DPLM: A Deep Perceptual Spatial-Audio Localization Metric.
Pranay ManochaAnurag KumarBuye XuAnjali MenonIsrael D. GebruVamsi K. IthapuPaul CalamiaPublished in: CoRR (2021)
Keyphrases
- geographic information systems
- spatial data
- spatial databases
- cross modal
- spatial relationships
- multimedia
- signal processing
- distance measure
- multi modal
- audio stream
- computer vision
- audio files
- audio signals
- perceptual grouping
- audio visual
- metric learning
- metric space
- spatial and temporal
- visual information
- distance metric
- euclidean distance
- knn
- low level
- spatio temporal