Showing cs.CVShow all
3 papers · 1 filter
cs.CV2018
Inter-BMV: Interpolation with Block Motion Vectors for Fast Semantic Segmentation on Video
Samvit Jain, Joseph E. Gonzalez
Models optimized for accuracy on single images are often prohibitively slow to run on each frame in a video. Recent work exploits the use of optical flow to warp image features for…
cs.CV2018
Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video
Samvit Jain, Xin Wang, Joseph Gonzalez
We present Accel, a novel semantic video segmentation system that achieves high accuracy at low inference cost by combining the predictions of two network branches: (1) a reference…
cs.CV2018
Fast Semantic Segmentation on Video Using Block Motion-Based Feature Interpolation
Samvit Jain, Joseph E. Gonzalez
Convolutional networks optimized for accuracy on challenging, dense prediction tasks are prohibitively slow to run on each frame in a video. The spatial similarity of nearby video…