Publication details

Towards Efficient Human Action Retrieval based on Triplet-Loss Metric Learning

Investor logo
Authors

KICO Iris SEDMIDUBSKÝ Jan ZEZULA Pavel

Year of publication 2022
Type Article in Proceedings
Conference 33rd International Conference on Database and Expert Systems Applications (DEXA)
MU Faculty or unit

Faculty of Informatics

Citation
Web https://link.springer.com/chapter/10.1007/978-3-031-12423-5_18
Doi http://dx.doi.org/10.1007/978-3-031-12423-5_18
Keywords human motion data;skeleton sequences;action similarity;action retrieval;triplet-loss learning;LSTM
Description Recent pose-estimation methods enable digitization of human motion by extracting 3D skeleton sequences from ordinary video recordings. Such spatio-temporal skeleton representation offers attractive possibilities for a wide range of applications but, at the same time, requires effective and efficient content-based access to make the extracted data reusable. In this paper, we focus on content-based retrieval of pre-segmented skeleton sequences of human actions to identify the most similar ones to a query action. We mainly deal with the extraction of content-preserving action features, which are learned using the triplet-loss approach in an unsupervised way. Such features are (1) effective as they achieve a similar retrieval quality as the features learned in a supervised way, and (2) of a fixed size which enables the application of indexing structures for efficient retrieval.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info