检索结果-内蒙古大学图书馆

Semantic and Emotional Dual Channel for Emotion Recognition in Conversation

IEEE Transactions on Affective Computing 2025年

作者： Yang, Zhenyu Zhang, Zhibo Cheng, Yuhu Zhang, Tong Wang, Xuesong Jinan250353 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250353 China China University of Mining and Technology Engineering Research Center of Intelligent Control for Underground Space Ministry of Education Xuzhou Key Laboratory of Artificial Intelligence and Big Data School of Information and Control Engineering Xuzhou221116 China South China University of Technology Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Guangzhou510335 China Engineering Research Center Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China

Emotion recognition in conversation (ERC) aims at accurately identifying emotional states expressed in conversational content. Existing ERC methods, although relying on semantic understanding, often encounter challenges when confronted with incomplete or misleading semantic information. In addition, when dealing with the interaction between emotional and semantic information, existing methods are often difficult to effectively distinguish the complex relationship between the two, which affects the accuracy of emotion recognition. To address the problems of semantic misdirection and emotional cross-talk encountered by traditional models when confronted with complex conversational data, we propose a semantic and emotional dual channel (SEDC) strategy for emotion recognition in conversations to process emotional and semantic information independently. Under this strategy, emotion information provides an auxiliary recognition function when the semantics are unclear or lacking, enhancing the accuracy of the model. Our model consists of two modules: the emotion processing module accurately captures the emotional features of each utterance through contrastive learning, and then constructs a dialogue emotion propagation map to simulate the emotional information conveyed in the dialogue;the semantic processing module combines an external knowledge base to enhance the semantic expression of the dialogue through knowledge enhancement strategies. This divide-and-conquer approach allows us to more deeply analyze the emotional and semantic dimensions of complex dialogues. Experimental results on the IEMOCAP, EmoryNLP, MELD, and DailyDialog datasets show that our approach significantly outperforms existing techniques and effectively improves the accuracy of dialogue emotion recognition. Our code is available at https://***/r/SEDC-FCF1. © 2010-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An enhanced MinHash encryption scheme for encrypted deduplication

An enhanced MinHash encryption scheme for encrypted deduplic...

引用

IEEE International Conference on Trust, security and Privacy in Computing and Communications (TrustCom)

作者： Qiaowen Jia Guanxiong Ha Hanwei Wang Haoyu Ma Hang Chen State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China College of Cyber Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Zhejiang Lab Hangzhou China The School of Cyber Engineering Xidian University Xi’an China

The encrypted deduplication can provide both storage savings and data confidentiality for cloud storage systems. Convergent encryption (CE) is a well-known solution for encrypted deduplication, but it brings huge computation and storage overheads for key management. MinHash encryption is an effective solution to this issue. It reduces the number of keys by grouping multiple consecutive chunks into segments and generating one key for each segment. However, MinHash encryption does not take full advantage of the segment similarity, which can be used to further reduce the overhead for key management. To this end, we augment MinHash encryption with Bloom filter and Locality Sensitivity Hash (LSH) to design an enhanced MinHash encryption scheme. Firstly, our scheme generates a sketch for each segment based on the Bloom filter, and projects sketches to the points in a hash table through LSH functions. Secondly, we detect the segment similarity by the distance between points, and similar segments are grouped into super-segments. Finally, we combine MinHash encryption and server-aided message-locked encryption to encrypt the super-segments for achieving encrypted deduplication. We conduct trace-driven experiments using a realworld dataset. Compared with MinHash encryption, our scheme has higher storage efficiency and better encryption performance.

关键词： Privacy Maximum likelihood estimation data privacy Cloud computing Sensitivity Encryption

来源：评论

学校读者我要写书评

暂无评论

Noise-Tolerant Learning for Audio-Visual Action Recognition

arXiv

引用

arXiv 2022年

作者： Han, Haochen Zheng, Qinghua Luo, Minnan Miao, Kaiyao Tian, Feng Chen, Yan The National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an710049 China The School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China The Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Ministry of Education Xi’an710049 China The School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an710049 China

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. Despite the benefits brought by contrastive training, it would overfit the noisy correspondence and thus provide false supervision. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Furthermore, due to the lack of suitable datasets, we establish a benchmark of real-world noisy correspondence in audio-visual data by relabeling the Kinetics dataset. Extensive experiments on a wide range of noisy levels demonstrate that our method significant

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Knowledge Distillation of Generative Adversarial networks

Research on Knowledge Distillation of Generative Adversarial...

引用

data Compression Conference (DCC)

作者： Wei Wang Baohua Zhang Tao Cui Yimeng Chai Yue Li College of Computer Science KLMDASR Trusted AI System Lab Nankai University Tianjin China College of Computer Science Tianjin Key Lab of Network and Data Security Technology Nankai University Tianjin China NCMIS LSEC Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

The compression of Generative Adversarial networks (GANs) has been an emerging study in recent years. However, conventional compression methods can hardly be applied to GANs due to the training process and optimization target of GANs are different from the traditional classification detection network. Inspired by the recent success of knowledge distillation, we condense the recent researches on them applied to particular GANs, i.e. WGAN and CGAN for special tasks into two strategies: Soft Target Only Strategy (STOS) and Inherited Hard Target Strategy (IHTS), and propose an novel Random Hard Target Strategy, namely RHTS. In RHTS, we take the student network generator loss as the hard target of knowledge distillation when the discriminator is fixed, and the output of the teacher network generator as the soft target to distill GANs. The experiments on image datasets (MNIST, CIFAR-10), and structured-data datasets (Australian Credit Approval dataset, Credit Approval data Set) show that STOS and IHTS are effective, and RHTS is the best. Such results are further proved on WGAN, WGAN-GP and LSGAN in order to demonstrate the better generalization ability of the strategies. Besides, the RHTS improve the stability of the GAN training process, where the performance and stability confirm the rationality of our design.

关键词： Training Knowledge engineering data compression Generative adversarial networks Generators Task analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Semantics-Guided Contrastive network for Zero-Shot Object Detection

arXiv

引用

arXiv 2021年

作者： Yan, Caixia Chang, Xiaojun Luo, Minnan Liu, Huan Zhang, Xiaoqin Zheng, Qinghua The Ministry of Education Key Lab of Intelligent Networks and Network Security National Engineering Lab for Big Data Analytics School of Electronic and Information Engineering Xi'an Jiaotong University Shaanxi710049 China The ReLER Lab AAAI Faculty of Engineering and Information Technology University of Technology Sydney Australia The College of Computer Science and Artificial Intelligence Wenzhou University China

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories;2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks. © 2021, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

LDPC Code based Pseudonym Scheme for Vehicular networks

LDPC Code based Pseudonym Scheme for Vehicular Networks

引用

Space-Air-Ground Computing (SAGC), International Conference on

作者： Jin Zhou Changsong Zheng Yuedi Li Hua Xu Zhiguang Qin Dajiang Chen Network and Data Security Key Lab of Sichuan Province UESTC Chengdu China Public Security Bureau of Sichuan Chengdu China School of Physics and Electronic Engineering Yancheng Teachers University Yancheng China

ISBN: (纸本)9781665430104

In this paper, an innovative pseudonym scheme based on Direct Anonymous Attestation (DAA) and Low-Density Parity-Check (LDPC) is proposed. For the sake of improving the efficiency of generating pseudonyms, the proposed scheme uses the LDPC code to encode the credential to produce more available versions. To detect whether a vehicle's On-Board Unit (OBU) is compromised, the proposed scheme grants the Revocation Authority (RA) to check if the compromised OBU uses a revoked pseudonym. Compared with the existing pseudonym scheme, the proposed scheme has a higher level of security and lower computation overhead.

关键词： Parity check codes security

来源：评论

学校读者我要写书评

暂无评论

LTE Device Identification Based on RF Fingerprint with Multi-Channel Convolutional Neural network

LTE Device Identification Based on RF Fingerprint with Multi...

引用

2021 IEEE Global Communications Conference (GLOBECOM)

作者： Pengcheng Yin Linning Peng Junqing Zhang Ming Liu Hua Fu Aiqun Hu School of Cyber Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories for Network and Communication Security Nanjing China University of Liverpool Liverpool United Kingdom Beijing Key Lab of Transportation Data Analysis and Mining Beijing Jiaotong University Beijing China School of Information Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9781728181059

Radio frequency fingerprint (RFF) identification technique has drawn great attention to wireless terminal authentication. Long-Term Evolution (LTE) has been widely deployed all over the world. RFF-based LTE terminal identifications can prevent the potential impersonation or denial of service (DoS) attacks in the physical layer. This paper proposes a novel multi-channel convolutional neural network (MCCNN) for LTE terminal identification. Differential constellation trace figure (DCTF) is extracted from the random access preamble of the physical random access channel (PRACH). To the best knowledge of the authors, this is the first work dedicated to RFF-based LTE terminal identification. The proposed scheme is evaluated in the hardware experimental system consisting of the LTE eNodeB implemented on the software-defined radio (SDR) platform and six LTE mobile phones. Experimental results show that the classification accuracy can reach 98.96% at the SNR level of 30 dB with the line-of-sight (LOS) scenarios. Furthermore, long-time evaluations show that the proposed DCTF-MCCNN scheme is robust over time.

关键词： Wireless communication Radio frequency Fingerprint recognition Mobile handsets Object recognition Convolutional neural networks Long Term Evolution

来源：评论

学校读者我要写书评

暂无评论

VFGCN: A Vertical Federated Learning Framework With Privacy Preserving for Graph Convolutional network

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Wang, Gang Li, Qingming Liu, Ximeng Yan, Xiaoran Dong, Qingkuan Wu, Huiwen Kong, Xiangjie Zhou, Li Zhejiang Lab HangZhou310000 China Zhejiang University College of Computer Science and Technology Hangzhou310058 China Fuzhou University Key Laboratory of Information Security of Network Systems College of Computer and Big Data Fuzhou350108 China Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China Zhejiang University of Technology College of Computer Science and Technology Hangzhou310023 China Dalian University of Technology School of Software Dalian116620 China

Due to the robust representational capabilities of graph data, employing graph neural networks for its processing has demonstrated superior performance over conventional deep learning algorithms. Graph data encompasses abundant features and structural information;however, its large-scale collection is often challenging in practice. This difficulty arises because data predominantly exists in isolated compartments, making it arduous to harmonize information across various organizations or to enable multiple organizations to collaborate effectively while safeguarding local data privacy. In light of an extreme data distribution scenario, where each client possesses distinct nodes with partially overlapping segments yet divergent data features, we introduce a dual-cloud server architecture. This framework encompasses the design of four secure subprotocols: ReEnc (secure re-encryption), SecPSI (secure outsourcing of PSI), SecWeight (secure weight calculation), and SecAgg (secure aggregation). Together, these components facilitate a vertical federated learning framework for graph convolutional networks, ensuring privacy preservation. We provide a security proof for the entire system and extensive evaluation on three benchmark datasets (Cora, Citeseer, and Pubmed) illustrates that our Vertical Federated Graph Convolutional network (VFGCN) surpasses existing privacy-preserving methodologies. © 2004-2012 IEEE.

关键词： Privacy by design

来源：评论

学校读者我要写书评

暂无评论

Shattered chain of trust: understanding security risks in cross-cloud IoT access delegation 20

Shattered chain of trust: understanding security risks in cr...

引用

Proceedings of the 29th USENIX Conference on security Symposium

作者： Bin Yuan Yan Jia Luyi Xing Dongfang Zhao XiaoFeng Wang Deqing Zou Hai Jin Yuqing Zhang School of Cyber Science and Engineering Huazhong Univ. of Sci. & Tech. China and National Engineering Research Center for Big Data Technology and System Cluster and Grid Computing Lab Services Computing Technology and System Lab and Big Data Security Engineering Research Center and Indiana University Bloomington and Shenzhen Huazhong University of Science and Technology Research Institute China School of Cyber Engineering Xidian University China and National Computer Network Intrusion Protection Center University of Chinese Academy of Sciences China and Indiana University Bloomington Indiana University Bloomington School of Cyber Science and Engineering Huazhong Univ. of Sci. & Tech. China and National Engineering Research Center for Big Data Technology and System Cluster and Grid Computing Lab Services Computing Technology and System Lab and Big Data Security Engineering Research Center School of Computer Science and Technology Huazhong Univ. of Sci. & Tech. China and National Engineering Research Center for Big Data Technology and System Cluster and Grid Computing Lab Services Computing Technology and System Lab and Big Data Security Engineering Research Center Huazhong Univ. of Sci. & Tech. China National Computer Network Intrusion Protection Center University of Chinese Academy of Sciences China and School of Cyber Engineering Xidian University China

ISBN: (纸本)9781939133175

IoT clouds facilitate the communication between IoT devices and users, and authorize users' access to their devices. In this paradigm, an IoT device is usually managed under a particular IoT cloud designated by the device vendor, e.g., Philips bulbs are managed under Philips Hue cloud. Today's mainstream IoT clouds also support device access delegation across different vendors (e.g., Philips Hue, LIFX, etc.) and cloud providers (e.g., Google, IFTTT, etc.): for example, Philips Hue and SmartThings clouds support to delegate device access to another cloud such as Google Home, so a user can manage multiple devices from different vendors all through Google Home. Serving this purpose are the IoT delegation mechanisms developed and utilized by IoT clouds, which we found are heterogeneous and ad-hoc in the wild, in the absence of a standardized delegation protocol suited for IoT environments. In this paper, we report the first systematic study on real-world IoT access delegation, based upon a semi-automatic verification tool we developed. Our study brought to light the pervasiveness of security risks in these delegation mechanisms, allowing the adversary (e.g., Airbnb tenants, former employees) to gain unauthorized access to the victim's devices (e.g., smart locks) or impersonate the devices to trigger other devices. We confirmed the presence of critical security flaws in these mechanisms through end-to-end exploits on them, and further conducted a measurement study. Our research demonstrates the serious consequences of these exploits and the security implications of the practice today for building these mechanisms. We reported our findings to related parties, which acknowledged the problems. We further propose principles for developing more secure cross-cloud IoT delegation services, before a standardized solution can be widely deployed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

XTQA: Span-Level Explanations for Textbook Question Answering

arXiv

引用

arXiv 2020年

作者： Ma, Jie Chai, Qi Liu, Jun Yin, Qingyu Wang, Pinghui Zheng, Qinghua Ministry of Education of Key Lab for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Amazon United States

Textbook Question Answering (TQA) is the task of correctly answering diagram or non-diagram questions given large multi-modal contexts consisting of abundant essays and diagrams. In real-world scenarios, an explainable TQA system plays a key role in deepening humans’ understanding of learned knowledge. However, there is no work to investigate how to provide explanations currently. To address this issue, we devise a novel architecture towards span-level eXplanations for TQA (XTQA). In this paper, spans are the combinations of sentences within a paragraph. The key idea is to consider the entire textual context of a lesson as candidate evidence, and then use our proposed coarse-to-fine grained Explanation Extracting (EE) algorithm to narrow down the evidence scope and extract the span-level explanations with varying lengths for answering different questions. The EE algorithm can also be integrated into other TQA methods to make them explainable and improve the TQA performance. Experimental results show that XTQA obtains the best overall explanation result (mIoU) of 52.38% on the first 300 questions of CK12-QA test splits, demonstrating the explainability of our method (non-diagram: 150 and diagram: 150). The results also show that XTQA achieves the best TQA performance of 36.46% and 36.95% on the aforementioned splits respectively. We have released our code in https://***/dr-majie/*** Codes 68T07 Copyright © 2020, The Authors. All rights reserved.

关键词： Textbooks

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：