Search Results for author:
Found 6 papers, 1 papers with code
PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation
In this work, we address these challenges by leveraging the abundance of unlabeled data available.
Lite-HRNet Plus: Fast and Accurate Facial Landmark Detection
Lite-HRNet Plus achieves two improvements: a novel fusion block based on a channel attention and a novel output module with less computational intensity using multi-resolution feature maps.
Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching
Recently proposed DNN-based stereo matching methods that learn priors directly from data are known to suffer a drastic drop in accuracy in new environments.
Visualizing Color-wise Saliency of Black-Box Image Classification Models
Several techniques have been proposed to address this problem; one of which is RISE, which explains a classification result by a heatmap, called a saliency map, which explains the significance of each pixel.
Team O2AS at the World Robot Summit 2018: An Approach to Robotic Kitting and Assembly Tasks using General Purpose Grippers and Tools
We propose a versatile robotic system for kitting and assembly tasks which uses no jigs or commercial tool changers.
Real-Time 6D Object Pose Estimation on CPU
BPT which is an efficient tree-based data structures for a large number of templates and template matching on rearranged feature maps where nearby features are linearly aligned accelerate the pose estimation.
