Clockwork Convnets for Video Semantic Segmentation.
Evan ShelhamerKate RakellyJudy HoffmanTrevor DarrellPublished in: ECCV Workshops (3) (2016)
Keyphrases
- semantic segmentation
- feed forward
- street scenes
- superpixels
- video sequences
- label transfer
- pascal voc
- scene classification
- weakly supervised
- video data
- conditional random fields
- video frames
- object detection
- object class
- bag of words
- object categories
- input image
- bayesian networks
- image set
- learning algorithm
- back propagation
- text classification
- active learning
- viewpoint
- artificial neural networks
- object recognition