Autoencoder-based anomaly detection in Rayleigh optical fiber sensors
Structural pattern recognition and intermediate representations
Video-to-video dynamics transfer with deep generative models
| Full text | |
| Author(s): |
Sousa e Santos, Anderson Carlos
;
Pedrini, Helio
;
Tremeau, A
;
Farinella, GM
;
Braz, J
Total Authors: 5
|
| Document type: | Journal article |
| Source: | PROCEEDINGS OF THE 14TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 5; v. N/A, p. 10-pg., 2019-01-01. |
| Abstract | |
The demand for automatic systems for action recognition has increased significantly due to the development of surveillance cameras with high sampling rates, low cost, small size and high resolution. These systems can effectively support human operators to detect events of interest in video sequences, reducing failures and improving recognition results. In this work, we develop and analyze a method to learn two-dimensional (2D) representations from videos through an autoencoder framework. A multi-stream network is used to incorporate spatial and temporal information for action recognition purposes. Experiments conducted on the challenging UCF101 and HMDB51 data sets indicate that our representation is capable of achieving competitive accuracy rates compared to the literature approaches. (AU) | |
| FAPESP's process: | 17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events |
| Grantee: | Anderson de Rezende Rocha |
| Support Opportunities: | Research Projects - Thematic Grants |