Visual-Semantic Alignment Across Domains Using a Semi-Supervised Approach.
Angelo CarraggiMarcella CorniaLorenzo BaraldiRita CucchiaraPublished in: ECCV Workshops (6) (2018)
Keyphrases
- semi supervised
- semi supervised learning
- semantic information
- semantic content
- visual information
- labeled data
- application domains
- active learning
- unlabeled data
- semantic knowledge
- low level
- multi view
- semantic web
- visual features
- cross domain
- semi supervised clustering
- domain knowledge
- pairwise
- semantic space
- word alignment
- high level
- domain ontology
- visual perception
- semantic features
- visual concepts
- image alignment
- semantically relevant
- semantic concepts
- low level features
- semantic annotation
- real world
- supervised learning
- feature space
- natural language
- co training
- subspace learning
- background knowledge
- semi supervised classification
- semantically related
- ontology matching
- machine learning