Extracting key frames from first-person videos in the common space of multiple sensors.
Yujie LiAtsunori KanemuraHideki AsohTaiki MiyanishiMotoaki KawanabePublished in: ICIP (2017)
Keyphrases
- key frames
- multiple sensors
- video content
- video data
- instructional videos
- video clips
- video retrieval
- video sequences
- data fusion
- video frames
- feature vectors
- multi sensor
- sensor data
- visual features
- video representation
- video shots
- video summarization
- space time
- video segments
- video abstraction
- object tracking
- sensor fusion
- video summaries
- keywords
- video database
- multiple cameras
- machine learning