IEEE

Learning Developmental Age From 3D Infant Kinetics Using Adaptive Graph Neural Networks

Abstract: Reliable methods for the neurodevelopmental assessment of infants are essential for early detection of problems that may need prompt interventions. Spontaneous motor activity, or ‘kinetics’, ...
IEEE

A Graph Neural Network-Based Recommendation System for Product Manufacturing Information in 3D-CAD Models

Abstract: Product Manufacturing Information is the key element in the digital transformation of manufacturing. It facilitates the transition from 2D drawing-based workflows to 3D model-based workflows ...
GitHub

Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation

DovSG constructs a Dynamic 3D Scene Graph and leverages task decomposition with large language models, enabling localized updates of the 3D scene graphs during interactive exploration. This assists ...
GitHub

Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images

This repository contains the code for the SCRSSG project. Our code is tested with Pytorch 2.5.0 and CUDA 11.8 on Ubuntu 20.04. # setup git clone https://github.com ...