Stacked auto-encoders based visual features for speech/music classification.
Arvind KumarSandeep Singh SolankiMahesh ChandraPublished in: Expert Syst. Appl. (2022)
Keyphrases
- visual features
- image classification
- audio features
- visual information
- acoustic features
- image categorization
- image search
- image retrieval
- classification accuracy
- image annotation
- visual appearance
- speech music discrimination
- visual content
- low level
- machine learning
- feature set
- feature extraction
- semantic concepts
- bag of words
- bag of features
- feature space
- image collections
- visual data
- audio visual
- semantic features
- video shots
- visual properties
- content based video retrieval
- visual and textual features
- visual words
- speech recognition
- text classification
- object recognition
- feature selection
- classification method
- semantic gap
- relevance feedback
- feature vectors
- training set
- textual features
- keywords
- face recognition
- textual and visual features
- computer vision