SOURCE-LINKED INTELLIGENCE

See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Unsupervised action segmentation aims to discover latent action categories and their temporal organization without action annotations. Optimal transport-based methods provide structured frame-to-action assignments, however, their pseudo-label quality is fundamentally conditioned on the representation space used to construct the transport cost. We argue that reliable OT pseudo-labeling requires a representation geometry that is simultaneously sensitive to discriminative action changes and coherent along local temporal progressions. Based on this insight, we propose SpecT-OT, a spectral-temporal

Read original source ↗ Open in workspace

recordType

paper

region

Global