Name
Abstract | ||
|---|---|---|
The MediaEval 2015 Affective Impact of Movies task challenged participants to automatically detect video content that depicts violence, or predict the affective impact that video content will have on viewers. In this paper, we describe our system and discuss the performance results obtained in this task. We adopt our recently proposed Trajectory Based Covariance (TBC) descriptor to depict the motion information. Besides that, other features including audio, scene, color and appearance are also utilized in our system. To combine these features, a late fusion strategy is employed. Our results show that the trajectory based motion feature can achieve very competitive performances, furthermore the combination with audio, scene, color and appearance features can improve the overall performance. |
Year | Venue | Field |
|---|---|---|
2015 | MediaEval | Computer vision,Artificial intelligence,Affect (psychology),Geography,Trajectory,Covariance |
DocType | Citations | PageRank |
Conference | 1 | 0.34 |
References | Authors | |
4 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yun Yi | 1 | 29 | 4.48 |
| Hanli Wang | 2 | 865 | 69.10 |
| Bowen Zhang | 3 | 80 | 4.49 |
| Jian Yu | 4 | 1 | 0.34 |