Peng Wu

Learning Causal Temporal Relation and Feature Discrimination for Anomaly Detection

2021 · IEEE Transactions on Image Processing

Weakly supervised anomaly detection is a challenging task since frame-level labels are not given in the training phase. Previous studies generally employ neural networks to learn features and produce frame-level predictions and then use multiple …

Attribute Augmented Network Embedding Based on Generative Adversarial Nets

2021 · IEEE Transactions on Neural Networks and Learning Systems

Network embedding is to learn low-dimensional representations of nodes while preserving necessary information for network analysis tasks. Though representations preserving both structure and attribute features have achieved in many real-world applications, learning these representations for …

Open-Vocabulary Video Anomaly Detection

2023 · arXiv (Cornell University)

Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. However, current approaches are inherently limited to a closed-set setting …

Research on Secure Communication Model for Station Based on Multi-Factor Identity Authentication

2023

With the advancement of communication technology, the diversity and number of terminal devices in the station communication network continue to grow, and the traditional single authentication method has been difficult to meet the needs of …

Improving the Performance of OPTICS on Short Text Clustering by IsoKernel and UMAP

2024

Clustering of short text streams has become significant due to the popularity of social media platforms. such as Twitter, Facebook, and Weibo. Clustering of short text can automatically detect new topics. Most existing approaches exploit …

CodEv: An Automated Grading Framework Leveraging Large Language Models for Consistent and Constructive Feedback

2024

Grading programming assignments is crucial for guiding students to improve their programming skills and coding styles. This study presents an automated grading framework, CodEv, which leverages Large Language Models (LLMs) to provide consistent and constructive …

DPMM-CFL: Clustered Federated Learning via Dirichlet Process Mixture Model Nonparametric Clustering

2026

Clustered Federated Learning (CFL) improves performance under non-IID client heterogeneity by clustering clients and training one model per cluster, thereby balancing between a global model and fully personalized models. However, most CFL methods require the …