Understanding event boundaries for egocentric activity recognition from photo-streams
Document typeConference report
Rights accessOpen Access
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%.
The final publication is available at link.springer.com
CitationCartas, A. [et al.]. Understanding event boundaries for egocentric activity recognition from photo-streams. A: 2021 ICPR International Workshops and Challenges (ICPR-IWC). "Proceeding of 2021 ICPR International Workshops and Challenges (ICPR-IWC)". Springer Nature, 2021, p. 334-347. DOI 10.1007/978-3-030-68796-0_24.