Publication

Understanding event boundaries for egocentric activity recognition from photo-streams

Conference Article

Conference

ICPR International Workshops and Challenges (ICPR-IWC)

Edition

2021

Pages

334-347

Doc link

https://doi.org/10.1007/978-3-030-68796-0_24

File

Download the digital copy of the doc pdf document

Authors

Abstract

The recognition of human activities captured by a wearable photo-camera is especially suited for understanding the behavior of a person. However, it has received comparatively little attention with respect to activity recognition from fixed cameras.In this work, we propose to use segmented events from photo-streams as temporal boundaries to improve the performance of activity recognition. Furthermore, we robustly measure its effectiveness when images of the evaluated person have been seen during training, and when the person is completely unknown during testing. Experimental results show that leveraging temporal boundary information on pictures of seen people improves all classification metrics, particularly it improves the classification accuracy up to 85.73%.

Categories

computer vision, pattern recognition.

Scientific reference

A. Cartas, E. Talavera, P. Radeva and M. Dimiccoli. Understanding event boundaries for egocentric activity recognition from photo-streams, 2021 ICPR International Workshops and Challenges, 2021, Milan, Italy (Virtual), in Pattern Recognition. ICPR International Workshops and Challenges. Proceedings, Part III, Vol 12663 of Lecture Notes in Computer Science, pp. 334-347, 2021, Springer International Publishing.