MTLE: A Multitask Learning Encoder of Visual Feature Representations for Video and Movie Description.
Oliver NinaWashington GarciaScott ClouseAlper YilmazPublished in: CoRR (2018)
Keyphrases
- multitask learning
- feature representations
- gaussian processes
- image representation
- multi task
- high level
- generative model
- feature representation
- learning tasks
- video data
- multi task learning
- semi supervised
- video sequences
- labeled data
- visual information
- low level
- visual features
- video frames
- classifier ensemble
- supervised learning
- key frames
- learning algorithm