Master Thesis

Exploring Graph Neural Networks for Video Action Segmentation

Work default illustration

Supervisor/s

Information

  • Started: 15/02/2022
  • Finished: 30/05/2023

Description

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

UPCommons

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)