ChunjingXiao

DiffAD

Imputation-based Time-Series Anomaly Detection with Conditional Weight-Incremental Diffusion Models, KDD 2023

DeepSeg

A deep learning-based activity segmentation framework for activity recognition using WiFi Channel State Information (CSI).

CsiGAN

An implementation for our paper: CsiGAN: Robust Channel State Information-based Activity Recognition with GANs (IEEE Internet of Things Journal, 2019), which is the semi-supervised Generative Adversarial Network (GAN) for Channel State Information (CSI) -based activity recognition.

WiTeacher

Mean Teacher-based Cross-Domain Activity Recognition using WiFi Signals, IoTJ 2023

SFTSeg

Self-Supervised Few-Shot Time-series Segmentation for Activity Recognition, TMC 2022

ConGNN

Controlled graph neural networks with denoising diffusion for anomaly detection, Expert Systems with Applications 2023

TwitterPopularity

An implementation for our paper: Time sensitivity-based popularity prediction for online promotion on Twitter (Information Sciences, 2020). This is an extended Latent Factor Model that can predict popularity values of tweets on Twitter when they are published at various times. The data includes Twitter user profiles and tweet information (tweetID, Text, published time, userID, retweetNumber).

CFAD

Counterfactual Graph Learning for Anomaly Detection on Attributed Networks, IEEE TKDE 2023

Awesome-Graph-Anomaly-Detection

CAGAD

chunjingxiao.github.io

Personal homepage

CLAR

TwitterFacebook

Find users who have accounts on both Twitter and Facebook, and identify cross-posts which mean two posts are actually containing the same information.