Stearns and Poletti present a technically impressive study that aims to uncover a deeper understanding of microsaccade function: their role in perceptual modulation and the associated temporal ...
This repository provides code and workflows to test several state-of-the-art vehicle detection deep learning algorithms —including YOLOX, SalsaNext, RandLA-Net, and VoxelRCNN— on a Flash Lidar dataset ...
Abstract: Single-view 3D human pose estimation (HPE) based on Graph Convolutional Networks currently suffers from problems such as insufficient feature representation and depth ambiguity. To address ...
Abstract: Weakly supervised 3D semantic segmentation has proven effective in alleviating the heavy dependence on dense annotations by generating high-quality pseudo-labels. However, due to the scene ...
This is the official implementation of "GotenNet: Rethinking Efficient 3D Equivariant Graph Neural Networks" published at ICLR 2025. GotenNet introduces a novel framework for modeling 3D molecular ...