End-to-end 3D CNN with separable convolutions for efficient simultaneous spatial-temporal video object and action segmentation.
Segnet: A deep convo- lutional encoder-decoder architecture for image segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Efficient 3D CNN for Action/Object Segmentation in Video
End-to-end 3D CNN with separable convolutions for efficient simultaneous spatial-temporal video object and action segmentation.