Abstract | ||
---|---|---|
Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing. However, human-generated data inherently suffer from distribution shift in semi-supervised learning due to the diverse biological conditions and behavior patterns of humans. To address this problem, we propose a generic distributionally robust model for semi-supervised learning on distributionally shifted data. Considering both the discrepancy and the consistency between the labeled data and the unlabeled data, we learn the latent features that reduce person-specific discrepancy and preserve task-specific consistency. We evaluate our model in a variety of people-centric recognition tasks on real-world datasets, including intention recognition, activity recognition, muscular movement recognition and gesture recognition. The experiment results demonstrate that the proposed model outperforms the state-of-the-art methods. |
Year | Venue | Field |
---|---|---|
2018 | THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Activity recognition,Semi-supervised learning,Computer science,Gesture recognition,Movement recognition,Artificial intelligence,Labeled data,Machine learning |
DocType | Volume | Citations |
Journal | abs/1811.05299 | 2 |
PageRank | References | Authors |
0.35 | 13 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kaixuan Chen | 1 | 47 | 4.80 |
Lina Yao | 2 | 981 | 93.63 |
Dalin Zhang | 3 | 22 | 3.53 |
Xiaojun Chang | 4 | 1585 | 76.85 |
Guodong Long | 5 | 655 | 47.27 |
Sen Wang | 6 | 477 | 37.24 |