5 papers
ReXCam: Resource-Efficient, Cross-Camera Video Analytics at Scale
Samvit Jain, Xun Zhang, Yuhao Zhou +4
Enterprises are increasingly deploying large camera networks for video analytics. Many target applications entail a common problem template: searching for and tracking an object or…
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…
Scaling Video Analytics Systems to Large Camera Deployments
Samvit Jain, Ganesh Ananthanarayanan, Junchen Jiang +2
Driven by advances in computer vision and the falling costs of camera hardware, organizations are deploying video cameras en masse for the spatial monitoring of their physical prem…
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…
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…