Fine-granularity semantic video annotation: An approach based on automatic shot level concept detection and object recognition.
Vanessa El-KhouryMartin JerglerGetnet Abebe BayouDavid CoquilHarald KoschPublished in: Int. J. Pervasive Comput. Commun. (2013)
Keyphrases
- video annotation
- video shots
- semantic concepts
- sports video
- object recognition
- low level features
- video data
- video content
- automatic annotation
- visual concepts
- higher level
- video retrieval
- key frames
- video indexing
- visual features
- low level
- video analysis
- video sequences
- multi modal
- semantic similarity
- semantic information
- computer vision
- high level
- semi automatic
- multimedia
- mid level
- semantic gap
- video database
- visual content
- video clips
- object categories
- video frames
- object detection
- information extraction
- semantic content
- generative model
- learning tasks
- multimedia data
- video streams