Search Results for author:
Found 3 papers, 2 papers with code
Adaptive Resolution Residual Networks -- Generalizing Across Resolutions Easily and Efficiently
We construct ARRNs from Laplacian residuals, which serve as generic adaptive-resolution adapters for fixed-resolution layers, and which allow casting high-resolution ARRNs into low-resolution ARRNs at inference time by simply omitting high-resolution Laplacian residuals, thus reducing computational cost on low-resolution signals without compromising performance.
Understanding Dynamic Scenes using Graph Convolution Networks
We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera.
Ranked #1 on
Test results
on KITTI
Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks
Understanding on-road vehicle behaviour from a temporal sequence of sensor data is gaining in popularity.
