Probability Estimates for Multi-class Classification by Pairwise Coupling
The Journal of Machine Learning Research
International Journal of Computer Vision
International Journal of Computer Vision
Slice&Dice: Recognizing Food Preparation Activities Using Embedded Accelerometers
AmI '09 Proceedings of the European Conference on Ambient Intelligence
Preprocessing techniques for context recognition from accelerometer data
Personal and Ubiquitous Computing
Human activity analysis: A review
ACM Computing Surveys (CSUR)
Action recognition by dense trajectories
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Rapid Speaker Adaptation Using Clustered Maximum-Likelihood Linear Basis With Sparse Training Data
IEEE Transactions on Audio, Speech, and Language Processing
Feature learning for activity recognition in ubiquitous computing
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Accelerometer Localization in the View of a Stationary Camera
CRV '12 Proceedings of the 2012 Ninth Conference on Computer and Robot Vision
Egocentric activity monitoring and recovery
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Combining embedded accelerometers with computer vision for recognizing food preparation activities
Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing
Hi-index | 0.00 |
Recognizing complex activities is a challenging research problem, particularly in the presence of strong variability in the way activities are performed. Food preparation activities are prime examples, involving many different utensils and ingredients as well as high inter-person variability. Recognition models need to adapt to users in order to robustly account for differences between them. This paper presents three methods for user-adaptation: combining classifiers that were trained separately on generic and user-specific data, jointly training a single support vector machine from generic and user-specific data, and a weighted K-nearest-neighbor formulation with different probability mass assigned to generic and user-specific samples. The methods are evaluated on video and accelerometer data of people preparing mixed salads. A combination of generic and user-specific models considerably increased activity recognition accuracy and was shown to be particularly promising when data from only a limited number of training subjects was available.