agoodge

LUNAR

LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks

APAE

Robustness of Autoencoders for Anomaly Detection Under Adversarial Impact

ARES

ARES: Locally Adaptive Reconstruction-based Anomaly Scoring

AccidentPredictor

An accurate traffic accident predictor can potentially save lives. I hereby described the creation and deployment of such a model using scikit-learn, Google Maps API, Flask and PythonAnywhere.

accidentRiskMap

agoodge.github.io

Website

GDN

Implementation code for the paper "Graph Neural Network-Based Anomaly Detection in Multivariate Time Series" (AAAI 2021)

OpenSTL

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

PointCLIP_V2

[ICCV 2023] PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

ROAD-ACCIDENTS-PREDICTION-AND-CLASSIFICATION

Final Year Project on Road Accident Prediction using user's Location,weather conditions by applying machine Learning concepts.

ST-SSL

ST-SSL (STSSL): Spatio-Temporal Self-Supervised Learning for Traffic Flow Forecasting/Prediction

UniST

Official implementation for "UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction" (KDD 2024)

UrbanGPT

[KDD'2024] "UrbanGPT: Spatio-Temporal Large Language Models"

ZLaP

Code for Label Propagation for Zero-shot Classification with Vision-Language Models (CVPR2024)