Scenes-Objects-Actions: A Multi-task, Multi-label Video Dataset.
Jamie RayHeng WangDu TranYufei WangMatt FeiszliLorenzo TorresaniManohar PaluriPublished in: ECCV (14) (2018)
Keyphrases
- multi label
- multi task
- learning tasks
- multi label classification
- text categorization
- multi task learning
- video dataset
- image classification
- learning problems
- graph cuts
- multi label learning
- text classification
- image annotation
- feature selection
- computer vision
- action recognition
- class labels
- transfer learning
- video data
- data sets
- supervised learning
- kernel methods
- image representation
- natural language processing
- multimedia
- learning algorithm
- machine learning
- data mining