Wei Wei

An Effective Hybrid Fraud Detection Method

2015 · Lecture notes in computer science

The rapid growth of data makes it possible for us to study human behavior patterns. Knowing the patterns of human behavior is of great use to help us detect the unusual fraud human behavior. Existing …

Research on University English Teaching Based on CBI

2016

Content-based Instruction (CBI) approach which combines the language teaching with the content teaching is considered as an efficient teaching approach in university English teaching. It is necessary to summarize the experience and lessons seriously of …

Phase Conductor on Multi-layered Attentions for Machine Comprehension

2017 · arXiv (Cornell University)

Attention models have been intensively studied to improve NLP tasks such as machine comprehension via both question-aware passage attention model and self-matching attention model. Our research proposes phase conductor (PhaseCond) for attention models in two …

An Ensemble Learning Algorithm Based on Resampling and Hybrid Feature Selection, with an Application to Software Defect Prediction

2022

In recent years, software defect prediction(SDP) based on ensemble learning has attracted extensive attention. Hevertheless, the forthcoming integrated learning means still have some shortcomings in improving the divergence of base classifiers. How to improve the …

Parameter Convex Neural Networks

2022 · arXiv (Cornell University)

Deep learning utilizing deep neural networks (DNNs) has achieved a lot of success recently in many important areas such as computer vision, natural language processing, and recommendation systems. The lack of convexity for DNNs has …

Automatic Design of Microcontroller System Simulation Based on Artificial Intelligence Technology and Data Intelligence Analysis

2023 · Procedia Computer Science

The automatic design of system simulation based on microcontroller can effectively improve the intelligence level of microcontroller system simulation through intelligent analysis of data and combined with AI (Artificial Intelligence) technology. On the basis of …

PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models

2024 · arXiv (Cornell University)

Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize rewards that reflect human …

Dataset Condensation with Latent Quantile Matching

2024 · arXiv (Cornell University)

Dataset condensation (DC) methods aim to learn a smaller synthesized dataset with informative data records to accelerate the training of machine learning models. Current distribution matching (DM) based DC methods learn a synthesized dataset by …

CSL learners’ acceptance and use of ChatGPT: an extended technology readiness and technology acceptance model

2026 · Humanities and Social Sciences Communications

As an advanced chatbot based on a large language model, ChatGPT receives widespread attention in the field of education, with its emergence potentially prompting a transformation in language learning methods. In this context, the present …

航空遥感场景跨域少样本目标检测进展研究

2026 · Journal of Image and Graphics

航空遥感目标检测在国土资源调查、灾害监测、交通监管和军事侦察等领域具有重要应用价值。然而，真实航空遥感场景中常同时存在目标域标注样本稀缺和源域与目标域分布差异显著的问题，导致传统依赖大规模同分布标注数据的检测方法难以获得稳定性能。跨域少样本目标检测（cross-domain few-shot object detection，CD-FSOD）期望在目标域仅有少量标注样本且存在明显域偏移的条件下实现对目标域目标的有效分类与定位，已成为航空遥感智能解译中的重要研究方向。本文围绕航空遥感场景下的CD-FSOD问题，梳理其基本定义、任务边界及其与少样本目标检测、跨域目标检测和遥感目标检测等相关任务的区别，并分析航空遥感场景中由成像平台、传感器类型、空间分辨率、地理区域、环境条件及目标分布差异所引起的复杂域偏移表现。在此基础上，本文对现有代表性方法进行分类综述，重点总结基于迁移与域对齐、基于元学习与度量学习、基于生成式数据增强与扩充、基于视觉语言对齐以及基于大模型的方法特点与研究进展。同时，本文归纳相关数据集、任务设置、常用评测指标及航空遥感目标检测的特殊性，并进一步讨论复杂域偏移统一建模、少样本条件下检测稳定性、数据集与真实应用脱节、多源异构数据适配以及大模型迁移等方面的主要问题与发展趋势。本文同步汇总代表性算法在航空遥感跨域少样本情境下的性能表现，并给出所涉及数据集、算法的开放资源访问链接：https：//github.com/Farenweh/CD-FSOD-Links（Github）或https：//gitee.com/cby1241385936/cd-fsod-links（Gitee）。总体来看，CD-FSOD正由单一迁移或少样本学习策略，逐步发展为融合域适应、特征增强、语义建模和基础模型迁移的综合性研究方向。随着遥感专用数据资源的丰富和多模态基础模型的发展，该方向有望为航空遥感智能感知提供更高效、更稳健的技术支撑。

Global Context Enhanced Graph Neural Networks for Session-based Recommendation

2020

Session-based recommendation (SBR) is a challenging task, which aims at recommending items based on anonymous behavior sequences. Almost all the existing solutions for SBR model user preference only based on the current session without exploiting …

LLMRec: Large Language Models with Graph Augmentation for Recommendation

2024

The problem of data sparsity has long been a challenge in recommendation systems, and previous studies have attempted to address this issue by incorporating side information. However, this approach often introduces side effects such as …