16 citations · 38 across the 19 of their papers we have counts for
21 papers
Agreement Disagreement Guided Knowledge Transfer for Cross-Scene Hyperspectral Imaging
Lu Huo, Haimin Zhang, Min Xu
Knowledge transfer plays a crucial role in cross-scene hyperspectral imaging (HSI). However, existing studies often overlook the challenges of gradient conflicts and dominant gradi…
Enhancing Knowledge Transfer in Hyperspectral Image Classification via Cross-scene Knowledge Integration
Lu Huo, Wenjian Huang, Jianguo Zhang +2
Knowledge transfer has strong potential to improve hyperspectral image (HSI) classification, yet two inherent challenges fundamentally restrict effective cross-domain transfer: spe…
MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models
Yunxiao Shi, Shuo Yang, Haimin Zhang +4
Neural Collaborative Filtering models are widely used in recommender systems but are typically trained under static settings, assuming fixed data distributions. This limits their a…
Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment
Jiahao Xia, Min Xu, Wenjian Huang +3
Despite the similar structures of human faces, existing face alignment methods cannot learn unified knowledge from multiple datasets with different landmark annotations. The limite…
A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Engine
Yunxiao Shi, Min Xu, Haimin Zhang +2
Large language models (LLMs) and retrieval-augmented generation (RAG) techniques have revolutionized traditional information access, enabling AI agent to search and summarize infor…
Unsupervised Part Discovery via Dual Representation Alignment
Jiahao Xia, Wenjian Huang, Min Xu +4
Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vis…
Beyond KAN: Introducing KarSein for Adaptive High-Order Feature Interaction Modeling in CTR Prediction
Yunxiao Shi, Wujiang Xu, Haimin Zhang +2
Modeling high-order feature interactions is crucial for click-through rate (CTR) prediction, yet traditional approaches typically predefine a maximum interaction order and exhausti…
Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems
Yunxiao Shi, Xing Zi, Zijing Shi +3
Retrieval-augmented generation (RAG) techniques leverage the in-context learning capabilities of large language models (LLMs) to produce more accurate and relevant responses. Origi…
Differential Encoding for Improved Representation Learning over Graphs
Haimin Zhang, Jiahao Xia, Min Xu
Combining the message-passing paradigm with the global attention mechanism has emerged as an effective framework for learning over graphs. The message-passing paradigm and the glob…
Conditional Local Feature Encoding for Graph Neural Networks
Yongze Wang, Haimin Zhang, Qiang Wu +1
Graph neural networks (GNNs) have shown great success in learning from graph-based data. The key mechanism of current GNNs is message passing, where a node's feature is updated bas…
ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization
Yunxiao Shi, Xing Zi, Zijing Shi +3
Retrieval-augmented generation (RAG) for language models significantly improves language understanding systems. The basic retrieval-then-read pipeline of response generation has ev…
Neighbour-level Message Interaction Encoding for Improved Representation Learning on Graphs
Haimin Zhang, Min Xu
Message passing has become the dominant framework in graph representation learning. The essential idea of the message-passing framework is to update node embeddings based on the in…
RandAlign: A Parameter-Free Method for Regularizing Graph Convolutional Networks
Haimin Zhang, Min Xu
Studies continually find that message-passing graph convolutional networks suffer from the over-smoothing issue. Basically, the issue of over-smoothing refers to the phenomenon tha…
Vital Sign Monitoring in Dynamic Environment via mmWave Radar and Camera Fusion
Yingqi Wang, Zhongqin Wang, J. Andrew Zhang +2
Contact-free vital sign monitoring, which uses wireless signals for recognizing human vital signs (i.e, breath and heartbeat), is an attractive solution to health and security. How…
Multimodal Hyperspectral Image Classification via Interconnected Fusion
Lu Huo, Jiahao Xia, Leijie Zhang +2
Existing multiple modality fusion methods, such as concatenation, summation, and encoder-decoder-based fusion, have recently been employed to combine modality characteristics of Hy…
SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks
Haimin Zhang, Min Xu, Guoqiang Zhang +1
Graph convolutional networks have been successfully applied in various graph-based tasks. In a typical graph convolutional layer, node features are updated by aggregating neighborh…
An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking
Jiahao Xia, Haimin Zhang, Shiping Wen +2
While Convolutional Neural Networks (CNNs) have significantly boosted the performance of face related algorithms, maintaining accuracy and efficiency simultaneously in practical us…
Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations
Haimin Zhang, Min Xu
Deep neural networks have been successfully applied in various machine learning tasks. However, studies show that neural networks are susceptible to adversarial attacks. This expos…
Dual Pattern Learning Networks by Empirical Dual Prediction Risk Minimization
Haimin Zhang, Min Xu
Motivated by the observation that humans can learn patterns from two given images at one time, we propose a dual pattern learning network architecture in this paper. Unlike convent…
Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos
Haimin Zhang, Min Xu
With the widespread of user-generated Internet videos, emotion recognition in those videos attracts increasing research efforts. However, most existing works are based on frameleve…
Modelling Temporal Information Using Discrete Fourier Transform for Video Classification
Haimin Zhang
Recently, video classification attracts intensive research efforts. However, most existing works are based on framelevel visual features, which might fail to model the temporal inf…