A Multi-modal Approach to Single-modal Visual Place Classification.
Tomoya IwasakiKanji TanakaKenta TsukaharaPublished in: CoRR (2023)
Keyphrases
- multi modal
- single modality
- cross modal
- multi modality
- video search
- audio visual
- semantic concepts
- image classification
- classification accuracy
- text classification
- image annotation
- high dimensional
- feature space
- medical images
- high level
- multimedia
- machine learning
- low level
- visual information
- feature vectors
- face recognition