Discovering Video Clusters from Visual Features and Noisy Tags.
Arash VahdatGuang-Tong ZhouGreg MoriPublished in: ECCV (6) (2014)
Keyphrases
- visual features
- semantic concepts
- key frames
- video shots
- keywords
- visual content
- visual similarity
- visual information
- visual data
- image classification
- motion features
- human actions
- content based video retrieval
- image retrieval
- image annotation
- image search
- low level features
- video database
- video content
- video retrieval
- bag of features
- audio features
- semantic gap
- low level
- video data
- video streams
- video sequences
- textual features
- visual appearance
- image collections
- web images
- video clips
- visual concepts
- multimedia
- metadata
- global features
- video frames
- visual descriptors
- multimedia data
- visual patterns
- multi modal
- semantic similarity
- space time
- image representation
- high level