检索结果-内蒙古大学图书馆

A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo School of Computer Science and Technology The Ministry of Education Key Laboratory for Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong Shaanxi Xi’an710049 China School of Computer Science and Technology Xi’an Jiaotong Shaanxi Xi’an710049 China The BigKE Joint Innovation Center SHMEEA Shanghai China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

Online Attentive Kernel-Based Temporal Difference Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

Crsanet: Class Representations Self-Attention Network for the Segmentation of Thyroid Nodules

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Sun, Shiyao Fu, Chong Xu, Sen Wen, Yingyou Ma, Tao School of Computer Science and Engineering Northeastern University Shenyang110819 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China General Hospital of Northern Theatre Command Shenyang110016 China Medical Imaging Research Department Neusoft Research of Intelligent Healthcare Technology Co. Ltd. Shenyang China Dopamine Group Ltd. Auckland1542 New Zealand

Segmenting accurate thyroid nodules in medical ultrasound images is always non-trivial due to the large variation in size, shape and texture of nodules, and also the presence of surrounding tissues and organs with similar intensity values. Existing algorithms solve this by designing multi-scale spatial context modeling modules and introducing the emerging self-attention based paradigm, while failing to learn the class-wise relational context around nodules. To this end, we propose a novel coarse-to-fine framework, namely, CRSANet, which leverages both class-wise relational context and spatial multi-scale context for comprehensive context perception. Specifically, we first introduce the concept of Class Representations, which describe the overall representation of thyroid nodules in ultrasound images from a categorical perspective. Secondly, we propose a backbone-free dual-branch Class Representation Self-Attention Module (CRSA) to refine the coarse segmentation results from segmentation backbones. Concretely, Fine Class Region (FCR) branch is proposed to impose consistency between pixels and their corresponding Class Representations to correct the wrongly classified pixels. Meanwhile, Class Contextual Representation (CCR) branch is introduced to enhance the ability of pixel representations with the corresponding Class Representations. We evaluate the effectiveness and generality of CRSANet using three types of backbone networks. In the experiments, our proposed U-CRSANet achieves a mIoU of 78.86% and 81.35%, an accuracy of 97.11% and 98.63%, a Dice value of 74.26% and 87.57%, respectively, which outperforms most state-of-the-art methods on the public DDTI and TN-SCUI datasets. © 2023, The Authors. All rights reserved.

关键词： Pixels

Hard Sample Matters a Lot in Zero-Shot Quantization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Huantong Wu, Xiangmiao Lv, Fanbing Liao, Daihai Li, Thomas H. Zhang, Yonggang Han, Bo Tan, Mingkui South China University of Technology China Changsha Hisense Intelligent System Research Institute Co. Ltd China Hong Kong Baptist University Hong Kong Key Laboratory of Big Data and Intelligent Robot Ministry of Education China PengCheng Laboratory China Information Technology R&D Innovation Center of Peking University China School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China

Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network quantization is performed using synthetic samples, thus, the performance of quantized models depends heavily on the quality of synthetic samples. Nonetheless, we find that the synthetic samples constructed in existing ZSQ methods can be easily fitted by models. Accordingly, quantized models obtained by these methods suffer from significant performance degradation on hard samples. To address this issue, we propose HArd sample Synthesizing and Training (HAST). Specifically, HAST pays more attention to hard samples when synthesizing samples and makes synthetic samples hard to fit when training quantized models. HAST aligns features extracted by full-precision and quantized models to ensure the similarity between features extracted by these two models. Extensive experiments show that HAST significantly outperforms existing ZSQ methods, achieving performance comparable to models that are quantized with real data. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

Traffic Engineering in Dynamic Hybrid Segment Routing Networks

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第7期68卷 655-670页

作者： Yingya Guo Kai Huang Cheng Hu Jiangyuan Yao Siyu Zhou College of Mathematics and Computer Science Fuzhou UniversityFuzhou350000China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350000China Key Laboratory of Spatial Data Mining&Information Sharing Ministry of EducationFuzhou350003China School of Information Science and Technology Guangdong University of Foreign StudiesGuangzhou510006China School of Computer Science and Cyberspace Security Hainan UniversityHaiKou570228China Tandon School of Engineering New York UniversityNew York10012USA Department of Computing Hong Kong Polytechnic UniversityHong Hom999077Hong Kong

The emergence of Segment Routing(SR)provides a novel routing paradigm that uses a routing technique called source packet *** SR architecture,the paths that the packets choose to route on are indicated at the ingress *** with shortest-path-based routing in traditional distributed routing protocols,SR can realize a flexible routing by implementing an arbitrary flow splitting at the ingress *** the advantages of SR,it may be difficult to update the existing IP network to a full SR deployed network,for economical and technical *** partial of the traditional IP network to the SR network,thus forming a hybrid SR network,is a preferable *** the traffic is dynamically changing in a daily time,in this paper,we propose a Weight Adjustment algorithm WASAR to optimize routing in a dynamic hybrid SR *** algorithm can be divided into three steps:firstly,representative Traffic Matrices(TMs)and the expected TM are obtained from the historical TMs through ultrascalable spectral clustering ***,given the network topology,the initial network weight setting and the expected TM,we can realize the link weight optimization and SR node deployment optimization through a Deep Reinforcement Learning(DRL)***,we optimize the flow splitting ratios of SR nodes in a centralized online manner under dynamic traffic demands,in order to improve the network *** the evaluation,we exploit historical TMs to test the performance of the obtained routing configuration in *** extensive experimental results validate that our proposed WASAR algorithm has superior performance in reducing Maximum Link Utilization(MLU)under the dynamic traffic.

关键词： Traffic engineering routing optimization segment routing deep reinforcement learning ultra-scalable spectral clustering

How to respond to emerging threats of cyberspace security via social engineering? A novel paradigm to solve cyberspace security issues

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Lin, Hao Wang, Chun-Dong Gao, Hao-Yu School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing Novel Software Technology Ministry of Education Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China College of Data Science and Application Inner Mongolia University of Technology Hohhot China

Cybersecurity researchers always ignore the "people" behind the issues when dealing with cyberspace security issues. The human and technological aspects of cyberspace security must be simultaneously addressed to enable a secure cyber environment. Social engineering is a discipline whose research object is people, and the combination of social engineering and cyberspace security can provide new solution ideas for lots of cyberspace security issues. This paper attempts to answer the question —— "How to solve cyberspace security issues via social engineering?" We briefly review existing frameworks for social engineering attacks and propose a novel, recursive, and iterative framework for social engineering attacks in cyberspace. The existing research achievements of combination of social engineering and cyberspace security were reviewed in the order of cyber personality, hacker psychology, human flesh search, and social engineering defense. To answer this question, we summarized four "guidelines" for using social engineering. Finally, we look ahead, give our thoughts, and discuss answers of the question and future research. It is aimed at getting more researchers of cyberspace security and social science to pay attention to this field. © 2022, CC BY.

关键词： Cybersecurity

Hybrid RAG-empowered Multi-modal LLM for Secure data Management in Internet of Medical Things: A Diffusion-based Contract Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Su, Cheng Wen, Jinbo Kang, Jiawen Wang, Yonghua Su, Yuanjia Pan, Hudan Zhong, Zishao Hossain, M. Shamim School of Automation The GuangdongHongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology Guangzhou510006 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Automation The Guangdong Basic Research Center of Excellence for Ecological Security and Green Development Key Laboratory for City Cluster Environmental Safety Green Development The Ministry of Education Guangdong University of Technology Guangzhou510006 China School of Automation The Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of Education Guangdong University of Technology Guangzhou510006 China School of Automation Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangdong University of Technology Guangzhou510006 China Guangzhou University of Traditional Chinese Medicine State Key Laboratory of Traditional Chinese Medicine Syndrome The Second Affiliated Hospital of Guangzhou University of Chinese Medicine Chinese Medicine Guangdong Laboratory Hengqin 519000 China Second Affiliated Hospital of Guangzhou University of Chinese Medicine Chinese Medicine Guangdong Laboratory Hengqin 519000 China Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh12372 Saudi Arabia

Secure data management and effective data sharing have become paramount in the rapidly evolving healthcare landscape, especially with the growing integration of the Internet of Medical Things (IoMT). The rise of generative artificial intelligence has further elevated Multi-modal Large Language Models (MLLMs) as essential tools for managing and optimizing healthcare data in IoMT. MLLMs can support multi-modal inputs and generate diverse types of content by leveraging large-scale training on vast amounts of multi-modal data. However, critical challenges persist in developing medical MLLMs, including security and freshness issues of healthcare data, affecting the output quality of MLLMs. To this end, in this paper, we propose a hybrid Retrieval-Augmented Generation (RAG)-empowered medical MLLM framework for healthcare data management. This framework leverages a hierarchical cross-chain architecture to facilitate secure data training. Moreover, it enhances the output quality of MLLMs through hybrid RAG, which employs multi-modal metrics to filter various unimodal RAG results and incorporates these retrieval results as additional inputs to MLLMs. Additionally, we employ age of information to indirectly evaluate the data freshness impact of MLLMs and utilize contract theory to incentivize healthcare data holders to share their fresh data, mitigating information asymmetry during data sharing. Finally, we utilize a generative diffusion model-based deep reinforcement learning algorithm to identify the optimal contract for efficient data sharing. Numerical results demonstrate the effectiveness of the proposed schemes, which achieve secure and efficient healthcare data management. Copyright © 2024, The Authors. All rights reserved.

关键词： Information management

RSAFormer: A method of polyp segmentation with region self-attention transformer

学校读者我要写书评

暂无评论

Computers in Biology and Medicine 2024年 172卷 108268-108268页

作者： Yin, Xuehui Zeng, Jun Hou, Tianxiao Tang, Chao Gan, Chenquan Jain, Deepak Kumar García, Salvador School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China School of Cyber Security and Information Law Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China Symbiosis Institute of Technology Symbiosis International University Pune412115 India Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Granada18071 Spain

Colonoscopy has attached great importance to early screening and clinical diagnosis of colon cancer. It remains a challenging task to achieve fine segmentation of polyps. However, existing State-of-the-art models still have limited segmentation ability due to the lack of clear and highly similar boundaries between normal tissue and polyps. To deal with this problem, we propose a region self-attention enhancement network (RSAFormer) with a transformer encoder to capture more robust features. Different from other excellent methods, RSAFormer uniquely employs a dual decoder structure to generate various feature maps. Contrasting with traditional methods that typically employ a single decoder, it offers more flexibility and detail in feature extraction. RSAFormer also introduces a region self-attention enhancement module (RSA) to acquire more accurate feature information and foster a stronger interplay between low-level and high-level features. This module enhances uncertain areas to extract more precise boundary information, these areas being signified by regional context. Extensive experiments were conducted on five prevalent polyp datasets to demonstrate RSAFormer's proficiency. It achieves 92.2% and 83.5% mean Dice on Kvasir and ETIS, respectively, which outperformed most of the state-of-the-art models. © 2024 Elsevier Ltd

关键词： Decoding