Multi-modal Attention Mechanisms in LSTM and Its Application to Acoustic Scene Classification.
Teng ZhangKailai ZhangJi WuPublished in: INTERSPEECH (2018)
Keyphrases
- multi modal
- scene classification
- object recognition
- natural scenes
- biologically inspired
- image classification
- indoor outdoor
- image representation
- visual words
- visual attention
- cross modal
- image annotation
- multi modality
- bag of features
- high dimensional
- uni modal
- single modality
- image processing
- visual recognition
- semantic concepts
- image retrieval
- multiscale