Unsupervised per-video action segmentation via deep kernel approximation of frame distributions using NTKs and MMD achieves competitive benchmark results.
The language of actions: Recovering the syntax and semantics of goal-directed human activities,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep kernel video approximation for unsupervised action segmentation
Unsupervised per-video action segmentation via deep kernel approximation of frame distributions using NTKs and MMD achieves competitive benchmark results.