On the robustness of action recognition methods in compressed and pixel domain
| Autor: | Wojciech Samek, Jan Meyer, Sebastian Bosse, Vignesh Srinivasan, Serhan Gül, Cornelius Hellge, Thomas Schierl |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Pixel
business.industry Computer science 020207 software engineering Pattern recognition 02 engineering and technology Convolutional neural network Robustness (computer science) Histogram 0202 electrical engineering electronic engineering information engineering Action recognition Codec 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Practical implications Decoding methods |
| Zdroj: | EUVIP |
| DOI: | 10.1109/euvip.2016.7764584 |
| Popis: | This paper investigates the robustness of two state-of-theart action recognition algorithms: a pixel domain approach based on 3D convolutional neural networks (C3D) and a compressed domain approach requiring only partial decoding of the video, based on feature description using motion vectors and Fisher vector encoding (MV-FV). We study the robustness of the two algorithms against: (i) quality variations, (ii) changes in video encoding scheme, (iii) changes in resolutions. Experiments are performed on the HMDB51 dataset. Our main findings are that C3D is robust to variations of these parameters while the MV-FV is very sensitive. Hence, we consider C3D as a baseline method for our analysis. We also analyze the reasons behind these different behaviors and discuss their practical implications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|