Duke Pratt School of Engineering

Mapping Behavior with Machine Learning

By transforming movement into data, Timothy Dunn is reshaping how scientists can study behavior and the brain.
IEEE

Yolo- Driven Machine Learning System for Enhanced Object Recognition and Automation

Abstract: This paper presents an object recognition system that uses machine learning to improve automation in industries. Using deep learning models, the system achieves high accuracy in real-time ...
GitHub

State Space Model Meets Transformer: A New Paradigm for 3D Object Detection

DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features ...
IEEE

Machine Learning-Based Object Movement Prediction Method Using Occupancy Grid Maps from Roadside Sensor

Abstract: For automated vehicles, wide-ranging and real-time detection of the surrounding environment and accurate recognition of objects, including pedestrians, vehicles, and their movements, are ...
GitHub

CTR-Gait: Semantic-Aware Contrastive Learning for Fine-Grained Gait Emotion Recognition

This repository contains the official PyTorch implementation of the paper: "CTR-Gait: Semantic-Aware Contrastive Learning for Fine-Grained Gait Emotion Recognition" (Submitted to IEEE Transactions on ...