Episodic Memory-Double Actor–Critic Twin Delayed Deep Deterministic Policy Gradient

Academic Background Deep Reinforcement Learning (DRL) has achieved remarkable success in various fields such as gaming, robotics, navigation, computer vision, and finance. However, existing DRL algorithms generally suffer from low sample efficiency, requiring vast amounts of data and training steps to achieve desired performance. Particularly in co...

Probabilistic Memory Auto-Encoding Network for Abnormal Behavior Detection in Surveillance Video

Probabilistic Memory Auto-Encoding Network for Abnormal Behavior Detection in Surveillance Video

Research on Abnormal Behavior Detection in Surveillance Video Based on Probabilistic Memory Auto-Encoding Network Academic Background In intelligent surveillance systems, abnormal behavior detection is a crucial function widely applied in anti-terrorism, social stability maintenance, and public safety assurance. However, a core challenge in abnorma...

Dataset-Free Weight-Initialization on Restricted Boltzmann Machine

Research on Weight Initialization Method for Restricted Boltzmann Machines Based on Statistical Mechanical Analysis Academic Background In deep learning, the initialization of neural network weights significantly impacts the training effectiveness of models. Particularly in feed-forward neural networks, several dataset-free weight initialization me...

Towards Zero-Shot Human–Object Interaction Detection via Vision–Language Integration

Towards Zero-Shot Human–Object Interaction Detection via Vision–Language Integration

Research on Zero-Shot Human-Object Interaction Detection Based on Vision-Language Integration Academic Background Human-Object Interaction (HOI) detection is an important research direction in the field of computer vision, aiming to identify interactions between humans and objects in images. Traditional HOI detection methods primarily rely on super...

PrivCore: Multiplication-Activation Co-Reduction for Efficient Private Inference

Efficient Private Inference in Deep Neural Networks: Breakthrough Research on the PrivCore Framework Background Introduction With the rapid development of deep learning technology, Deep Neural Networks (DNNs) have been increasingly applied in fields such as image recognition, natural language processing, and medical diagnosis. However, as the deman...

Learn the Global Prompt in the Low-Rank Tensor Space for Heterogeneous Federated Learning

Academic Background With the increasing complexity of artificial intelligence (AI) models and the growing demand for data privacy protection, Federated Learning (FL) has emerged as a hot research topic as a distributed machine learning paradigm. Federated Learning allows multiple clients to collaboratively train a global model without sharing local...

Dual-View Graph-of-Graph Representation Learning with Graph Transformer for Graph-Level Anomaly Detection

Research on Graph-Level Anomaly Detection Based on Dual-View Graph-of-Graph Representation Learning Academic Background In today’s data-driven world, graphs, as a powerful data structure, are widely used in fields such as social network analysis, financial fraud detection, and bioinformatics. Graphs can effectively represent complex relational data...

Memory Flow-Controlled Knowledge Tracing with Three Stages

Academic Background With the rapid development of artificial intelligence (AI) technology, intelligent tutoring systems (ITS) such as Khan Academy and Coursera have made significant progress in personalized learning. Knowledge Tracing (KT), as a key technology in ITS, aims to infer students’ knowledge mastery and predict their future learning perfo...

Continual Learning of Conjugated Visual Representations through Higher-Order Motion Flows

Continual Learning of Conjugated Visual Representations through Higher-Order Motion Flows: A Study on the CMOSFET Model Academic Background In the fields of artificial intelligence and computer vision, continual learning from continuous visual data streams has long been a challenge. Traditional machine learning methods typically rely on the assumpt...

Exploiting Instance-Label Dynamics through Reciprocal Anchored Contrastive Learning for Few-Shot Relation Extraction

Exploiting Instance-Label Dynamics through Reciprocal Anchored Contrastive Learning for Few-Shot Relation Extraction Academic Background In the field of Natural Language Processing (NLP), Relation Extraction (RE) is a fundamental task aimed at identifying and extracting relationships between entities in text. However, traditional supervised learnin...