Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition.
Taeoh KimHyeongmin LeeMyeongAh ChoHo Seong LeeDong Heon ChoSangyoun LeePublished in: CoRR (2020)
Keyphrases
- prior knowledge
- temporal information
- data sets
- learning process
- data collection
- background knowledge
- database
- learning algorithm
- video sequences
- multimedia data
- training examples
- data points
- knowledge discovery
- supervised learning
- learning tasks
- visual recognition
- video data
- recognition rate
- data mining techniques
- feature set
- data sources
- hidden markov models
- feature vectors
- object recognition
- feature extraction
- d objects
- image features
- image data
- low level
- unsupervised learning
- data analysis
- data structure
- key frames
- learning models
- invariant features
- decision trees