检索结果-内蒙古大学图书馆

Sparse and Dense: Learning Confusion Representation Network for 3D Action Recognition

IEEE Internet of Things Journal 2025年第12期12卷 21240-21254页

作者： Hou, Xinran Geng, Pei Li, Tianchen Li, Yalin Li, Yan Lyu, Lei School of Information Science and Engineering Shandong Normal University Jinan250358 China School of Information Engineering Shandong Management University Jinan250100 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250358 China

In the field of the Internet of Medical Things (IoMT), the demand for Human Action Recognition (HAR) is growing. Due to the limitations of portability and privacy of traditional sensors, many endeavors have made significant progress in 3D skeleton-based action recognition. However, existing methods ignore potential higher-order semantic information between joints and fail to perceive rapidly changing dynamic details, resulting in frequent confusion of actions with similar motion trajectories. To alleviate this issue, we propose a novel learning confusion representation network (LCR-Net). Specifically, a progressive feature enhancement module is first designed to utilize self-attention to gradually aggregate lower-order features to higher-order features, emphasizing the relative movement between body parts. Second, we design the enhanced spatiotemporal convolution to explore the potential spatio-temporal dependencies between joints by adding a mask matrix and an attention fusion mechanism. To further perceive the spatiotemporal relationships in subtle changes, we divide the interactive sparse-dense pathways at different spatio-temporal resolutions and enhance the complementary information between the two pathways through feature interaction. Finally, the frequency excitation learning module is proposed to efficiently learn the importance of different frequencies by cross-channel modeling, promoting the compactness of actions within classes and the separability of confusion actions. In addition, the lightweight LCR-Net+ is achieved through model compression optimization to meet the deployment requirements of IoT systems. Comprehensive experiments conducted on three public datasets (NTU-RGB+ D60&120, NW-UCLA) demonstrate the superior performance of our model. © 2025 IEEE. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

FAER: Fairness-aware Event-participant Recommendation in Event-based Social Networks 22

FAER: Fairness-aware Event-participant Recommendation in Eve...

引用

Proceedings of the 2022 6th International Conference on computer Science and Artificial Intelligence

作者： Yuan Liang School of Computer Science and Engineering Beihang University China and Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology China

ISBN: (纸本)9781450397773

An event-based social network (EBSN) is a new type of social network that combines online and offline networks. In recent years, an important task in EBSN recommendation systems has been to design better and more reasonable recommendation algorithms to improve the accuracy of recommendation and enhance user satisfaction. However, the current research seldom considers how to coordinate fairness among individual users and reduce the impact of individual unreasonable feedback in group event recommendation. In addition, while considering the fairness of individuals, the accuracy of recommendation is less improved by fully combining the context key information. To solve these problems, we propose a prefiltering algorithm to filter the candidate event set, a multidimensional context recommendation to provide personalized event recommendations for each user in the group. Finally, we verify the effectiveness of our proposed algorithm in real data sets and find that FAGR is superior to the latest algorithms in terms of global satisfaction, distance satisfaction and user fairness.

关键词： Fairness-aware Event-participant recommendation Event-based social networks

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

arXiv

引用

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer 37

DPText-DETR: Towards Better Scene Text Detection with Dynami...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Ye, Maoyuan Zhang, Jing Zhao, Shanshan Liu, Juhua Bo, Du Tao, Dacheng Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China The University of Sydney Australia JD Explore Academy National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

ISBN: (纸本)9781577358800

Recently, Transformer-based methods, which predict polygon points or Bezier curve control points for localizing texts, are popular in scene text detection. However, these methods built upon detection transformer framework might achieve sub-optimal training efficiency and performance due to coarse positional query modeling. In addition, the point label form exploited in previous works implies the reading order of humans, which impedes the detection robustness from our observation. To address these challenges, this paper proposes a concise Dynamic Point Text DEtection TRansformer network, termed DPText-DETR. In detail, DPText-DETR directly leverages explicit point coordinates to generate position queries and dynamically updates them in a progressive way. Moreover, to improve the spatial inductive bias of non-local self-attention in Transformer, we present an Enhanced Factorized Self-Attention module which provides point queries within each instance with circular shape guidance. Furthermore, we design a simple yet effective positional label form to tackle the side effect of the previous form. To further evaluate the impact of different label forms on the detection robustness in real-world scenario, we establish an Inverse-Text test set containing 500 manually labeled images. Extensive experiments prove the high training efficiency, robustness, and state-of-the-art performance of our method on popular benchmarks. The code and the Inverse-Text test set are available at https://***/ymy-k/DPText-DETR. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Research on Visual Slam Technology for UAV Positioning and Navigation

Research on Visual Slam Technology for UAV Positioning and N...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： ZHOU WANG LIU ZHIHAO TIAN YING YANG YUJUN School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer and Software Engineering Xihua University Chengdu China Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College LuZhou China College of Computer and Artificial Intelligence (Software College) Huaihua University Huaihua China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

UAV (Unmanned Aerial Vehicle) navigation can be considered as the process of robots that determine how to successfully and quickly reach the target location. Specifically, in order to complete the scheduled task successfully, the UAV must accurately understand its status, such as position, navigation speed, heading, as well as the starting point and target position. Moreover, it mainly depends on the current environment and location. This article generally focuses on the research on visual SLAM (Simultaneous localization and mapping) for UAV positioning and navigation.

关键词： Visualization Simultaneous localization and mapping Navigation Information processing Media Autonomous aerial vehicles Robots

来源：评论

学校读者我要写书评

暂无评论

Causality-Guided Context-Aware Multimodal Public Speaking Anxiety Detection for Out-of-Distribution Generalization

Causality-Guided Context-Aware Multimodal Public Speaking An...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tingting Zhang Jiachen Tan Zihua Xiong Bin Wu Chunping Zheng Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China School of Humanities Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Public Speaking Anxiety Detection (PSAD) is a complex and challenging task that involves detecting anxiety through diverse multimodal cues. While deep neural networks have achieved remarkable success in this task, their performance tends to degrade significantly under distribution shifts, especially in Out-Of-Distribution (OOD) scenarios. Given the substantial impact of latent contexts in PSAD, it is crucial to explore how contexts influence OOD generalization. Causality plays a fundamental role in uncovering the relationships between multimodal data and labels. Understanding these causal relationships helps tackle the OOD generalization challenge via causal invariance under context-driven shifts. In this work, we propose a novel Context-Aware Multimodal Adversarial Learning (CAMAL) framework to model and debias complex multimodal contexts in PSAD. A dual adversarial learning strategy jointly optimizes the causal independence between multimodal causal features and contexts. Experimental results on two benchmark datasets demonstrate the superiority of our approach over state-of-the-art baselines under distribution shifts.

关键词： Training Anxiety disorders Cause effect analysis Artificial neural networks Signal processing Benchmark testing Speech Adversarial machine learning Speech processing Context modeling

来源：评论

学校读者我要写书评

暂无评论

FreqSense: Universal and Low-Latency Adversarial Example Detection for Speaker Recognition with Interpretability in Frequency Domain

FreqSense: Universal and Low-Latency Adversarial Example Det...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yihuan Huang Yuanzhe Li Yanzhen Ren Weiping Tu Yuhong Yang Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speaker recognition (SR) systems are particularly vulnerable to adversarial example (AE) attacks. To mitigate these attacks, AE detection systems are typically integrated into SR systems. To overcome the limitations of low detection accuracy, poor generalization, and high latency in existing schemes, this paper proposes FreqSense, an AE detection scheme based on frequency distribution features. FreqSense detects a variety of unknown AE attacks with low latency, and provides interpretability in its detection process. The basic idea of FreqSense is that AE typically introduce carefully designed noise in specific frequency bands that are associated with highly distinctive speaker identities. Therefore, leveraging the distributional variations in these frequency bands can effectively distinguish between AE and benign audio. FreqSense models frequency distribution features by integrating time-frequency transformation technology with a self-attention mechanism and employs a neural network-based classifier to distinguish between AE and benign audio. Experimental results show that FreqSense achieves an overall detection accuracy of 99.2%, surpassing state-of-the-art (SOTA) schemes by 27.2%. When confronting unknown AE attacks, FreqSense achieves a detection accuracy of 98.3% with a latency of just 0.0014 seconds.

关键词： Time-frequency analysis Accuracy Noise Speech recognition Feature extraction Acoustics Speaker recognition Low latency communication Speech processing

来源：评论

学校读者我要写书评

暂无评论

Inner-approximate Reachability Computation via Zonotopic Boundary Analysis

arXiv

引用

arXiv 2024年

作者： Ren, Dejin Liang, Zhen Wu, Chenyu Ding, Jianqiang Wu, Taoran Xue, Bai Key Laboratory of System Software Chinese Academy of Sciences 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 Computer Science and Technology National University of Defense Technology Changsha China Department of Electrical Engineering and Automation Aalto University Espoo Finland

Inner-approximate reachability analysis involves calculating subsets of reachable sets, known as inner-approximations. This analysis is crucial in the fields of dynamic systems analysis and control theory as it provides a reliable estimation of the set of states that a system can reach from given initial states at a specific time instant. In this paper, we study the inner-approximate reachability analysis problem based on the set-boundary reachability method for systems modelled by ordinary differential equations, in which the computed inner-approximations are represented with zonotopes. The set-boundary reachability method computes an inner-approximation by excluding states reached from the initial set’s boundary. The effectiveness of this method is highly dependent on the efficient extraction of the exact boundary of the initial set. To address this, we propose methods leveraging boundary and tiling matrices that can efficiently extract and refine the exact boundary of the initial set represented by zonotopes. Additionally, we enhance the exclusion strategy by contracting the outer-approximations in a flexible way, which allows for the computation of less conservative inner-approximations. To evaluate the proposed method, we compare it with state-of-the-art methods against a series of benchmarks. The numerical results demonstrate that our method is not only efficient but also accurate in computing inner-approximations. Copyright © 2024, The Authors. All rights reserved.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Ranking Aggregation with Interactive Feedback for Collaborative Person Re-identification 33

Ranking Aggregation with Interactive Feedback for Collaborat...

引用

33rd British Machine Vision Conference Proceedings, BMVC 2022

作者： Huang, Ji Liang, Chao Zhang, Yue Wang, Zhongyuan Zhang, Chunjie National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing Jiaotong University Beijing100044 China

Person re-identification (re-ID) aims to retrieve the same person from a group of networking cameras. Ranking aggregation (RA), a method to aggregates multiple ranking results, can further improve the retrieval accuracy in re-ID tasks. Existing RA work can be generally divided into unsupervised methods and fully-supervised methods. Unsupervised methods lack external supervision, can hardly achieve the optimal results. In contrast, fully-supervised methods need massive labeling data for training, which is prohibitively expensive in the practical application. This paper studies interactive RA (IRA) to address the above challenges in existing RA research. The core idea is to utilize a small amount of supervisory information, obtained from users' relevance feedback, to supervise RA method to produce better re-ranking results. Compared with unsupervised methods, IRA introduces supervisory information and thus has better aggregation accuracy. Compared with fully-supervision methods, the supervisory information of IRA is more readily available, and can be targeted to specific queries. Particularly, we propose two IRA implementations, based on ranking positions and scores respectively, to adapt to diverse application scenarios, where rankers only give rankings, or rankers give similarity scores. Experiments on three public re-ID datasets have shown that IRA significantly outperforms the-state-of-art unsupervised baselines, and achieves similar accuracy with less labeling cost than the fully-supervised RA method. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance 26

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wang, Feiyu Zhou, Jian-Tao Guo, Xu Inner Mongolia University College of Computer Science Inner Mongolia Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Engineering Research Center of Ecological Big Data Ministry of Education Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software China

ISBN: (纸本)9798350331684

In a multi-cloud storage system, provenance data records all operations and ownership during its lifecycle, which is critical for data security and audibility. However, recording provenance data also poses some challenging security and storage issues. In this paper, we present a secure and efficient multi-cloud storage data source scheme, BMDP. We use blockchain technology to ensure the secure storage of provenance data and design a smart contract to utilize the provenance data to ensure the proper operation of the multi-cloud storage system. Finally, we analyze the scheme's safety and do simulation experiments to show that the scheme has practicality. © 2023 IEEE.

关键词： Smart contract

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：