Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition.
Taeoh KimHyeongmin LeeMyeongAh ChoHo Seong LeeDong Heon ChoSangyoun LeePublished in: ECCV Workshops (2) (2020)
Keyphrases
- prior knowledge
- data collection
- human activities
- training data
- knowledge discovery
- learned models
- data analysis
- learning algorithm
- data structure
- data sets
- temporal information
- unsupervised learning
- feature extraction
- learning process
- reinforcement learning
- video sequences
- image data
- database
- supervised learning
- data mining techniques
- recognition rate
- active learning
- xml documents
- data points
- learning tasks
- learning models
- affine invariant
- extracted features
- invariant features
- data sources