CQT-based Convolutional Neural Networks for Audio Scene Classification.
Thomas LidyAlexander SchindlerPublished in: DCASE (2016)
Keyphrases
- scene classification
- convolutional neural networks
- object recognition
- natural scenes
- convolutional network
- image classification
- biologically inspired
- indoor outdoor
- image representation
- multimedia
- visual words
- scene recognition
- bag of features
- spatial layout
- visual information
- bag of words
- scene representation
- natural images
- multi instance multi label learning
- cross modal
- multi modal
- image quality
- image retrieval
- similarity measure
- image segmentation