检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zaidi, Syed Aun Muhammad Latif, Siddique Qadir, Junaid USQ Australia Distributed Sensing Systems Group Data61 CSIRO Australia Computer Science and Engineering Department College of Engineering Qatar University Doha Qatar

Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems are unable to achieve improved performance in cross-language settings. In this paper, we propose a Multimodal Dual Attention Transformer (MDAT) model to improve cross-language SER. Our model utilises pretrained models for multimodal feature extraction and is equipped with a dual attention mechanism including graph attention and co-attention to capture complex dependencies across different modalities and achieve improved cross-language SER results using minimal target language data. In addition, our model also exploits a transformer encoder layer for high-level feature representation to improve emotion classification accuracy. In this way, MDAT performs refinement of feature representation at various stages and provides emotional salient features to the classification layer. This novel approach also ensures the preservation of modality-specific emotional information while enhancing cross-modality and cross-language interactions. We assess our model's performance on four publicly available SER datasets and establish its superior effectiveness compared to recent approaches and baseline models. Copyright © 2023, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey

arXiv

引用

arXiv 2024年

作者： Guo, Jingcai Rao, Zhijie Chen, Zhi Guo, Song Zhou, Jingren Tao, Dacheng Department of Computing The Hong Kong Polytechnic University Hong Kong School of Electrical Engineering and Computer Science The University of Queensland BrisbaneQLD4072 Australia Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Alibaba Group Hangzhou311121 China College of Computing and Data Science Nanyang Technological University Singapore

Zero-shot image recognition (ZSIR) aims to recognize and reason in unseen domains by learning generalized knowledge from limited data in the seen domain. The gist of ZSIR is constructing a well-aligned mapping between the input visual space and the target semantic space, which is a bottom-up paradigm inspired by the process by which humans observe the world. In recent years, ZSIR has witnessed significant progress on a broad spectrum, from theory to algorithm design, as well as widespread applications. However, to the best of our knowledge, there remains a lack of a systematic review of ZSIR from an element-wise perspective, i.e., learning fine-grained elements of data and their inferential associations. To fill the gap, this paper thoroughly investigates recent advances in element-wise ZSIR and provides a sound basis for its future development. Concretely, we first integrate three basic ZSIR tasks, i.e., object recognition, compositional recognition, and foundation model-based open-world recognition, into a unified element-wise paradigm and provide a detailed taxonomy and analysis of the main approaches. Next, we summarize the benchmarks, covering technical implementations, standardized datasets, and some more details as a library [link]. Last, we sketch out related applications, discuss vital challenges, and suggest potential future directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Learnware Specification via Label-Aware Neural Embedding 39

Learnware Specification via Label-Aware Neural Embedding

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Wei Mao, Jun-Xiang Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Ministry of Education China Information Technology and Data Management Department of China Mobile Communications Group Zhejiang Co. Ltd China

ISBN: (纸本)157735897X

The learnware paradigm aims to establish a learnware dock system of numerous well-trained machine learning models, enabling users to reuse existing helpful models for their tasks instead of starting from scratch. Each learnware in the system is a well-established model submitted by its developer, associated with a specification generated by the learnware dock system. The specification characterizes the specialty of the corresponding model, enabling it to be identified accurately for new task requirements. Existing specification generation methods are mostly based on the Reduced Kernel Mean Embedding (RKME) technique, which uses the Maximum Mean Discrepancy (MMD) in the Reproducing Kernel Hilbert Space (RKHS) to seek a reduced set that characterizes the model’s capabilities. However, existing RKME-based methods mainly utilize feature information to generate specifications by assuming the existence of the ground-truth labeling function, while leaving the label information, which is capable of providing rich semantic characterization, untouched. Furthermore, the quality of the generated specifications heavily relies on the choice of the kernels, which makes it prohibitive to adapt to all real-world scenarios. In this paper, to overcome the above limitations, we propose a novel specification approach named LANE, i.e., Label-Aware Neural Embedding. In LANE, the neural embedding space is utilized to replace the RKHS, effectively circumventing the step of kernel selection and thereby addressing the dependency on kernels in existing RKME-based specification methods. More importantly, LANE uses the label information as additional supervision to enhance the generation process, resulting in specifications of superior quality. Extensive experiments demonstrate the effectiveness and superiority of the proposed LANE approach in the learnware paradigm. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Hilbert spaces

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of UAV-Carried IRS for Urban Low Altitude mmWave Communications with Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Xie, Wenwen Sun, Geng Liu, Bei Li, Jiahui Wang, Jiacheng Du, Hongyang Niyato, Dusit Kim, Dong In The College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China The College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore The College of Computing and Data Science Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering The University of Hong Kong 999077 Hong Kong The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Emerging technologies in sixth generation (6G) of wireless communications, such as terahertz communication and ultra-massive multiple-input multiple-output, present promising prospects. Despite the high data rate potential of millimeter wave communications, millimeter wave (mmWave) communications in urban low altitude economy (LAE) environments are constrained by challenges such as signal attenuation and multipath interference. Specially, in urban environments, mmWave communication experiences significant attenuation due to buildings, owing to its short wavelength, which necessitates developing innovative approaches to improve the robustness of such communications in LAE networking. In this paper, we explore the use of an unmanned aerial vehicle (UAV)-carried intelligent reflecting surface (IRS) to support low altitude mmWave communication. Specifically, we consider a typical urban low altitude communication scenario where a UAV-carried IRS establishes a line-of-sight (LoS) channel between the mobile users and a source user (SU) despite the presence of obstacles. Subsequently, we formulate an optimization problem aimed at maximizing the transmission rates and minimizing the energy consumption of the UAV by jointly optimizing phase shifts of the IRS and UAV trajectory. Given the non-convex nature of the problem and its high dynamics, we propose a deep reinforcement learning-based approach incorporating neural episodic control, long short-term memory, and an IRS phase shift control method to enhance the stability and accelerate the convergence. Simulation results show that the proposed algorithm effectively resolves the problem and surpasses other benchmark algorithms in various performances. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DynamicVisionCore: A Predictive Object Tracking Framework for Real-Time Robotics Applications

DynamicVisionCore: A Predictive Object Tracking Framework fo...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Sajja Suneel Reema Rallan R Jayakarthik R. Naveenkumar Alok Dubey Shivaputra Department of CSE(Data Science) Institute of Aeronautical Engineering Hyderabad Telangana India Department of Computer Application Lovely Professional University Phagwara Punjab Dept of Computer science Saveetha College of Liberal Arts and Sciences SIMATS Department of Computer Science and Engineering Chandigarh Colleges of Engineering Chandigarh Group of Colleges Mohali Punjab India Department of Preventive Dental Sciences College of Dentistry Jazan University Jazan Saudi Arabia Department of Electronics and Communication Engineering Dr. Ambedkar Institute of Technology Bengaluru

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

DynamicVisionCore is a novel predictive object tracking framework designed for real-time robotics applications. The system integrates YOLOv8 for object detection and DeepSORT for multi-object tracking, ensuring high accuracy and low latency. The framework achieves an impressive MOTA of 72.5% and MOTP of 80.1% on the MOT17 dataset, outperforming traditional methods such as SORT and ByteTrack. Motion prediction is enhanced using a hybrid Kalman Filter and LSTM-based model, reducing RMSE from 9.7 to 6.3 in occlusion scenarios. Additionally, the system ensures robust performance under challenging conditions, achieving 91.3% accuracy in normal lighting and 85.6% in low-light environments. The implementation is optimized for edge computing platforms like Jetson Xavier, where it achieves real-time processing at 9.7ms per frame. The system's robustness is further validated against varying lighting conditions, occlusions, motion blur, and extreme environments. This research demonstrates the efficacy of DynamicVisionCore in real-time robotic vision applications, ensuring reliable object tracking for autonomous systems. Future work will explore a daptiv e reinforcement learning strategies and improved sensor fusion techniques to further enhance tracking robustness.

关键词： Accuracy Lighting Reinforcement learning Sensor fusion Predictive models Robot sensing systems Real-time systems Robustness Object tracking Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Enhancing Aspect-based Sentiment Analysis with ParsBERT in Persian Language

arXiv

引用

arXiv 2025年

作者： Ariai, Farid Mahmoudi, Maryam Tayefeh Moeini, Ali Department of Computer Engineering University of Tehran Kish International Campus Kish Iran Data Analysis & Processing Research Group IT Research Faculty ICT Research Institute Tehran Iran School of Engineering Science College of Engineering University of Tehran Tehran Iran

In the era of pervasive internet use and the dominance of social networks, researchers face significant challenges in Persian text mining including the scarcity of adequate datasets in Persian and the inefficiency of existing language models. This paper specifically tackles these challenges, aiming to amplify the efficiency of language models tailored to the Persian language. Focusing on enhancing the effectiveness of sentiment analysis, our approach employs an aspect-based methodology utilizing the ParsBERT model, augmented with a relevant lexicon. The study centers on sentiment analysis of user opinions extracted from the Persian website 'Digikala.' The experimental results not only highlight the proposed method's superior semantic capabilities but also showcase its efficiency gains with an accuracy of 88.2% and an F1 score of 61.7. The importance of enhancing language models in this context lies in their pivotal role in extracting nuanced sentiments from user-generated content, ultimately advancing the field of sentiment analysis in Persian text mining by increasing efficiency and accuracy. © 2025, CC BY.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Flavours of Convolution for Unsupervised Aspect Extraction and Aspect-based Sentiment Analysis 7

Flavours of Convolution for Unsupervised Aspect Extraction a...

引用

7th Workshop on Natural Language for Artificial Intelligence, NL4AI 2023

作者： Chatterjee, Soumick Prakash, Sowmya Nürnberger, Andreas Genomics Research Centre Human Technopole Viale Rita Levi-Montalcini 1 Milan20157 Italy Faculty of Computer Science Otto von Guericke University Magdeburg Universitätspl. 2 Magdeburg39106 Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Universitätspl. 2 Magdeburg39106 Germany Centre for Behavioural Brain Sciences Magdeburg Germany

Sentiment analysis, the task of understanding the underlying sentiment from a given data, is frequently used in various fields, from market research to recommender systems. To analyse different sentiments for different aspects present in a given sentence, aspect-based sentiment analysis (ABSA) approaches have been proposed. The task of ABSA can be divided into two subtasks: aspect extraction (AE) and aspect-based polarity detection (ABPD). Most of the state-of-the-art approaches are based on some form of neural networks using convolutional layers. Recently, flavours of convolution, like extremely separated convolution layer (XSepConv) - which can reduce computational cost along with the parameter size of large kernels and depth-wise over-parameterised convolutional layer (DOConv) - which can improve the training efficiency, have been proposed. They have shown their superior capabilities when it comes to image-related tasks, but they have not been explored for textual tasks like ABSA. This paper performs unsupervised AE and weakly supervised ABSA using those specialised convolutional layers. It could be shown that using such layers instead of traditional convolutional layers can significantly improve the performance of the model. © 2023 Copyright for this paper by its authors.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Towards reliable data-based optimal and predictive control using extended DMD

引用

IFAC-PapersOnLine 2023年第1期56卷 169-174页

作者： Manuel Schaller Karl Worthmann Friedrich Philipp Sebastian Peitz Feliks Nüske Technische Universität Ilmemau Institute of Mathematics Optimization-based Control group Germany Paderborn University Department of Computer Science Data Science for Engineering Germany Max Planck Institute for Dynamics of Complex Technical Systems Magdeburg Germany

While Koopman-based techniques like extended Dynamic Mode Decomposition are nowadays ubiquitous in the data-driven approximation of dynamical systems, quantitative error estimates were only recently established. To this end, both sources of error resulting from a finite dictionary and only finitely-many data points in the generation of the surrogate model have to be taken into account. We generalize the rigorous analysis of the approximation error to the control setting while simultaneously reducing the impact of the curse of dimensionality by using a recently proposed bilinear approach. In particular, we establish uniform bounds on the approximation error of state-dependent quantities like constraints or a performance index enabling data-based optimal and predictive control with guarantees.

关键词： Approximation error data-based dictionary size eDMD estimation error finite data Koopman predicted control projection error optimal control

来源：评论

学校读者我要写书评

暂无评论

computer Vision and Its Algorithmic Evolution in Image Understanding

Computer Vision and Its Algorithmic Evolution in Image Under...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： B S Smitha Alok Jain D Sreenivasulu Saurabh Sharma B. Ravali Reddy Taqi Mohammed Khattab Al-Rubaye Department of Automobile Engineering New Horizon College of Engineering Bangalore India Lovely Professional University Phagwara India Computer Science and Engineering (Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad India Lloyd Law College Plot No. 11 Knowledge Park II Greater Noida Uttar Pradesh Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana India Department of Medical Laboratory Technology College of Medical Technologies The Islamic University Najaf Iraq

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

As computer vision systems have improved, mostly through machine vision progress, people’s views on pictures have changed a lot. In response to this change, the Dynamic AdaptNet project is making an advanced system for analysing pictures that uses data from the surroundings. The manuscripts goals is to offer a full range of features, such as dynamic convolutional neural networks (CNNs), adaptable segmentation, and temporal attention. Standard, Baseline, Enhanced, Advanced, Optimised, and Specialised are some of the choices for the system. Standard is the easiest and most important to use. This study compares and contrasts different methods by checking how well they work based on several factors, such as success, adaptability, and resilience. Independent reviews and comparisons show that Dynamic AdaptNet is a complete tool for real-time picture analysis. This shows that it has the ability to make computer vision better.

关键词： computer vision Visualization Image segmentation Shape Reviews Heuristic algorithms Object segmentation Robustness Standards Resilience

来源：评论

学校读者我要写书评

暂无评论

The Power of Bamboo: On the Post-Compromise Security for Searchable Symmetric Encryption 30

The Power of Bamboo: On the Post-Compromise Security for Sea...

引用

30th Annual Network and Distributed System Security Symposium, NDSS 2023

作者： Chen, Tianyang Xu, Peng Picek, Stjepan Luo, Bo Susilo, Willy Jin, Hai Liang, Kaitai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Cluster and Grid Computing Lab School of Computer Science and Technology China Huazhong University of Science and Technology Wuhan430074 China Digital Security Group Radboud University Nijmegen Netherlands Department of EECS Institute of Information Sciences The University of Kansas LawrenceKS United States Institute of Cybersecurity and Cryptology School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628 CD Netherlands

ISBN: (纸本)1891562835

Dynamic searchable symmetric encryption (DSSE) enables users to delegate the keyword search over dynamically updated encrypted databases to an honest-but-curious server without losing keyword privacy. This paper studies a new and practical security risk to DSSE, namely, secret key compromise (e.g., a user’s secret key is leaked or stolen), which threatens all the security guarantees offered by existing DSSE schemes. To address this open problem, we introduce the notion of searchable encryption with key-update (SEKU) that provides users with the option of non-interactive key updates. We further define the notion of post-compromise secure with respect to leakage functions to study whether DSSE schemes can still provide data security after the client’s secret key is compromised. We demonstrate that post-compromise security is achievable with a proposed protocol called "Bamboo". Interestingly, the leakage functions of Bamboo satisfy the requirements for both forward and backward security. We conduct a performance evaluation of Bamboo using a real-world dataset and compare its runtime efficiency with the existing forward-and-backward secure DSSE schemes. The result shows that Bamboo provides strong security with better or comparable performance. © 2023 30th Annual Network and Distributed System Security Symposium, NDSS 2023. All Rights Reserved.

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：