Τίτλος:
An adversarial semi-supervised approach for action recognition from pose information
Γλώσσες Τεκμηρίου:
Αγγλικά
Περίληψη:
The collection of video data for action recognition is very susceptible to measurement bias; the equipment used, camera angle and environmental conditions are all factors that majorly affect the distribution of the collected dataset. Inevitably, training a classifier that can successfully generalize to new data becomes a very hard problem, since it is impossible to gather general enough training sets. Recent approaches in the literature attempt to solve this problem by augmenting a given training set, with synthetic data, so as to better represent the global distribution of the covariates. However, these approaches are limited because they essentially involve hand-crafted data synthesizers, which are typically hard to implement and problem specific. In this work, we propose a different approach to tackling the above issues, which relies on the combination of two techniques: pose extraction, and domain adaptation as a means to improve the generalization capabilities of classifiers. We show that adapted skeletal representations can be retrieved automatically in a semi-supervised setting and these help to generalize classifiers to new forms of measurement bias. We empirically validate our approach for generalizing across different camera angles. © 2020, Springer-Verlag London Ltd., part of Springer Nature.
Συγγραφείς:
Pikramenos, G.
Mathe, E.
Vali, E.
Vernikos, I.
Papadakis, A.
Spyrou, E.
Mylonas, P.
Περιοδικό:
Neural Computing and Applications
Εκδότης:
Springer Science and Business Media Deutschland GmbH
Λέξεις-κλειδιά:
Cameras, Action recognition; Data synthesizers; Domain adaptation; Environmental conditions; Generalization capability; Global distribution; Measurement bias; Pose information, Classification (of information)
DOI:
10.1007/s00521-020-05162-5
