Master Thesis

Action segmentation of untrimmed videos via a hierarchical unsupervised approach

Work default illustration



  • Started: 15/02/2022


This project aims at segmenting untrimmed videos by using a graph-based hierarchical approach in an unsupervised fashion.

The work is under the scope of the following projects:

  • GREAT: Beyond Graph Neural Networks: Joint graph topology learning and graph-based inference for computer vision (web)