Abstract | ||
---|---|---|
The success of recognizing periodic actions in single-person-simple-background datasets, such as Weizmann and KTH, has created a need for more difficult datasets to push the performance of action recognition systems. We identify the significant weakness in systems based on popular descriptors by creating a synthetic dataset using Weizmann dataset. Experiments show that introducing complex backgrounds, stationary or dynamic, into the video causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning the system or selecting better interest points. Instead, we show that the problem lies at the cuboid level and must be addressed by modifying cuboids. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICCVW.2011.6130433 | 2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCV WORKSHOPS) |
Keywords | Field | DocType |
support vector machine,support vector machines,accuracy,degradation,image recognition | Computer vision,Computer science,Action recognition,Support vector machine,Artificial intelligence,Cuboid,Vocabulary,Machine learning,Corruption | Conference |
Volume | Issue | Citations |
2011 | 1 | 3 |
PageRank | References | Authors |
0.42 | 16 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Syed Zain Masood | 1 | 92 | 5.80 |
Adarsh Nagaraja | 2 | 21 | 1.65 |
Nazar Khan | 3 | 15 | 6.38 |
Jiejie Zhu | 4 | 378 | 21.71 |
Marshall F. Tappen | 5 | 1901 | 89.34 |