Implicit visual concept modeling in image / video annotation.
Klimis S. NtalianisAnastasios D. DoulamisNicolas TsapatsoulisPublished in: ARTEMIS@ACM Multimedia (2010)
Keyphrases
- visual concepts
- video annotation
- image content
- image collections
- object categories
- image features
- video content
- multiscale
- input image
- semantic gap
- visual content
- image data
- semantic concepts
- learning tasks
- image representation
- visual data
- computer vision
- image annotation
- image retrieval
- image classification
- high resolution
- machine learning
- object recognition
- image database
- visual information
- visual features
- image matching
- multi modal
- low level features
- low level
- image regions
- object classes
- video analysis
- training data
- positive examples
- web images
- high level
- metadata
- spatial information