Squeeze-Excitation Convolutional Recurrent Neural Networks for Audio-Visual Scene Classification.
Javier Naranjo-AlcazarSergi Perez-CastanosAaron Lopez-GarciaPedro ZuccarelloMaximo CobosFrancesc J. FerriPublished in: CoRR (2021)
Keyphrases
- audio visual
- recurrent neural networks
- scene classification
- object recognition
- multi modal
- biologically inspired
- natural scenes
- image classification
- visual words
- neural network
- visual information
- feed forward
- echo state networks
- image representation
- visual data
- bag of features
- artificial neural networks
- multimedia
- bag of words
- metadata
- computer vision
- higher order
- co occurrence
- search engine