Name: Shuxiao Ding
Type: User
Company: Mercedes-Benz & University of Bonn
Bio: PhD student at Mercedes-Benz and University of Bonn. Focus on Graph Neural Network applications in traffic scenes.
Location: Stuttgart & Nanjing
Shuxiao Ding's Projects
Offical implementation of ICCV2023 paper 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking.
Offical implementation of CVPR2024 paper ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association.
Official code for "EagerMOT: 3D Multi-Object Tracking via Sensor Fusion" [ICRA 2021]
Pytorch code for our ECCV 2018 paper "Graph R-CNN for Scene Graph Generation" and other papers
Implementation of Segnet, FCN, UNet and other models in Keras.
Models and examples built with TensorFlow
POWERBEV, a novel and elegant vision-based end-to-end framework that only consists of 2D convolutional layers to perform perception and forecasting of multiple objects in BEVs.
Sparse Blocks Networks
This repo contains all exercises and corresponding solutions for Sensor Fusion ND.
Computation using data flow graphs for scalable machine learning
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.