Weakly-supervised Automated Audio Captioning via text only training.
Theodoros KouzelisVassilis KatsourosPublished in: CoRR (2023)
Keyphrases
- weakly supervised
- semantic attributes
- object detectors
- topic models
- object class
- superpixels
- relation extraction
- semi supervised
- text mining
- training samples
- training examples
- keywords
- training set
- object detection
- object recognition
- visual information
- long range
- automatic extraction
- multi class
- object categories
- supervised learning