A Comparative Study on the Use of Multi-label Classification Techniques for Concept-Based Video Indexing and Annotation.
Fotini MarkatopoulouVasileios MezarisIoannis KompatsiarisPublished in: MMM (1) (2014)
Keyphrases
- video indexing
- multi label
- image annotation
- video retrieval
- text categorization
- automatic image annotation
- semantic concepts
- multi label classification
- image classification
- video data
- video shots
- graph cuts
- visual content
- text classification
- class labels
- video analysis
- video surveillance
- multimedia content
- image collections
- video segments
- low level features
- active learning
- feature selection
- visual features
- retrieval systems
- visual concepts
- video content
- text documents
- knn
- image segmentation
- computer vision
- key frames
- semi supervised learning
- image representation
- k nearest neighbor
- multi modal
- image retrieval
- video sequences
- metadata