SOURCE-LINKED INTELLIGENCE

Boundary Voting Network for Ambiguity-Aware Timestamp-Supervised Action Segmentation

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Timestamp-supervised action segmentation aims to segment and classify actions in untrimmed videos with a random frame annotated per action. Precisely localizing action boundaries from timestamp annotations is crucial for this setting, as it enables generating framewise pseudo-labels and applying the well-explored fully-supervised training. However, prevailing methods struggle with intrinsic uncertainty in boundary localization due to less discriminative features in action-transiting regions. This imprecise boundary estimation significantly reduces the stability and reliability of the generated

Read original source ↗ Open in workspace

recordType

paper

region

Global