Senior Machine Learning Scientist@PicsArt, PhD candidate@Computer Vision Group (CVG), University of Bonn
ADA-Track. Offical implementation of CVPR2024 paper ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association.
1433DMOTFormer. Offical implementation of ICCV2023 paper 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking.
96adhd-copilot. A Claude Code custom skill that serves as an ADHD-friendly companion assistant.
25PowerBEV. 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.
1dsx0511.github.io. My personal website.
1