Table 8 Statistics for COGNIMUSE Database (Hollywood movies and GWW) annotated with Audio-Visual events per event category. Subcategories with numerous instances but with small duration
Frequent audio and visual events with small duration | ||
|---|---|---|
Category/subcategory | Instances | Dur. (min) |
Voice: shouting | 204 | 8 |
Voice: crying | 101 | 7 |
Voice: breathing | 102 | 18.55 |
Movement: footsteps | 165 | 11.51 |
Social signals: door opening closing | 114 | 2.18 |
General facial actions: smile | 115 | 3.72 |
General body mov.: running | 109 | 5.56 |
General body mov: turn | 216 | 4.79 |
Gestures: wave hands | 116 | 3.97 |