Carregant...
Fitxers
Tipus de document
ArticleVersió
Versió acceptadaData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/144211
Towards social pattern characterization in egocentric photo-streams
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
Following the increasingly popular trend of social interaction analysis in egocentric vision, this article presents a comprehensive pipeline for automatic social pattern characterization of a wearable photo-camera user. The proposed framework relies merely on the visual analysis of egocentric photo-streams and consists of three major steps. The first step is to detect social interactions of the user where the impact of several social signals on the task is explored. The detected social events are inspected in the second step for categorization into different social meetings. These two steps act at event-level where each potential social event is modeled as a multi-dimensional time-series, whose dimensions correspond to a set of relevant features for each task; finally, LSTM is employed to classify the time-series. The last step of the framework is to characterize social patterns of the user. Our goal is to quantify the duration, the diversity and the frequency of the user social relations in various social situations. This goal is achieved by the discovery of recurrences of the same people across the whole set of social events related to the user. Experimental evaluation over EgoSocialStyle - the proposed dataset in this work, and EGO-GROUP demonstrates promising results on the task of social pattern characterization from egocentric photo-streams.
Matèries (anglès)
Citació
Citació
AGHAEI, Maedeh, DIMICCOLI, Mariella, CANTON-FERRER, Cristian, RADEVA, Petia. Towards social pattern characterization in egocentric photo-streams. _Computer Vision and Image Understanding_. 2018. Vol. 171, núm. 104-117. [consulta: 14 de gener de 2026]. ISSN: 1077-3142. [Disponible a: https://hdl.handle.net/2445/144211]