An unsupervised GNN-based system reaches 82.66% mAP on the DSV Diving dataset by detecting curvature inflections of learned embedding norms, matching supervised baselines.
The au- thors encoded the action pattern into curvatures on the global timescale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
UTAL-GNN: Unsupervised Temporal Action Localization using Graph Neural Networks
An unsupervised GNN-based system reaches 82.66% mAP on the DSV Diving dataset by detecting curvature inflections of learned embedding norms, matching supervised baselines.