Name
Abstract | ||
|---|---|---|
In order to promote the utilization of lifelog videos, an effective retrieval framework of the emotional scenes, which are considered to be important scenes, is proposed in this paper. The proposed method is based on facial expression recognition since the emotional scenes can be detected by taking the facial expressions into consideration. Most of conventional facial expression recognition methods require a large amount of training data to construct a recognition model. Adopting such methods for large-scale video databases is unrealistic because preparing sufficient training data requires considerable human efforts. We introduce an unsupervised machine learning framework to solve this issue by making it possible to construct a facial expression recognition model without any training data set. The proposed method is evaluated through an emotional scene detection experiment. A prototype of the emotional scene retrieval system based on the proposed emotional scene detection method is implemented. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/IIAI-AAI.2014.130 | IIAI-AAI |
Keywords | Field | DocType |
face recognition,object detection,unsupervised learning,video retrieval,emotional scene detection experiment,facial expression recognition model,large-scale video databases,lifelog videos,unsupervised emotional scene retrieval framework,unsupervised machine learning framework,clustering,ensemble learning,facial expression recognition,lifelog,training data,accuracy,clustering algorithms | Training set,Facial recognition system,Lifelog,Pattern recognition,Facial expression recognition,Computer science,Speech recognition,Unsupervised learning,Facial expression,Artificial intelligence,Cluster analysis,Ensemble learning | Conference |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hiroki Nomiya | 1 | 64 | 31.50 |
| Morikuni, A. | 2 | 0 | 0.34 |
| Teruhisa Hochin | 3 | 65 | 37.91 |