A Neural-Symbolic Approach for Explanation Generation Based on Sub-concept Detection: An Application of Metric Learning for Low-Time-Budget Labeling.
Johannes RaboldPublished in: Künstliche Intell. (2022)
Keyphrases
- multiple kernel learning
- metric learning
- multi task
- concept detection
- semi supervised learning
- video retrieval
- learning tasks
- semi supervised
- learning problems
- concept learning
- kernel methods
- distance metric
- dimensionality reduction
- distance function
- unsupervised learning
- active learning
- pairwise
- semantic concepts
- high level
- image processing
- video shots
- labeled data
- image segmentation
- feature space
- kernel function
- machine learning
- computer vision