Name
Abstract | ||
|---|---|---|
Since people perform activities differently, to avoid overfitting, creating a general model with activity data of various users is required before the deployment for personal use. However, annotating a large amount of activity data is expensive and time-consuming. In this paper, we create a general model for activity recognition with a limited amount of labelled data. We combine Latent Dirichlet Allocation (LDA) and AdaBoost to jointly train a general activity model with partially labelled data. After that, when AdaBoost is used for online prediction, we combine it with graphical models (such as HMM and CRF) to exploit the temporal information in human activities to smooth out accidental misclassifications. Experiments on publicly available datasets show that we are able to obtain the accuracy of more than 90% with 1% labelled data. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1145/2802083.2808399 | IEEE International Semantic Web Conference |
Field | DocType | Citations |
Latent Dirichlet allocation,Activity recognition,AdaBoost,General activity,Computer science,Exploit,Artificial intelligence,Overfitting,Graphical model,Hidden Markov model,Machine learning | Conference | 3 |
PageRank | References | Authors |
0.39 | 9 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jiahui Wen | 1 | 21 | 2.37 |
| Mingyang Zhong | 2 | 25 | 5.17 |
| Jadwiga Indulska | 3 | 2092 | 146.96 |