Audio Pyramid Transformer with Domain Adaption for Weakly Supervised Sound Event Detection and Audio Classification.
Yifei XinDongchao YangYuexian ZouPublished in: INTERSPEECH (2022)
Keyphrases
- event detection
- weakly supervised
- soccer video
- decision trees
- audio visual
- superpixels
- activity recognition
- text classification
- object class
- visual information
- topic models
- unsupervised learning
- machine learning
- image classification
- domain specific
- object detection
- feature vectors
- feature space
- feature selection
- multi modal
- text categorization
- supervised learning
- semi supervised
- training set
- multiscale
- feature extraction