Aggregating concepts for event representation in lifelogging
Wang, Peng and Smeaton, Alan F.ORCID: 0000-0003-1028-8389
(2011)
Aggregating concepts for event representation in lifelogging.
In: Third International Workshop on Semantic Web Information Management (SWIM 2011), 12-16 June 2011, Athens, Greece.
ISBN 978-1-4503-0651-5
The performance of automatic detection of concepts in im-
age and video data has been improved to a satisfactory level
for some generic concepts like indoor, outdoor, faces, etc.
on high quality data from broadcast TV or movies. How-
ever it remains a challenge to apply this to interpreting the
high-level semantics of events as they occur in visual lifelogs
from wearable cameras. This is because poorer quality im-
age data and the activities of the wearer make it difficult to
automatically categorise them. In this paper, we propose an
interestingness-based semantic aggregation and representa-
tion algorithm, to tackle the problem of event management
and representation in visual lifelogging. Semantic concept
interestingness is calculated by fusing image-level concepts
which are then exploited to select a representation for the
semantic event correlated to various event topics. Experi-
mental results show the efficacy of our algorithm in fusing
semantics at the event level, and in selecting representations
for event management in visual lifelogging.