Search Results for author: Dongwoon Bai

Found 4 papers, 1 papers with code

DVIO: Depth aided visual inertial odometry for RGBD sensors

no code implementations20 Oct 2021 Abhishek Tyagi, Yangwen Liang, Shuangquan Wang, Dongwoon Bai

Specifically, we propose methods to use the depth measurement using one-dimensional (1D) feature parameterization as well as three-dimensional (3D) feature parameterization.

Frame

GSANet: Semantic Segmentation with Global and Selective Attention

no code implementations14 Feb 2020 Qing-Feng Liu, Mostafa El-Khamy, Dongwoon Bai, Jungwon Lee

The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a novel selective attention that deploys a condensation and diffusion mechanism to aggregate the multi-scale contextual information from the extracted deep features.

Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.