An autoencoder with joint-disentangled embeddings and vector-quantized temporal patches segments skeleton sequences into actions without labels, beating prior unsupervised methods on HuGaDB, LARa, and two of three BABEL subsets.
Unified fully and timestamp supervised temporal action segmentation via sequence to se- quence translation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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
-
Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation
An autoencoder with joint-disentangled embeddings and vector-quantized temporal patches segments skeleton sequences into actions without labels, beating prior unsupervised methods on HuGaDB, LARa, and two of three BABEL subsets.