Multiple temporal scale aggregate network for temporal action segmentation

doi:10.1016/j.patcog.2025.112165

Multiple temporal scale aggregate network for temporal action segmentation

2025-07-23

0

PRE

AI

DOI：10.1016/j.patcog.2025.112165

Original

Original request for help

Save

Abstract

En 中文

• We show the potential of initial predictions in multi-stage refinement to enhance TAS through rich multi-scale temporal cues. • We propose the MTSAN that is designed based on a U-Net-style architecture to utilize temporal dependencies at various scales. • Experimental results validate the effectiveness of utilizing multi-scale temporal dependencies in the initial stage.

Keywords:

multi-stage refinement

temporal attention network

U-Net-style architecture

multi-scale temporal cues

target-aware synthesis

Multiple temporal scale aggregate network for temporal action segmentation

Abstract

Journal

Organization