Convolutional sparse coding for capturing high speed video content.
Ana SerranoElena GarcesDiego GutierrezBelén MasiáPublished in: CoRR (2018)
Keyphrases
- sparse coding
- video content
- high speed
- natural images
- sparse representation
- dictionary learning
- video data
- image classification
- linear combination
- video streams
- video sequences
- unsupervised learning
- image representation
- generative model
- video frames
- feature space
- video retrieval
- image patches
- frame rate
- key frames
- visual words
- deep belief networks
- higher order
- object detection
- high dimensional
- multiscale
- input image
- prior knowledge
- object recognition
- high quality
- visual concepts
- face recognition