Motion-based AI video detectors exploit motion biases in evaluation datasets and drop to near-random performance on rebalanced data, while frequency-based detectors remain robust.
Expanding language-image pretrained models for general video recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
An SNN-based detector combining multi-channel pseudo-event residuals with frozen semantic features reaches 93.14% mean accuracy on unseen generators under the Pika-trained GenVideo protocol.
citing papers explorer
-
Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection
Motion-based AI video detectors exploit motion biases in evaluation datasets and drop to near-random performance on rebalanced data, while frequency-based detectors remain robust.
-
Detecting AI-Generated Videos with Spiking Neural Networks
An SNN-based detector combining multi-channel pseudo-event residuals with frozen semantic features reaches 93.14% mean accuracy on unseen generators under the Pika-trained GenVideo protocol.