Publication

Leveraging triplet loss for unsupervised action segmentation

Conference Article

Conference

CVPR Workshop on Learning with Limited Labelled Data (L3D-IVU)

Edition

2023

Pages

4922-4930

Doc link

https://doi.ieeecomputersociety.org/10.1109/CVPRW59228.2023.00520

File

Download the digital copy of the doc pdf document

Abstract

In this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data. Our method is a deep metric learning approach rooted in a shallow network with a triplet loss operating on similarity distributions and a novel triplet selection strategy that effectively models temporal and semantic priors to discover actions in the new representational space. Under these circumstances, we successfully recover temporal boundaries in the learned action representations with higher quality compared with existing unsupervised approaches. The proposed method is evaluated on two widely used benchmark datasets for the action segmentation task and it achieves competitive performance by applying a generic clustering algorithm on the learned representations.

Categories

computer vision, pattern recognition.

Author keywords

Video Understanding, Action Segmentation, Deep Metric Learning

Scientific reference

E.B. Bueno Benito, B. Tura and M. Dimiccoli. Leveraging triplet loss for unsupervised action segmentation, 2023 CVPR Workshop on Learning with Limited Labelled Data, 2023, Vancouver, Canadá, pp. 4922-4930, IEEE.