Semantic Concept Annotation of Consumer Videos at Frame-Level Using Audio.
Junwei LiangQin JinXixi HeGang YangJieping XuXirong LiPublished in: PCM (2014)
Keyphrases
- image understanding
- image annotation
- semantic concepts
- automatic image annotation
- computer vision
- image collections
- multimedia
- concept detection
- visual concepts
- visual content
- semantic concept detection
- higher level
- multi modal
- visual information
- visual features
- semantic similarity
- image retrieval
- key frames
- semantic information
- natural language processing
- video sequences
- metadata