Title | ||
---|---|---|
A Continuous Learning Framework for Activity Recognition Using Deep Hybrid Feature Models |
Abstract | ||
---|---|---|
Most of the research on human activity recognition has focused on learning a static model, considering that all the training instances are labeled and present in advance, while in streaming videos new instances continuously arrive and are not labeled. Moreover, these methods generally use application- specific hand-engineered and static feature models, which are not suitable for continuous learnin... |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/TMM.2015.2477242 | IEEE Transactions on Multimedia |
Keywords | Field | DocType |
Training,Videos,Computational modeling,Machine learning,Feature extraction,Data models,Labeling | Instance-based learning,Semi-supervised learning,Active learning (machine learning),Computer science,Unsupervised learning,Feature (machine learning),Artificial intelligence,Computer vision,Stability (learning theory),Pattern recognition,Feature extraction,Feature learning,Machine learning | Journal |
Volume | Issue | ISSN |
17 | 11 | 1520-9210 |
Citations | PageRank | References |
20 | 0.59 | 49 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mahmudul Hasan | 1 | 158 | 10.17 |
Amit K. Roy-Chowdhury | 2 | 530 | 30.76 |