Social Role Discovery in Human Events

We deal with the problem of recognizing social roles played by people in an event. Social roles are governed by human interactions, and form a fundamental component of human event description. We focus on a weakly supervised setting, where we are provided different videos belonging to an event class...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 2475 - 2482
Main Authors Ramanathan, Vignesh, Bangpeng Yao, Li Fei-Fei
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2013
Subjects
Approximation methods
Context
Face recognition
Feature extraction
Training
Videos
YouTube
Online AccessGet full text
ISSN1063-6919
1063-6919
DOI10.1109/CVPR.2013.320

Cover

More Information
Summary:We deal with the problem of recognizing social roles played by people in an event. Social roles are governed by human interactions, and form a fundamental component of human event description. We focus on a weakly supervised setting, where we are provided different videos belonging to an event class, without training role labels. Since social roles are described by the interaction between people in an event, we propose a Conditional Random Field to model the inter-role interactions, along with person specific social descriptors. We develop tractable variational inference to simultaneously infer model weights, as well as role assignment to all people in the videos. We also present a novel YouTube social roles dataset with ground truth role annotations, and introduce annotations on a subset of videos from the TRECVID-MED11 [1] event kits for evaluation purposes. The performance of the model is compared against different baseline methods on these datasets.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.320