papers

Publications (24)

cs.LG2023

PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection

Junjun Pan, Yixin Liu, Yizhen Zheng +1

Node-level graph anomaly detection (GAD) plays a critical role in identifying anomalous nodes from graph-structured data in various domains such as medicine, social networks, and e…

cs.CV2022

Diverse Dance Synthesis via Keyframes with Transformer Controllers

Junjun Pan, Siyuan Wang, Junxuan Bai +1

Existing keyframe-based motion synthesis mainly focuses on the generation of cyclic actions or short-term motion, such as walking, running, and transitions between close postures.…

cs.LG2025

A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models

Junjun Pan, Yu Zheng, Yue Tan +1

Graph anomaly detection (GAD) has attracted increasing attention in recent years for identifying malicious samples in a wide range of graph-based applications, such as social media…

cs.LG2019

Tucker Decomposition Network: Expressive Power and Comparison

Ye Liu, Junjun Pan, Michael Ng

Deep neural networks have achieved a great success in solving many machine learning and computer vision problems. The main contribution of this paper is to develop a deep network b…

math.NA2024

Block Diagonalization of Quaternion Circulant Matrices with Applications

Junjun Pan, Michael K. Ng

It is well-known that a complex circulant matrix can be diagonalized by a discrete Fourier matrix with imaginary unit . The main aim of this paper is to demonstrate tha…

cs.LG2025

A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection

Junjun Pan, Yixin Liu, Xin Zheng +4

Graph fraud detection (GFD) has rapidly advanced in protecting online services by identifying malicious fraudsters. Recent supervised GFD research highlights that heterophilic conn…

cs.CV2026

RAGMesh with FaME-G2E: Long-Form Text-Driven 3D Face Generation and Editing

Hao Li, Ju Dai, Feng Zhou +6

Text-driven 3D face generation and editing remains challenging due to the difficulty of translating long-form descriptions into fine-grained facial geometry. Existing methods prima…

cs.CV2025

AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation

Hao Li, Ju Dai, Feng Zhou +3

While 3D facial animation has made impressive progress, challenges still exist in realizing fine-grained stylized 3D facial expression manipulation due to the lack of appropriate d…

cs.CV2021

Nonnegative Low Rank Tensor Approximation and its Application to Multi-dimensional Images

Tai-Xiang Jiang, Michael K. Ng, Junjun Pan +1

The main aim of this paper is to develop a new algorithm for computing nonnegative low rank tensor approximation for nonnegative tensors that arise in many multi-dimensional imagin…

stat.ML2019

Orthogonal Nonnegative Tucker Decomposition

Junjun Pan, Michael K. Ng, Ye Liu +2

In this paper, we study the nonnegative tensor data and propose an orthogonal nonnegative Tucker decomposition (ONTD). We discuss some properties of ONTD and develop a convex relax…

cs.LG2019

Generalized Separable Nonnegative Matrix Factorization

Junjun Pan, Nicolas Gillis

Nonnegative matrix factorization (NMF) is a linear dimensionality technique for nonnegative data with applications such as image analysis, text mining, audio source separation and…

cs.CV2025

Non-Negative Reduced Biquaternion Matrix Factorization with Applications in Color Face Recognition

Jifei Miao, Junjun Pan, Michael K. Ng

Reduced biquaternion (RB), as a four-dimensional algebra highly suitable for representing color pixels, has recently garnered significant attention from numerous scholars. In this…

math.NA2026

Quaternion Maximum-Volume Submatrix Selection with Applications to Multichannel Imaging and Visual Data

Vsevolod Kliushev, Junjun Pan, Valentin Leplat

Low-rank approximation based on selected rows and columns is a useful alternative to singular value decompositions when the goal is an interpretable and compact matrix representati…

cs.CV2026

VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network

Zepeng Yang, Junxuan Bai, Hao Li +4

The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art (SOTA) HPE pipelines still…

cs.LG2026

CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection

Junjun Pan, Yixin Liu, Yu Zheng +3

Text-attributed graph fraud detection (TAGFD) plays a critical role in preventing fraudulent activities on online social and e-commerce platforms. However, to evade detection, frau…

cs.LG2021

Co-Separable Nonnegative Matrix Factorization

Junjun Pan, Michael K. Ng

Nonnegative matrix factorization (NMF) is a popular model in the field of pattern recognition. It aims to find a low rank approximation for nonnegative data M by a product of two n…

cs.LG2025

Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time

Junjun Pan, Yixin Liu, Chuan Zhou +3

Graph anomaly detection (GAD), which aims to detect outliers in graph-structured data, has received increasing research attention recently. However, existing GAD methods assume ide…

cs.SD2025

Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation

Hao Li, Ju Dai, Xin Zhao +3

In 3D speech-driven facial animation generation, existing methods commonly employ pre-trained self-supervised audio models as encoders. However, due to the prevalence of phonetical…

math.NA2024

Hierarchical Alternating Least Squares Methods for Quaternion Nonnegative Matrix Factorizations

Junjun Pan

In this report, we discuss a simple model for RGB color and polarization images under a unified framework of quaternion nonnegative matrix factorization (QNMF) and present a hierar…

math.NA2026

Hermitian Quaternion Toeplitz Matrices by Quaternion-valued Generating Functions

Xue-lei Lin, Michael K. Ng, Junjun Pan

In this paper, we study Hermitian quaternion Toeplitz matrices generated by quaternion-valued functions. We show that such generating function must be the sum of a real-valued func…

cs.CV2022

Separable Quaternion Matrix Factorization for Polarization Images

Junjun Pan, Michael K. Ng

Polarization is a unique characteristic of transverse wave and is represented by Stokes parameters. Analysis of polarization states can reveal valuable information about the source…

math.NA2026

A Provably-Correct and Robust Convex Model for Smooth Separable NMF

Junjun Pan, Valentin Leplat, Michael Ng +1

Nonnegative matrix factorization (NMF) is a linear dimensionality reduction technique for nonnegative data, with applications such as hyperspectral unmixing and topic modeling. NMF…

math.NA2026

QuatIca: Advanced Numerical Linear Algebra and Optimization for Quaternionic Matrices in Python

Valentin Leplat, Salman Ahmadi-Asl, Junjun Pan +2

Quaternion-valued representations provide a convenient way to model coupled multi-channel signals (e.g., RGB imagery, polarization data, vector fields, and multi-detector time seri…

cs.CR2025

Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection

Junjun Pan, Yixin Liu, Rui Miao +5

Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly autonomous in various safety-critical…