检索结果-内蒙古大学图书馆

Dual-Recommendation Disentanglement Network for View Fuzz in Action Recognition

IEEE Transactions on Image Processing 2023年 32卷 2719-2733页

作者： Liu, Wenxuan Zhong, Xian Zhou, Zhuo Jiang, Kui Wang, Zheng Lin, Chia-Wen Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Wuhan University of Technology Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan430070 China Peking University School of Electronics Engineering and Computer Science Beijing100091 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Wuhan University School of Computer Science Wuhan430072 China National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Multi-view action recognition aims to identify action categories from given clues. Existing studies ignore the negative influences of fuzzy views between view and action in disentangling, commonly arising the mistaken recognition results. To this end, we regard the observed image as the composition of the view and action components, and give full play to the advantages of multiple views via the adaptive cooperative representation among these two components, forming a Dual-Recommendation Disentanglement Network (DRDN) for multi-view action recognition. Specifically, 1) For the action, we leverage a multi-level Specific Information Recommendation (SIR) to enhance the interaction among intricate activities and views. SIR offers a more comprehensive representation of activities, measuring the trade-off between global and local information. 2) For the view, we utilize a Pyramid Dynamic Recommendation (PDR) to learn a complete and detailed global representation by transferring features from different views. It is explicitly restricted to resist the fuzzy noise influence, focusing on positive knowledge from other views. Our DRDN aims for complete action and view representation, where PDR directly guides action to disentangle with view features and SIR considers mutual exclusivity of view and action clues. Extensive experiments have indicated that the multi-view action recognition method DRDN we proposed achieves state-of-the-art performance over powerful competitors on several standard benchmarks. The code will be available at https://***/51cloud/DRDN. © 1992-2012 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Multi-perspective Feature Fusion for Event-Event Relation Extraction 12th

Multi-perspective Feature Fusion for Event-Event Relation E...

引用

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Liu, Wei Pang, Zhangdeng Xie, Shaorong Li, Weimin School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (纸本)9783031446955

Event-Event Relation Extraction (EERE) is a crucial task in the information extraction domain, which aims to obtain the relation between events and understand the relation structure of the event chain in a document. Existing methods mainly focused on single-event relations, such as causality, while only utilizing trigger words or semantic span as model inputs, ignoring the impact of event arguments and contextual features on events. Hence, we propose a novel Multi-Perspective Graph feature Fusion (MPGF) model. We model event triggers, arguments, sentences, and document context as heterogeneous graphs and transform event relation prediction into a graph edge classification problem. Applying three graph feature fusion strategies from different perspective to complete the node representation learning and learn local and global semantic features. At the same time, our model architecture can be flexibly adjusted according to different graph algorithm combinations. Extensive experiments on two benchmark datasets show that MPGF significantly outperforms previous SOTA methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming

Be a Multitude to Itself: A Prompt Evolution Framework for R...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Li, Rui Wang, Peiyi Ma, Jingyuan Zhang, Di Sui, Zhifang Sha, Lei State Key Laboratory of Multimedia Information Processing School of Computer Science Peking University China Institute of Artificial Intelligence Beihang University China

ISBN: (纸本)9798891761681

Large Language Models (LLMs) have gained increasing attention for their remarkable capacity, alongside concerns about safety arising from their potential to produce harmful content. Red teaming aims to find prompts that could elicit harmful responses from LLMs, and is essential to discover and mitigate safety risks before real-world deployment. However, manual red teaming is both time-consuming and expensive, rendering it unscalable. In this paper, we propose RTPE, a scalable evolution framework to evolve red teaming prompts across both breadth and depth dimensions, facilitating the automatic generation of numerous high-quality and diverse red teaming prompts. Specifically, in-breadth evolving employs a novel enhanced in-context learning method to create a multitude of quality prompts, whereas in-depth evolving applies customized transformation operations to enhance both content and form of prompts, thereby increasing diversity. Extensive experiments demonstrate that RTPE surpasses existing representative automatic red teaming methods on both attack success rate and diversity. In addition, based on 4,800 red teaming prompts created by RTPE, we further provide a systematic analysis of 8 representative LLMs across 8 sensitive topics. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

GamEmotion: A Serious Game for Emotion Regulation in Young Adolescents

GamEmotion: A Serious Game for Emotion Regulation in Young A...

引用

IEEE Symposium on Computational intelligence and Games, CIG

作者： Eliana Silva Pedro França Luís Paulo Reis LIACC/ FEUP Artificial Intelligence and Computer Science Lab Faculty of Engineering University of Porto Porto Portugal

ISBN: (数字)9798350350678

ISBN: (纸本)9798350350685

Serious games (SGs) have emerged as an appropriate intervention for adolescents due to their significant use of video games. Although literature reviews and meta-analyses increasingly support the effectiveness and acceptability of SGs in addressing mental health problems and promoting healthy lifestyles in young people, there remains a significant gap in SGs specifically designed to improve emotion regulation (ER) skills. In response, we present the serious game GamEmotion, a 3D digital action-adventure game developed in Unity, designed to provide psychoeducation about six basic emotions (happiness, sadness, fear, anger, surprise, and disgust) and two ER strategies (cognitive reappraisal and expressive suppression). We believe that we have developed the first SG to improve emotional awareness and ER in Portuguese adolescents, based on the Gross process model, one of the most widely reported models of ER. We present the GamEmotion framework alongside our ongoing usability study protocol with young adolescents ($10-14$ years) and their parents. By proposing this innovative tool, we aim to broaden the application of SG and address specific challenges in adolescent ER to improve mental health.

关键词： Video games Pediatrics Three-dimensional displays Protocols Bibliographies Education Mental health

来源：评论

学校读者我要写书评

暂无评论

A Grassmannian Manifold Self-Attention Network for Signal Classification 33

A Grassmannian Manifold Self-Attention Network for Signal Cl...

引用

33rd International Joint Conference on artificial intelligence, IJCAI 2024

作者： Wang, Rui Hu, Chen Chen, Ziheng Wu, Xiao-Jun Song, Xiaoning School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China Department of Information Engineering and Computer Science University of Trento Trento Italy

ISBN: (纸本)9781956792041

In the community of artificial intelligence, significant progress has been made in encoding sequential data using deep learning techniques. Nevertheless, how to effectively mine useful information from channel dimensions remains a major challenge, as these features have a submanifold structure. Linear subspace, the basic element of the Grassmannian manifold, has proven to be an effective manifold-valued feature descriptor in statistical representation. Besides, the Euclidean self-attention mechanism has shown great success in capturing long-range relationships of data. Inspired by these facts, we extend the self-attention mechanism to the Grassmannian manifold. Our framework can effectively characterize the spatiotemporal fluctuations of sequential data encoded in the Grassmannian manifold. Extensive experimental results on three benchmarking datasets (a drone recognition dataset and two EEG signal classification datasets) demonstrate the superiority of our method over the state-of-the-art. The code and supplementary material for this work can be found at https://***/ChenHu-ML/GDLNet. © 2024 International Joint Conferences on artificial intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Full-duplex strategy for video object segmentation

引用

Computational Visual Media 2023年第1期9卷 155-175页

作者： Ge-Peng Ji Deng-Ping Fan Keren Fu Zhe Wu Jianbing Shen Ling Shao School of Computer Science Wuhan UniversityWuhanChina Computer Vision Lab ETH ZurichETF C113.2Sternwartstrasse 78092 ZurichSwitzerland College of Computer Science Sichuan UniversityChengduChina Peng Cheng Laboratory ShenzhenChina School of Computer Science Beijing Institute of TechnologyBeijingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Previous video object segmentation approachesmainly focus on simplex solutions linking appearance and motion,limiting effective feature collaboration between these two *** this work,we study a novel and efficient full-duplex strategy network(FSNet)to address this issue,by considering a better mutual restraint scheme linking motion and appearance allowing exploitation of cross-modal features from the fusion and decoding ***,we introduce a relational cross-attention module(RCAM)to achieve bidirectional message propagation across embedding *** improve the model’s robustness and update inconsistent features from the spatiotemporal embeddings,we adopt a bidirectional purification module after the *** experiments on five popular benchmarks show that our FSNet is robust to various challenging scenarios(e.g.,motion blur and occlusion),and compares well to leading methods both for video object segmentation and video salient object *** project is publicly available at https://***/GewelsJI/FSNet.

关键词： video object segmentation(VOS) video salient object detection(V-SOD) visual attention

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Empowered Asynchronous Federated Reinforcement Learning for IoT-Based Traffic Trajectory Prediction

引用

IEEE Internet of Things Journal 2025年第11期12卷 17095-17109页

作者： Wang, Bin Tian, Zhao Tang, Fengxiao Pan, Heng She, Wei Liu, Wei Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou450002 China Zhengzhou University School of Cyber Science and Engineering Zhengzhou450002 China Central South University School of Computer Science and Engineering Changsha410083 China Zhongyuan University of Technology School of Cyber Space Security Zhengzhou450007 China Zhengzhou University School of Cyber Science and Engineering Zhengzhou Key Laboratory of Blockchain and Data Intelligence Zhengzhou450002 China

Vehicle trajectory prediction plays a crucial role in IoT-based intelligent transportation systems, which can effectively address key issues, such as driving safety and multivehicle collaboration. However, the sensitivity of trajectory data and the reluctance of data holders to share it constrain the prediction model’s ability to capture vehicle behavior patterns in different scenarios. To address the above problems, we propose a blockchain-enabled asynchronous federated proximal policy optimization framework (BE-AFPPO) for the trajectory prediction of self-driving vehicles. First, we propose a curiosity proximal policy optimization (C-PPO) algorithm. The method utilizes a driven exploration strategy to actively motivate the intelligent agent to explore the unknown state space. The avoidance policy model reaches a local optimum when processing trajectory data. In addition, we design historical gated recurrent unit (GRU) and future GRU as input layers. The target’s historical motion features and future trajectory features are extracted, respectively. Then, various data is received through asynchronous federated learning. This model can fully learn the vehicle’s behavior patterns in different scenarios, which improves prediction accuracy. Based on this, we develop a blockchain-based dynamic group practical Byzantine fault tolerance (DG-PBFT) consensus algorithm. This enhances the credibility and integrity of the data while enriching the sources of trajectory data. Finally, we perform the experiments on the publicly available dataset nuScenes. The results demonstrate that the proposed method improves the robustness and accuracy of trajectory prediction. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Combining KNN with AutoEncoder for Outlier Detection

引用

Journal of computer science & Technology 2024年第5期39卷 1153-1166页

作者： Shu-Zheng Liu Shuai Ma Han-Qing Chen Li-Zhen Cui Jie Ding State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Software Shandong UniversityJinan 250100China Joint SDU-NTU Centre for Artificial Intelligence Research Shandong UniversityJinan 250100China School of Computer Science Jiangsu University of Science and TechnologyZhenjiang 212003China

K-nearest neighbor(KNN)is one of the most fundamental methods for unsupervised outlier detection because of its various advantages,e.g.,ease of use and relatively high ***,most data analytic tasks need to deal with high-dimensional data,and the KNN-based methods often fail due to“the curse of dimensionality”.AutoEncoder-based methods have recently been introduced to use reconstruction errors for outlier detection on high-dimensional data,but the direct use of AutoEncoder typically does not preserve the data proximity relationships well for outlier *** this study,we propose to combine KNN with AutoEncoder for outlier ***,we propose the Nearest Neighbor AutoEncoder(NNAE)by persevering the original data proximity in a much lower dimension that is more suitable for performing ***,we propose the K-nearest reconstruction neighbors(K NRNs)by incorporating the reconstruction errors of NNAE with the K-distances of KNN to detect ***,we develop a method to automatically choose better parameters for optimizing the structure of ***,using five real-world datasets,we experimentally show that our proposed approach NNAE+K NRN is much better than existing methods,i.e.,KNN,Isolation Forest,a traditional AutoEncoder using reconstruction errors(AutoEncoder-RE),and Robust AutoEncoder.

关键词： outlier detection AutoEncoder K-nearest neighbor(KNN) unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Modeling Super-Lightweight Cellular Traffic Prediction via Multiservice and Multimodal Feature Fusion Network

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第1期6卷 16-20页

作者： Li, Yingqi Hao, Mingxiang Sun, Xiaochuan Zhang, Haijun University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China North China University of Science and Technology College of Artificial Intelligence Tangshan063210 China Hebei Key Laboratory of Industrial Perception Tangshan063210 China

Cellular Traffic Prediction has proven to be a key enabler towards automatic network management. However, to pursue performance improvement, the existing studies mainly focus on developing complex deep neural network models, which suffer from extensive computation cost and large model size inevitably. Such models are quite difficult to be deployed on resource-constrained devices. In this letter, we propose a multiservice and multimodal feature fusion network for super-lightweight cellular network traffic prediction, namely m^2FFNet , to address the issue. Briefly speaking, such a network consists of a duel feature extraction channel based on grouped 3D convolution for capturing multiservice feature and multimodal feature (yielded from wavelet transform decomposition), respectively. Simulation results demonstrate that our proposal can achieve comparable prediction accuracy as the state-of-the-art deep learning methods, meanwhile obtaining much less computation burden with rather few model size. © 2019 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DPK:Deep Neural Network Approximation of the First Piola-Kirchhoff Stress

引用

Advances in Applied Mathematics and Mechanics 2024年第1期16卷 75-100页

作者： Tianyi Hu Jerry Zhijian Yang Cheng Yuan Institute of Artificial Intelligence School of Computer ScienceWuhan UniversityWuhanHubei 430072China School of Mathematics and Statistics Wuhan UniversityWuhanHubei 430072China Hubei Key Laboratory of Computational Science Wuhan UniversityWuhanHubei 430072China

This paper presents a specific network architecture for approximation of the first Piola-Kirchhoff *** neural network enables us to construct the constitutive relation based on both macroscopic observations and atomistic simulation *** contrast to traditional deep learning models,this architecture is intrinsic symmetric,guarantees the frame-indifference and material-symmetry of ***,we build the approximation network inspired by the Cauchy-Born rule and virial stress *** numerical results and theory analyses are presented to illustrate the learnability and effectiveness of our network.

关键词： Piola-Kirchhoff stress deep neural networks Cauchy-Born rule

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：