A database for fine grained activity detection of cooking activities

While activity recognition is a current focus of research the challenging problem of fine-grained activity recognition is largely overlooked. We thus propose a novel database of 65 cooking activities, continuously recorded in a realistic setting. Activities are distinguished by fine-grained body mot...

Full description

Saved in:
Bibliographic Details
Published in2012 IEEE Conference on Computer Vision and Pattern Recognition pp. 1194 - 1201
Main Authors Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2012
Subjects
Estimation
Feature extraction
Humans
Joints
Surveillance
Trajectory
Online AccessGet full text
ISBN9781467312264
1467312266
ISSN1063-6919
1063-6919
DOI10.1109/CVPR.2012.6247801

Cover

More Information
Summary:While activity recognition is a current focus of research the challenging problem of fine-grained activity recognition is largely overlooked. We thus propose a novel database of 65 cooking activities, continuously recorded in a realistic setting. Activities are distinguished by fine-grained body motions that have low inter-class variability and high intra-class variability due to diverse subjects and ingredients. We benchmark two approaches on our dataset, one based on articulated pose tracks and the second using holistic video features. While the holistic approach outperforms the pose-based approach, our evaluation suggests that fine-grained activities are more difficult to detect and the body model can help in those cases. Providing high-resolution videos as well as an intermediate pose representation we hope to foster research in fine-grained activity recognition.
ISBN:9781467312264
1467312266
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2012.6247801