Abstract     Description     Claims     Drawing  

Fully convolutional networks for semantic segmentation   [0010] 
Multi-scale context aggregation by dilated convolutions   [0011] 
Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs   [0012] 
Rethinking atrous convolution for semantic image segmentation   [0012] 
Pyramid scene parsing network   [0012] 
Feature space optimization for semantic video segmentation   [0015] 
Semantic video CNNs through representation warping   [0016] 
Clockwork convnets for video semantic segmentation   [0017] 
Learning phrase representations using rnn encoder-decoder for statistical machine translation   [0035] 
Long short-term memory   [0035] 
Delving deeper into convolutional networks for learning video representations   [0038] 
Convolutional Istm network: A machine learning approach for precipitation nowcasting   [0038] 
Convolutional gated recurrent networks for video segmentation   [0040] 
Microsoft coco: Common objects in context   [0061] 
Deep residual learning for image recognition   [0069] 
Flownet: Learning optical flow with convolutional networks   [0074] 
Playing for benchmarks   [0082] 
Dense point trajectories by gpu-accelerated large displacement optical flow   [0099] 
The cityscapes dataset for semantic urban scene understanding   [0109]