检索结果-内蒙古大学图书馆

Customized Transformer Adapter with Frequency Masking for Deepfake Detection

IEEE Transactions on Information Forensics and Security 2025年 20卷 5904-5918页

作者： Shi, Zenan Chen, Haipeng Jia, Yixin Zhang, Dong Lu, Wei Yang, Xun Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Jilin University College of Software Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Sun Yat-sen University School of Computer Science and Engineering Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China

The evolution of advanced artificial intelligence generated content approaches has heightened concerns about deepfake, due to the sophisticated forgeries and concealed appearances they produce. To this end, the pre-trained Vision Transformer (ViT) model has become a de facto choice for deepfake detection, thanks to its powerful learning capability. Despite favorable results achieved by existing ViT-based methods, they have inherent limitations that could result in suboptimal performance in scenarios with continuously evolving forgery techniques, such as overfitting to single forgery patterns or placing excessive emphasis on dominant forgery regions. In this paper, we propose CUTA, a simple yet effective deepfake detection paradigm that utilizes ViT adapters as the medium and fully exploits the spatial- and frequency-domain features of given images to overcome the limitations of existing methods. Specifically, CUTA focuses on frequency domain masking within the input space, which obscures parts of the high-frequency image to intensify the training challenge while preserving subtle forgery cues in the frequency domain to facilitate comprehensive forgery representations. Furthermore, we propose two task-customized modules within the ViT model, i.e., the texture enhancement module and the multi-scale perceptron module, to seamlessly integrate local texture and rich contextual features. These two modules ensure an organic interaction between the task-specific forgery patterns and general semantic features within the pre-trained ViT framework. The experimental results on several publicly available benchmark datasets demonstrate CUTA’s superiority in performance, particularly showcasing its significant advantages in both cross-dataset and cross-manipulation scenarios. 2005-2012 IEEE.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

A Method for Extracting Electronic Medical Record Entities by Fusing Multichannel Self-Attention Mechanism with Location Relationship Features

A Method for Extracting Electronic Medical Record Entities b...

引用

作者： Hongyan Xu Hong Wang Yong Feng Rongbing Wang Yonggang Zhang College of Information Liaoning University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University

With the implementation of the "Internet+" strategy, electronic medical records are generally applied in the medical field. Deep mining of electronic medical record content data is an effective means to obtain medical knowledge and analyse patients' states, but the existing methods for extracting entities from electronic medical records have problems of redundant information, overlapping entities, and low accuracy rates. Therefore, this paper proposes an entity extraction method for electronic medical records based on the network framework of BERT-Bi LSTM, which incorporates a multichannel self-attention mechanism and location relationship features. First, the text input sequence was encoded using the BERT-BiLSTM network framework, and the global semantic information of the sentence was mined more deeply using the multichannel self-attention mechanism. Then, the position relation characteristic was used to extract the local semantic message of the text, and the position relation characteristic of the word and the position embedding matrix of the whole sentence were obtained. Next, the extracted global semantic information was stitched with the positional embedding matrix of the sentence to obtain the current entity classification matrix. Finally,the proposed method was validated on the dataset of Chinese medical text entity relationship extraction and the 2010i2b2/VA relationship corpus, and the experimental results indicate that the proposed method surpasses existing methods in terms of precision, recall, F1 value and training time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification

arXiv

引用

arXiv 2024年

作者： Li, Mengyu Liu, Yonghao Giunchiglia, Fausto Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education College of Computer Science and Technology Jilin University China University of Trento Italy

Text classification is a crucial and fundamental task in natural language processing. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach has received tremendous attention due to its powerful feature learning capability and robustness. Although several studies have incorporated this technique for text classification, some limitations remain. First, many text datasets are imbalanced, and the learning mechanism of supervised contrastive learning is sensitive to data imbalance, which may harm the model performance. Moreover, these models leverage separate classification branch with cross entropy and supervised contrastive learning branch without explicit mutual guidance. To this end, we propose a novel model named SharpReCL for imbalanced text classification tasks. First, we obtain the prototype vector of each class in the balanced classification branch to act as a representation of each class. Then, by further explicitly leveraging the prototype vectors, we construct a proper and sufficient target sample set with the same size for each class to perform the supervised contrastive learning procedure. The empirical results show the effectiveness of our model, which even outperforms popular large language models across several datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Structure-and Logic-Aware Heterogeneous Graph Learning for Recommendation 40

Structure-and Logic-Aware Heterogeneous Graph Learning for R...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Li, Anchen Yang, Bo Huo, Huan Hussain, Farookh Khadeer Xu, Guandong College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Aalto University Espoo Finland School of Computer Science University of Technology Sydney Sydney Australia Education University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9798350317152

Recently, there has been a surge in recommendations based on heterogeneous information networks (HINs), attributed to their ability to integrate complex and rich semantics. Despite this advancement, most HIN-based recommenders overlook two critical aspects. First, they often fail to consider HIN's heterophily nature, hindering the capture of non-local structures in HINs. Second, most methods lack the capability for logical reasoning. In this paper, we propose a novel structure-and logic-aware heterogeneous graph learning framework for recommender systems (SLHRec). Our SLHRec contains a structure-aware module and a logic-aware module. The former uses network geometry to construct non-local neighborhoods for nodes in HINs, and then introduces a graph neural network to integrate constructed neighbors for modeling the heterophily of HINs. The logic-aware module uses the Markov logic network (MLN) to infuse logic rules into heterogeneous graph learning, thereby boosting logic reasoning in recommendations. Furthermore, we utilize contrastive learning to model cooperative signals between modules, enabling them to complement each other. In the prediction stage, both modules contribute to generating recommendations. Compared with several strong recommender baselines, our SLHRec achieves superior performance on four real-world datasets. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enabling Generalized Zero-Shot Vulnerability Classification

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Hu, Jinghao Guo, Jinsong Luo, Chen Hu, Yang Lanzinger, Matthias Li, Zhanshan Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Software Changchun130012 China University College London Department of Computer Science United Kingdom Amazon United States United Kingdom University of Oxford Department of Computer Science United Kingdom Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Changchun130012 China

Regarding computer security, the growth of code vulnerability types presents a persistent challenge. These vulnerabilities, which may cause severe consequences, necessitate precise classification for effective mitigation. However, the rapid emergence of new vulnerability types complicates the classification process. Traditional methodologies, which often involve human expertise and the manual labeling or generation of example instances, are not only resource-intensive but also struggle to adapt to the dynamic nature of these vulnerabilities. This paper introduces VulnSense, an innovative method that harnesses the capabilities of Generalized Zero-Shot Learning (GZSL) to address the vulnerability classification problem. VulnSense learns about unseen vulnerability classes from the descriptions of these unseen classes, while not requiring to see any instances of these unseen classes. Specifically, VulnSense learns from three main resources: (1) seen classes with labeled code instances;(2) descriptions of these seen classes;and (3) descriptions of "unseen"classes which have no labeled instances. Our experiments underscore VulnSense's superiority over existing GZSL methods in classifying instances of unseen classes. Concurrently, it maintains a performance parity with traditional labeled-example based learning methods in classifying instances of seen vulnerabilities. VulnSense demonstrates the potential of using GZSL for vulnerability classification, while also highlighting challenges that inspire future work. © 2004-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

COVID-19 knowledge Graph for Drug and Vaccine Development

COVID-19 Knowledge Graph for Drug and Vaccine Development

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Huang, Lan Guan, Hongrui Liang, Yanchun Guan, Renchu Feng, Xiaoyue Jilin University The Key Laboratory for Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Changchun China Zhuhai College of Science and Technology Zhuhai Sub Laboratory Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Zhuhai China

ISBN: (纸本)9781665401265

The worldwide spread of COVID-19 has made a severe impact on human health and life. It has shown rapid propagation, long in vitro survival, and a long incubation period. More seriously, COVID-19 is more susceptible to variation, as it is an RNA virus. Mutations of COVID-19 have been reported in multiple countries worldwide, which makes drug and vaccine development a significant challenge. To search for potential drugs and vaccines and reveal the atlas of COVID-19 evolution, we extract information from massive unstructured data and construct a COVID-19 knowledge graph using the COVID-19 data. Based on machine learning approaches, we infer and predict novel coronavirus pneumonia-related diseases, drug action targets, etc. to speculate on new and more effective treatment methods. In addition, to study transcriptome of SARS-CoV-2, new ideas can be provided to biomedical experts with flexible responses to viral variation. An in-depth analysis of the COVID-19 pathomechanism at the pharmaceutical, genetic, and protein levels provides effective means and tools for novel coronavirus pneumonia vaccines, drug development, and therapeutic program design. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An AutoEncoder-Based Matrix Factorization Approach to Estimating Cell Proportion from Bulk Tumor RNA-seq Data

An AutoEncoder-Based Matrix Factorization Approach to Estima...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xu, Yingze Wang, Yan Xie, Xuping Wang, Feilong Chen, Qiong Sun, Huiyan Jilin University College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun China Jilin University School of Artificial Intelligence Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun China

ISBN: (纸本)9781665401265

The deconvolution of infiltrating immune cells and stromal cells from complex tumor tissues is significant for studying the impact of these cells on tumor development, as well as assisting cancer therapies. Integrating cell-specific marker genes from several references, we put forward an AutoEncoder-based matrix factorization method to estimate the cell proportion in heterogeneous samples. The proportion predicted by our method achieved over 0.95 Pearson correlation coefficient (PCC) with the ground truth. Moreover, through analyzing association between cell proportion of tumor tissues and clinical information of the tumor patients, we found that the proportion of cancer-associated fibroblast (CAF) gradually increased with the progress of tumor, and the proportion of B cell in tissues was significantly related to the five-year survival rate of tumor patients. © 2021 IEEE.

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

Instance-adaptive Zero-shot Chain-of-Thought Prompting 38

Instance-adaptive Zero-shot Chain-of-Thought Prompting

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yuan, Xiaosong Shen, Chen Yan, Shaotian Zhang, Xiaofeng Xie, Liang Wang, Wenxiao Guan, Renchu Wang, Ying Ye, Jieping College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering MoE Jilin University China Alibaba Cloud Computing China Shanghai Jiao Tong University China College of Computer Science and Technology Zhejiang University of Technology China College of Software Zhejiang University China

Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt uniformly applied across the whole of instances is inherently limited since one prompt cannot be a good partner for all, a more appropriate approach should consider the interaction between the prompt and each instance meticulously. This work introduces an instance-adaptive prompting algorithm as an alternative zero-shot CoT reasoning scheme by adaptively differentiating good and bad prompts. Concretely, we first employ analysis on LLMs through the lens of information flow to detect the mechanism under zero-shot CoT reasoning, in which we discover that information flows from question to prompt and question to rationale jointly influence the reasoning results most. We notice that a better zero-shot CoT reasoning needs the prompt to obtain semantic information from the question, and then the rationale aggregates sufficient information from the question directly and via the prompt indirectly. On the contrary, lacking any of those would probably lead to a bad one. Stem from that, we further propose an instance-adaptive prompting strategy (IAP) for zero-shot CoT reasoning. Experiments conducted with LLaMA-2, LLaMA-3, and Qwen on math, logic, and commonsense reasoning tasks (e.g., GSM8k, MMLU, Causal Judgement) obtain consistent improvement, demonstrating that the instance-adaptive zero-shot CoT prompting performs better than other task-level methods with some curated prompts or sophisticated procedures, showing the significance of our findings in the zero-shot CoT reasoning mechanism. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing YOLOv8-IC network for industrial scene recognition under camera surveillance

Optimizing YOLOv8-IC network for industrial scene recognitio...

引用

2024 International Conference on Computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2024

作者： Zhang, Jiaming Chen, Jingtian Zhao, Peng Li, Yingxuan Yu, Biao Zhou, You JILIN Institute of Electronic Information Products Inspection Changchun China College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130012 China

ISBN: (纸本)9781510689275

In the context of industrial automation and intelligent monitoring, accurate identification of the industrial environment is crucial to risk management. However, traditional scene classification methods struggle to capture the features of diverse structures and irregular shapes in complex industrial scenes. Additionally, they have shortcomings in extracting details and defining boundaries under dynamic lighting conditions. Deep learning-based methods, however, are better equipped to adapt to the complex backgrounds and dynamic detail variations in industrial environments through automatic feature learning. Although the YOLOv8 network benefits from the advantages of deep learning models, it still has limitations in meeting the recognition needs of complex industrial scenes. These limitations include difficulty in effectively capturing irregular structures and details, low positioning accuracy for overlapping boundaries, and susceptibility to interference from complex backgrounds. To address these issues, this paper introduces YOLOv8-IC (Industrial Classification), an improved version of YOLOv8, to meet the specific requirements of industrial scene classification. This enhancement improves feature extraction, target positioning, and key area focusing capabilities in complex environments. To further validate the model's effectiveness, a new dataset, Places24, was constructed by combining industrial scenes from the Places365 dataset with self-collected camera monitoring images. This approach enhances the model's applicability to real industrial environments. Experimental results show that the YOLOv8-IC network outperforms the original model in classification accuracy and real-time performance, significantly enhancing the stability and accuracy of industrial scene classification. The proposed YOLOv8-IC-based industrial scene classification scheme offers a more accurate solution for intelligent industrial monitoring systems. © 2025 SPIE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

GazePuffer: Hands-Free Input Method Leveraging Puff Cheeks for VR

GazePuffer: Hands-Free Input Method Leveraging Puff Cheeks f...

引用

IEEE Annual International Symposium Virtual Reality

作者： Yunfei Lai Minghui Sun Zhuofeng Li College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

Gaze input is a popular hands-free input method that allows for intuitive and rapid pointing but lacks a confirmation mechanism. This study introduces GazePuffer, an interaction method that combines puffing cheeks with gaze. We explored the design space of mouth gestures, proposed a set of candidate gestures, filtered them through user subjective evaluation, and selected five basic gestures and four variations. We determined the corresponding virtual reality (VR) actions for these gestures through brainstorming. We achieved an accuracy of 93.8% in recognizing the five basic mouth gestures using the built-in sensors of the head-mounted display devices. We compared GazePuffer with two baseline methods in target selection tasks, demonstrating that GazePuffer is on par with Gaze&Pinch in throughput and speed, slightly outperforming Gaze&Dwell. Finally, we showcased the applicability of GazePuffer in real VR interaction tasks, with users generally finding it usable and effortless.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：