Motion-guided spatiotemporal multitask feature discrimination for self-supervised video representation learning.
Shuai BiZhengping HuHehao ZhangJirui DiZhe SunPublished in: Pattern Recognit. (2024)
Keyphrases
- multi task
- space time
- video representation
- learning tasks
- spatial and temporal
- learning algorithm
- multi task learning
- multitask learning
- active learning
- spatio temporal
- learning problems
- prior knowledge
- supervised learning
- generative model
- video content
- motion analysis
- moving objects
- video analysis
- dynamic textures
- training data