Max-AST: Combining Convolution, Local and Global Self-Attentions for Audio Event Classification.
Tony AlexSara AhmedArmin MustafaMuhammad AwaisPhilip JB JacksonPublished in: ICASSP (2024)
Keyphrases
- classification accuracy
- classification scheme
- pattern recognition
- training set
- feature selection
- classification method
- benchmark datasets
- training samples
- image classification
- multimedia
- feature vectors
- classification process
- classification systems
- machine learning
- image processing
- decision rules
- feature extraction
- support vector machine
- feature space
- multi modal
- decision trees
- text classification
- event detection
- pattern classification
- video sequences
- hidden markov models
- soccer video
- multiple classifier systems