A multi-modal approach to detect inappropriate cartoon video contents using deep learning networks.
Mohammad Yasser ChutturA. NazurallyPublished in: Multim. Tools Appl. (2022)
Keyphrases
- multi modal
- deep learning
- video content
- video search
- unsupervised learning
- video data
- video streams
- machine learning
- video frames
- audio visual
- video retrieval
- video sequences
- weakly supervised
- text classification
- high dimensional
- key frames
- image annotation
- model selection
- image content
- object class
- semantic concepts
- high level
- information retrieval