We propose a source-free domain adaptation framework that refines pseudo labels using task-domain agreement and adapts CLIP with uncertainty-aware optimization based on proposed Tsallis mutual information.

We proposed novel SKETCH method that extracts high level feature transforming a raw four-dimensional online skeleton point coordinates data to graph images.

We propose a novel time encoding approach that learns effective reference points and incorporates temporal and intervariable dependencies to enhance classification performance on irregular multivariate time series.