检索结果-内蒙古大学图书馆

FER-Former: Multimodal Transformer for Facial Expression Recognition

IEEE Transactions on Multimedia 2025年 27卷 2412-2422页

作者： Li, Yande Wang, Mingjie Gong, Minglun Lu, Yonggang Liu, Li Lanzhou University School of Information Science and Engineering Lanzhou730000 China University of Guelph School of Computer Science GuelphONN1G 2W1 Canada University of Alberta Department of Electrical & Computer Engineering EdmontonABT6G 1H9 Canada Zhejiang Sci-Tech University School of Science Hangzhou310018 China Chongqing University School of Big Data and Software Engineering Chongqing401331 China

The ever-increasing demands for intuitive interactions in virtual reality have led to surging interests in facial expression recognition (FER). There are however several issues commonly seen in existing methods, including narrow receptive fields and homogenous supervisory signals. To address these issues, we propose in this paper a novel multimodal supervision-steering transformer for facial expression recognition in the wild, referred to as FER-former. Specifically, to address the limitation of narrow receptive fields, a hybrid feature extraction pipeline is designed by cascading both prevailing CNNs and transformers. To deal with the issue of homogenous supervisory signals, a heterogeneous domain-steering supervision module is proposed to incorporate text-space semantic correlations to enhance image features, based on the similarity between image and text features. Additionally, a FER-specific transformer encoder is introduced to characterize conventional one-hot label-focusing and CLIP-based text-oriented tokens in parallel for final classification. Based on the collaboration of multifarious token heads, global receptive fields with multimodal semantic cues are captured, delivering superb learning capability. Extensive experiments on popular benchmarks demonstrate the superiority of the proposed FER-former over the existing state-of-the-art methods. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

FedNorm: Optimised Federated Learning Strategy Using Hybrid Regularisation Norm 12th

FedNorm: Optimised Federated Learning Strategy Using Hybrid ...

引用

12th International Conference on Big data and Artificial Intelligence, BDA 2024

作者： John, Binu Menon, Varun Adhikari, Mainak Department of Computer Science and Engineering SCMS School of Engineering and Technology Kerala Ernakulam683576 India APJ Abdul Kalam Technological University Kerala Thiruvananthapuram695016 India School of Data Science Indian Institute of Science Education and Research Vithura Kerala Thiruvananthapuram695551 India

ISBN: (纸本)9783031818202

Federated Learning (FL) has emerged as a game-changing method for training machine learning (ML) models on decentralized data sources without centralizing the data itself. Conventional FL algorithms frequently exhibit performance instability and inefficiency, especially when working with non-Independent and Identically Distributed (non-IID) data distributions. To overcome these difficulties, we present FedNorm, a new FL method that uses hybrid regularisation approach to improve model stability and accuracy by balancing sparsity and smoothness, to increase generalization across varied data distributions. Our experimental setup uses the MNIST dataset to train models in both Independent and Identically Distributed (IID) and non-IID situations. The findings show that FedNorm routinely outperforms classic algorithms like FedAvg, FedSGD, FedNova and FedSAM, with minimal test loss and high accuracy. FedNorm has an exceptional accuracy rating of 0.98 on both IID and non-IID data. FedNorm addresses the constraints of conventional FL algorithms, resulting in a strong and dependable solution for FL in diverse situations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Piccolo: Large-Scale Graph Processing with Fine-Grained in-Memory Scatter-Gather 31

Piccolo: Large-Scale Graph Processing with Fine-Grained in-M...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Shin, Changmin Song, Jaeyong Jang, Hongsun Kim, Dogeun Sung, Jun Kwon, Taehee Ju, Jae Hyung Liu, Frank Choi, Yeonkyu Lee, Jinho Seoul National University Department of Electrical and Computer Engineering Korea Republic of Old Dominion Univeristy School of Data Science United States Samsung Electronics Korea Republic of

ISBN: (纸本)9798331506476

Graph processing requires irregular, fine-grained random access patterns incompatible with contemporary off-chip memory architecture, leading to inefficient data access. This inefficiency makes graph processing an extremely memory-bound application. Because of this, existing graph processing accelerators typically employ a graph tiling-based or processing-in-memory (PIM) approach to relieve the memory bottleneck. In the tiling-based approach, a graph is split into chunks that fit within the on-chip cache to maximize data reuse. In the PIM approach, arithmetic units are placed within memory to perform operations such as reduction or atomic addition. However, both approaches have several limitations, especially when implemented on current memory standards (i.e., DDR). Because the access granularity provided by DDR is much larger than that of the graph vertex property data, much of the bandwidth and cache capacity are wasted. PIM is meant to alleviate such issues, but it is difficult to use in conjunction with the tiling-based approach, resulting in a significant disadvantage. Furthermore, placing arithmetic units inside a memory chip is expensive, thereby supporting multiple types of operation is thought to be impractical. To address the above limitations, we present Piccolo, an end-to-end efficient graph processing accelerator with fine-grained in-memory random scatter-gather. Instead of placing expensive arithmetic units in off-chip memory, Piccolo focuses on reducing the off-chip traffic with non-arithmetic function-in-memory of random scatter-gather. To fully benefit from in-memory scatter-gather, Piccolo redesigns the cache and miss-handling architecture (MHA) of the accelerator such that it can enjoy both the advantage of tiling and in-memory operations. Piccolo achieves a maximum speedup of 3.28 × and a geometric mean speedup of 1.62 ×, along with up to 59.7% reduction in energy consumption across various and extensive benchmarks. © 2025 IEEE.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Rule-Based Dialect of Tulang Bawang Stemmer

Rule-Based Dialect of Tulang Bawang Stemmer

引用

2025 International Conference on Advancement in data science, E-learning and Information System, ICADEIS 2025

作者： Abidin, Zaenal Junaidi, Akmal Wamiliana Lumbanraja, Favorisen Rosyking Kurniasari, Dian Borman, Rohmat Indra Doctoral Program of Mathematics and Natural Sciences Universitas Lampung Bandar Lampung Indonesia Universitas Lampung Department of Computer Science Bandar Lampung Indonesia Universitas Lampung Department of Mathematics Bandar Lampung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandar Lampung Indonesia

ISBN: (纸本)9798331513320

Stemming, an essential procedure in natural language processing (NLP), diminishes words to their base forms, facilitating tasks such as information retrieval and sentiment analysis. Although stemming techniques for highresource languages are well-developed, numerous low-resource languages, including dialect of Tulang Bawang, suffer from inadequate solutions owing to a scarcity of linguistic data and resources. Existing systems, including rule-based stemmers, have demonstrated efficacy in processing low-resource languages such as Indonesian and Javanese by utilizing established morphological rules. Nonetheless, these methods encounter considerable obstacles, such as restricted adaptability, inability to accommodate unusual root structures, and excessive dependence on fixed rules that might result in over- or understemming. Rule-based methodologies frequently misidentify roots when faced with intricate affixes or unconventional word forms. We introduce an improved rule-based Tulang Bawang Stemmer aimed at overcoming these constraints by enhancing current linguistic rules and integrating new patterns specific to the language's morphology. Assessed on 500 test samples and 200 independent test samples, our improved stemmer attained gold standard evaluation metrics of 96.2% and 94%, respectively, surpassing prior implementations in both precision and generalization. The findings demonstrate the potential of enhanced rule-based techniques to improving NLP for lowresource languages. Improved stemming performance enables better downstream applications, promotes more efficient text analysis, and advances research in underrepresented languages. © 2025 IEEE.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

A comprehensive evaluation of diversity measures for TCR repertoire profiling

引用

BMC Biology 2025年第1期23卷 1-18页

作者： Mika, Justyna Polanska, Alicja Blenman, Kim RM Pusztai, Lajos Polanska, Joanna Candéias, Serge Marczyk, Michal Department of Data Science and Engineering Silesian University of Technology Gliwice Poland Mullard Space Science Laboratory University College London Dorking United Kingdom Yale Cancer Center Yale School of Medicine New Haven CT United States Department of Computer Science School of Engineering and Applied Science New Haven CT United States Université Grenoble Alpes CEA CNRS IRIG-LCBM Grenoble France

Background: T cells play a crucial role in adaptive immunity, as they monitor internal and external immunogenic signals through their specific receptors (TCRs). Using high-throughput sequencing, one can assess TCR repertoire in various clinical settings and describe it quantitatively by calculating a diversity index. Multiple diversity indices that capture the richness of TCRs and the evenness of their distribution have been proposed in the literature;however, there is no consensus on gold-standard measures and interpretation of each index is complex. Our goal was to examine the performance characteristics of 12 commonly used diversity indices in simulated and real-world data. Results: Simulated data were generated to evaluate how data richness and evenness affect index values using three nonparametric models. Fourteen real-world TCR datasets were obtained to examine differences in indices by analysis protocols and test their robustness to subsampling. Pielou, Basharin, d50, and Gini primarily describe evenness and highly correlate with one another. They are best suited for measuring the representation of TCR clones. Richness is best captured by S index, next Chao1 and ACE which also consider information on evenness. Shannon, ***, D3, D4, and *** measure richness and increasingly more information on evenness. More skewed TCR distributions provided more stable results in subsampling. Gini-Simpson, Pielou, and Basharin were the most robust in both simulated and experimental data. Conclusions: Our results could guide investigators to select the best diversity index for their particular experimental question and draw attention to factors that can influence the accuracy and reproducibility of results. © The Author(s) 2025.

关键词： Diversity Evenness Immunosequencing Richness TCR profiling TCR sequencing

来源：评论

学校读者我要写书评

暂无评论

Scaling Rich Style-Prompted Text-to-Speech datasets

arXiv

引用

arXiv 2025年

作者： Diwan, Anuj Zheng, Zhisheng Harwath, David Choi, Eunsol Department of Computer Science The University of Texas Austin United States Department of Computer Science and Data Science New York University United States

We introduce Paralinguistic Speech Captions (ParaSpeechCaps), a large-scale dataset that annotates speech utterances with rich style captions. While rich abstract tags (e.g. guttural, nasal, pained) have been explored in small-scale human-annotated datasets, existing large-scale datasets only cover basic tags (e.g. low-pitched, slow, loud). We combine off-the-shelf text and speech embedders, classifiers and an audio language model to automatically scale rich tag annotations for the first time. ParaSpeechCaps covers a total of 59 style tags, including both speaker-level intrinsic tags and utterance-level situational tags. It consists of 342 hours of human-labelled data (PSC-Base) and 2427 hours of automatically annotated data (PSC-Scaled). We finetune Parler-TTS, an open-source style-prompted TTS model, on ParaSpeechCaps, and achieve improved style consistency (+7.9% Consistency MOS) and speech quality (+15.5% Naturalness MOS) over the best performing baseline that combines existing rich style tag datasets. We ablate several of our dataset design choices to lay the foundation for future work in this space. Our dataset, models and code are released at https://***/ajd12342/paraspeechcaps. Copyright © 2025, The Authors. All rights reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Communication Framework for Secure and Scalable Healthcare data Processing

Blockchain-Enabled Communication Framework for Secure and Sc...

引用

IEEE Southeastcon

作者： Debashis Das La Chiara Landrum Pushpita Chatterjee Uttam Ghosh Sajid Hussain Department of Computer Science and Data Science Meharry Medical College Nashville TN USA

ISBN: (数字)9798331504847

ISBN: (纸本)9798331504854

The need for secure and efficient communication between connected devices continues to grow in healthcare systems within smart cities. Secure communication of healthcare data in Internet of Things (IoT) systems is critical to ensure patient privacy and data integrity. Problems with healthcare communication, like data breaches, integrity issues, scalability issues, and cyber threats, make it harder for people to trust doctors, cause costs to rise, stop people from using new technology, and put private data at risk. So, this paper presents a blockchain-based hybrid method for sending secure healthcare data that combines IoT systems with blockchain technology and high-tech encryption techniques like elliptic curve cryptography (ECC). The proposed method uses the public key of a smart contract to encrypt private data to protect its privacy. It also uses cryptographic hashing and digital signatures to make sure that the data is correct and real. The framework stores metadata (e.g., hashes and signatures) on-chain, and large data uses off-chain storage like IPFS to reduce costs and improve scalability. It also incorporates a mechanism to authenticate IoT devices and enable secure communication across heterogeneous networks. Moreover, this work bridges gaps in existing solutions by providing an end-to-end secure communication system for healthcare applications. It provides strong data security and efficient storage for a reliable and scalable way to handle healthcare data safely in IoT ecosystems.

关键词： Costs Scalability data integrity Medical services Elliptic curve cryptography Real-time systems Blockchains Encryption Internet of Things Digital signatures

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impacts of Dynamic Game Balancing in a Survival Roguelike Chess Game

Analyzing the Impacts of Dynamic Game Balancing in a Surviva...

引用

Advancement in data science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Mario Yulyani Arifin Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

This research investigates the novel application of Dynamic Game Balancing (DGB) techniques in the context of a hybrid chess-survival roguelike game, a unique combination of genres not widely explored in previous studies. The study addresses two primary research questions: the identification of suitable DGB techniques for these genres and the enhancement of user experience through DGB. A game prototype was developed using Unity, where players control a chess knight in a turn-based system, facing increasingly challenging enemy pieces. The DGB system dynamically adjusts the game's difficulty based on player performance, utilizing various inputs such as damage received or dealt, health points, powerup usage, and decision speed. Preliminary results from 14 beta-testers show overall positive feedback, with players reporting higher engagement and enjoyment due to the seamless difficulty adjustments, as reflected by the high mean scores from surveys like the User Experience Questionnaire (UEQ). This research fills a gap in the literature by demonstrating the feasibility and benefits of integrating DGB in a chess-survival roguelike setting. These findings highlight the potential for DGB to significantly improve player experience in hybrid game genres, suggesting that its application can create more adaptive and immersive gaming environments in various other genres as well.

关键词： Surveys Video games Electronic learning Prototypes Games data science User experience Information systems

来源：评论

学校读者我要写书评

暂无评论

Confidence Estimation via Sequential Likelihood Mixing

arXiv

引用

arXiv 2025年

作者： Kirschner, Johannes Krause, Andreas Meziu, Michele Mutný, Mojmir Swiss Data Science Center Switzerland ETH Zurich Department of Computer Science Switzerland

We present a universal framework for constructing confidence sets based on sequential likelihood mixing. Building upon classical results from sequential analysis, we provide a unifying perspective on several recent lines of work, and establish fundamental connections between sequential mixing, Bayesian inference and regret inequalities from online estimation. The framework applies to any realizable family of likelihood functions and allows for non-i.i.d. data and anytime validity. Moreover, the framework seamlessly integrates standard approximate inference techniques, such as variational inference and sampling-based methods, and extends to misspecified model classes, while preserving provable coverage guarantees. We illustrate the power of the framework by deriving tighter confidence sequences for classical settings, including sequential linear regression and sparse estimation, with simplified proofs. Copyright © 2025, The Authors. All rights reserved.

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

Intelligent Guitar Chord Recognition Using Spectrogram-Based Feature Extraction and AlexNet Architecture for Categorization

引用

International Journal of Advanced computer science and Applications 2025年第4期16卷 758-767页

作者： Korade, Nilesh B. Salunke, Mahendra B. Bhosle, Amol A. Sangve, Sunil M. Joshi, Dhanashri M. Asalkar, Gayatri G. Kadu, Sujata R. Sarwade, Jayesh M. Department of Computer Engineering JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India Department of Computer Engineering PCET’s Pimpri Chinchwad College of Engineering and Research Ravet Maharashtra Pune412101 India Department of Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Bibwewadi Pune411037 India Department of Computer Engineering Terna Engineering College Maharashtra Mumbai India Department of Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Chord prediction plays a key role in the advancement of musical technological innovations, such as automatic music transcription, real-time music tutoring, and intelligent composition tools. Accurate chord prediction can assist musicians, educators, and developers in constructing tools that help in learning, playing, and composing music. Background noise and audio distortions may have an impact on chord prediction accuracy, particularly in real-world situations. Chords can have distinct voicings or finger positions on the guitar, resulting in slight variations in audio representation. This study focuses on the classification of guitar chords using techniques of deep learning. There are eight major and minor guitar chords in the dataset. They have been turned into spectrograms, chromagrams, and Mel Frequency Cepstral Coefficients (MFCC) so that features can be extracted. Various deep learning architectures, including CNN, ResNet50, AlexNet, and VGG, were employed to classify the chords. Experimental results demonstrated that the spectrogram-based AlexNet model outperforms others, achieving good accuracy and robustness in chord classification. The proposed study demonstrates the efficiency of spectrograms and advanced deep learning models for audio signal processing in music applications. By automating chord detection, this study provides beneficial resources for music learners as well as educators, enabling more efficient learning and real-time feedback during practice sessions. © (2025), (science and Information Organization). All Rights Reserved.

关键词： Deep learning

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：