Selected Space-Time Based Methods for Action Recognition
| Autor: | Kamil Wereszczyński, Konrad Wojciechowski, Artur Bąk, Sławomir Wojciechowski, Rafał Wyciślok, Marek Kulbacki, Jakub Segen |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
business.industry
Computer science Space time Deep learning 02 engineering and technology Machine learning computer.software_genre Work (electrical) 020204 information systems Encoding (memory) 0202 electrical engineering electronic engineering information engineering Action recognition 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Zdroj: | Intelligent Information and Database Systems ISBN: 9783662493892 ACIIDS (2) |
| DOI: | 10.1007/978-3-662-49390-8_41 |
| Popis: | A survey on very recent and efficient space-time methods for action recognition is presented. We select the methods with highest accuracy achieved on the challenging datasets such as: HMDB51, UCF101 and Hollywood2. This research focuses on two main space-time based approaches, namely the hand-crafted and deep learning features. We intuitively explain the selected pipelines and review good practices used in state-of-the-art methods including the best descriptors, encoding methods, deep architectures and classifiers. The best methods were chosen and some of them were explained in more details. Furthermore, we conclude how to improve the methods in speed as well as in accuracy and propose directions for further work. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|