Understanding Event Boundaries for Egocentric Activity Recognition from Photo-Streams

Alejandro Cartas, Estefania Talavera, Petia Radeva, Mariella Dimiccoli

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review


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%.
Original languageEnglish
Title of host publicationPattern Recognition. ICPR International Workshops and Challenges
Subtitle of host publicationVirtual Event, January 10–15, 2021, Proceedings, Part III
Publication statusPublished - 21 Feb 2021
Externally publishedYes

Publication series

NameLecture notes in computer science


Dive into the research topics of 'Understanding Event Boundaries for Egocentric Activity Recognition from Photo-Streams'. Together they form a unique fingerprint.

Cite this