Multimodal video concept classification based on convolutional neural network and audio feature combination.
Berkay SelbesMustafa SertPublished in: SIU (2017)
Keyphrases
- convolutional neural network
- multimedia
- feature vectors
- face detection
- audio video
- pattern recognition
- feature set
- visual data
- multi modal
- video data
- story segmentation
- support vector machine
- feature space
- audio visual
- neural network
- digital video
- feature values
- classifier combination
- classification accuracy
- multimodal information
- multimodal fusion
- visual speech
- single modality
- audio files
- video content analysis
- video classification
- audio stream
- brain image analysis
- audio features
- scene change detection
- machine learning
- video streams
- text classification
- video sequences
- audio content
- feature selection
- audio visual content
- decision trees
- acoustic signals
- support vector
- training set
- cross modal
- image features
- image classification
- multimedia data
- event detection
- semantic concepts