Abstract | ||
---|---|---|
In this paper, we present a novel approach to find informative and anomalous samples in videos exploiting the concept of typicality from information theory. In most video analysis tasks, selection of the most informative samples from a huge pool of training data in order to learn a good recognition model is an important problem. Furthermore, it is also useful to reduce the annotation cost, as it i... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TIP.2019.2910634 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Videos,Computational modeling,Anomaly detection,Entropy,Manuals,Labeling,Training | Information theory,Anomaly detection,Activity recognition,Markov process,Annotation,Active learning,Pattern recognition,Markov chain,Correlation,Artificial intelligence,Mathematics | Journal |
Volume | Issue | ISSN |
28 | 10 | 1057-7149 |
Citations | PageRank | References |
1 | 0.35 | 23 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jawadul H. Bappy | 1 | 75 | 5.64 |
Sujoy Paul | 2 | 75 | 7.66 |
Ertem Tuncel | 3 | 386 | 36.48 |
Amit K. Roy Chowdhury | 4 | 1153 | 73.96 |