM to capture temporal dependencies, achieving strong F1-scores on four benchmark datasets and demonstrating robust cross-dataset generalization.
arXiv Machine Learning
Aug 31
What Do Interaction Representations Actually Measure? Pre-Event Separability in Weakly-Supervised Violence Detection
The paper investigates whether detailed articulated human pose provides more discriminative power than coarse spatial relationships for early violence detection. By fixing the downstream pipeline and comparing five interaction representations—including bounding‑box geometry, handcrafted pose analogues, enriched pose descriptors, and a learned joint encoder—the study finds that pose‑based representations do not outperform coarse geometry. When visual encoders are frozen and evaluated on larger datasets, person‑crop appearance and whole‑frame context outperform geometry, but cropping to interacting people offers no advantage over encoding the entire frame. The authors further demonstrate that pre‑onset frames contain source‑related artifacts (e.g., title cards, watermarks) that contribute significantly to discrimination, suggesting that benchmark performance may reflect these artifacts rather than true event evidence.
arXiv Computer Vision
Oct 7
CCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance Footage
arXiv:2610.07939v1 Announce Type: new Abstract: Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both hum...
arXiv Computer Vision
Oct 7
HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic data
arXiv:2610.08433v1 Announce Type: new Abstract: Modern action recognition models rely on video transformers pretrained on massive collections of web-crawled videos, such as Kinetics-700. However, the...