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.
BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Skeleton-based motion representations are robust for action localization and understanding for their invariance to perspective, lighting, and occlusion, compared with images. Yet, they are often ambiguous and incomplete when taken out of context, even for human annotators. As infants discern gestures before associating them with words, actions can be conceptualized before being grounded with labels. Therefore, we propose the first unsupervised pre-training framework, Boundary-Interior Decoding (BID), that partitions a skeleton-based motion sequence into discovered semantically meaningful pre-action segments. By fine-tuning our pre-training network with a small number of annotated data, we show results out-performing SOTA methods by a large margin.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.