SIGHT is a backpropagation-free TTA framework for WHAR that uses prototype-based surprise estimation and geometry-aware transition routing to adapt models using temporal structure in unlabeled streams.
Proceedings of the 42nd International Conference on Machine Learning , pages =
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
-
Temporal Structure Matters for Efficient Test-Time Adaptation in Wearable Human Activity Recognition
SIGHT is a backpropagation-free TTA framework for WHAR that uses prototype-based surprise estimation and geometry-aware transition routing to adapt models using temporal structure in unlabeled streams.