Violent Scene Detection of Film Videos Based on Multi-Task Learning of Temporal-Spatial Features.
Zhengxin ZhengWei ZhongLong YeLi FangQin ZhangPublished in: MIPR (2021)
Keyphrases
- spatial features
- multi task learning
- video sequences
- multi task
- spatial information
- geometric properties
- spatial objects
- gaussian processes
- learning problems
- learning tasks
- transfer learning
- pattern discovery
- spatial relationships
- image sequences
- high order
- machine learning
- hyperspectral
- spatial databases
- dynamic textures
- arbitrary shape
- spatial relations
- theoretical analysis
- moving objects
- inductive learning
- geometric constraints
- spatial data
- image data
- feature selection
- learning algorithm