An encoder-only Video ViT with self-supervised masked video pretraining matches or beats specialized traffic anomaly detectors and is more efficient.
Scaling egocentric vision: The epic-kitchens dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Simplifying Traffic Anomaly Detection with Video Foundation Models
An encoder-only Video ViT with self-supervised masked video pretraining matches or beats specialized traffic anomaly detectors and is more efficient.