End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding.
Effrosyni MavroudiDivya BhaskaraShahin SefatiHaider AliRené VidalPublished in: WACV (2018)
Keyphrases
- energy function
- fine grained
- end to end
- sparse coding
- random field models
- sparse codes
- discriminative power
- random fields
- markov random field
- object category recognition
- dictionary learning
- unsupervised learning
- natural images
- coarse grained
- image classification
- sparse representation
- segmentation method
- image segmentation
- linear combination
- discriminative dictionary
- image representation
- access control
- generative model
- feature space
- multiscale
- visual words
- image patches
- high dimensional
- autoregressive
- image processing
- test images
- conditional random fields
- parameter estimation
- segmentation algorithm
- semi supervised
- video sequences
- feature selection
- bag of words
- maximum entropy
- high dimensional data
- non stationary
- text classification
- image quality