检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Yihui, Qiu Rajan, Deepu College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9783031781094

Human activities are inherently task-oriented, and integrating explicit task learning into action segmentation models is hypothesized to enhance performance. However, empirical evaluations using the Ego4D Goal Step dataset reveal a paradox: the inclusion of learning tasks deteriorated model performance. This issue partially arises from limited task samples, i.e., over 50% of tasks have less than two training samples, leading to bias and overfitting in the training process. To address this, we propose a novel grammar induction method to accurately capture the hierarchical decomposition of a task with limited task samples, and use the induced grammar to guide neural predictions. Experiments demonstrate that our induction method achieves comparable results with SOTA on the Breakfast dataset with as few as two training samples for each task. Additionally, incorporating our grammar significantly boosts temporal action segmentation results for Ego4D Goal Step dataset by 8%. This approach not only mitigates data scarcity but also enhances the robustness and accuracy of action segmentation and action detection models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Context sensitive grammars

来源：评论

学校读者我要写书评

暂无评论

Optimised EfficientNet for multi-class skin cancer diagnosis: integrating chaotic grey wolf algorithms

引用

Current science 2025年第7期128卷 728-736页

作者： Rama, P. Angayarkanni, V. Theresa, W. Gracy Pandiaraj, A. Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603 203 India Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai600 123 India

The detection of skin cancer holds paramount importance worldwide due to its impact on global health. While deep convolutional neural networks (DCNNs) have shown potential in this domain, current approaches often struggle with fine-grained variability in skin lesion features, imbalanced datasets and inadequate augmentation. The objectives of our study encompass building a model that not only enhances accuracy but also reduces training time and cost, improves dimensionality reduction during classification and segmentation, and is evaluated on larger datasets for robustness. We enhance the learning process using an improved nature-inspired optimisation algorithm tailored specifically for skin cancer classification tasks. This algorithm optimises model parameters to maximise classification accuracy while minimising computational overhead. Our proposed architecture leverages a gold standard dermatological image dataset meticulously curated and validated by experts. This dataset spans eight distinct classes, including actinic keratosis, basal cell carcinoma, melanoma, nevus, and others, ensuring a diverse representation of skin conditions. The balanced class distribution in the training and test sets enables fair evaluation and robustness assessment of our deep learning models. The developed algorithm showcases novelty in its approach, contributing to advancements in early skin cancer detection technologies. This study introduces an optimised deep learning model designed for the early detection of skin cancer, achieving a notable accuracy of 97.48%. Our study aims to contribute significantly to the medical field by providing a reliable and efficient tool for dermatologists and healthcare practitioners to assist in diagnosing skin conditions accurately and promptly, ultimately improving patient outcomes and healthcare efficiency. © (2025), (Indian Academy of sciences). All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Agnostic Weakly Supervised Method For Describing Textures

An Encoder-Agnostic Weakly Supervised Method For Describing ...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Mao, Shangbo Rajan, Deepu College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798331510831

Recent advances in Large Language Models (LLMs) have enabled the semantic description of textures in natural language, aiming to capture them in richer detail. However, most methods are confined to either depending on supervised training with pairs of images and manually annotated visual attributes that most texture datasets lack or using Vision-Language Models (VLMs) such as CLIP. In this paper, we develop an encoder-agnostic Weakly supervised Texture Description Generator (WTDG) that employs a novel Scaled Ranked Kullback-Leibler divergence (SR-KL) loss between image and text modalities. Within the SR-KL loss formulation, we leverage category information, which is always available as ground-truths for all benchmark texture recognition datasets. We further extend our proposed WTDG to assist in texture recognition by using its generated texture descriptions. Thus, we develop a multimodal framework, called Tex2, which is adept at simultaneous generation of texture description and recognition. Our approach exhibits promising performance in describing and recognizing textures on benchmark datasets. © 2025 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

End-to-end Compilation is All FPGAs Need: A Unified Overlay-based FPGA Compiler for Deep Learning 25

End-to-end Compilation is All FPGAs Need: A Unified Overlay-...

引用

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Qian, Kai Lu, Haodong Liu, Yinqiu Zhang, Zexu Wang, Kun School of Microelectronics Fudan University China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798400706356

Field-Programmable Gate Array (FPGA) has shown great application potential in deploying Neural Networks (NNs) due to the characteristics of programmability, low power consumption, etc. However, deploying NNs on FPGA is non-trivial because (1) Mainstream NNs pose significant FPGA architecture design challenges due to their large number of parameters, complex operations, and the need for data optimization, and (2) Supporting the deployment of different machine learning frameworks to FPGA requires significant manual effort, consuming a large amount of time. In this paper, we propose AutoCompiler, a unified compiler for mapping NNs to different FPGAs, along with overlay techniques to enable fast and efficient implementation. To the best of our knowledge, we are the first work to support both Deep Neural Networks (DNNs) and Transformer-based networks for overlay-based FPGA deployment. AutoCompiler comprises three integrated enablers: (1) Model Translator, built on top of a topology-based NNs representation, which can optimize the topology and data representation of the models from an algorithmic level based on different hardware configurations, e.g., DSP utilization, (2) Instruction Generator, which generates pipeline data streams according to various FPGA resource configurations by manipulating the instruction set at the upper level rapidly, and (3) End-to-end optimization, which moves as much of the computational processes as possible onto the FPGA chip and minimizes the interaction between CPU and FPGA. Extensive experiments on various Xilinx FPGAs show that AutoCompiler outperforms state-of-the-art overlay-based compiler by 1.2× - 1.35× and same-level GPUs by 1.15× - 1.59× for classic DNN models, and ViT inference, respectively. © 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Reasoning with Trees: Faithful Question Answering over Knowledge Graph 31

Reasoning with Trees: Faithful Question Answering over Knowl...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Shen, Tiesunlong Wang, Jin Zhang, Xuejie Cambria, Erik School of Information Science and Engineering Yunnan University Kunming China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761964

Recent advancements in large language models (LLMs) have shown remarkable progress in reasoning capabilities, yet they still face challenges in complex, multi-step reasoning tasks. This study introduces Reasoning with Trees (RwT), a novel framework that synergistically integrates LLMs with knowledge graphs (KGs) to enhance reasoning performance and interpretability. RwT reformulates knowledge graph question answering (KGQA) as a discrete decision-making problem, leveraging Monte Carlo Tree Search (MCTS) to iteratively refine reasoning paths. This approach mirrors human-like reasoning by dynamically integrating the LLM's internal knowledge with external KG information. We propose a real-data guided iteration technique to train an evaluation model that assesses action values, improving the efficiency of MCTS. Experimental results on two benchmark KGQA datasets demonstrate that RwT significantly outperforms existing state-of-the-art methods, with an average performance improvement of 9.81%. Notably, RwT achieves these improvements without requiring complete LLM retraining, offering a more efficient and adaptable approach to enhancing LLM reasoning capabilities. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

DkvSSO: Delegatable Keyed-Verification Credentials for Efficient Anonymous Single Sign-on

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4196-4211页

作者： Xue, Wenyi Yang, Yang Huang, Minming Li, Yingjiu Pang, Hwee Hwa Deng, Robert H. Fuzhou University College of Computer and Data Science Fuzhou350116 China Singapore Management University School of Computing and Information Systems 188065 Singapore University of Oregon Department of Computer and Information Science United States

Anonymous single sign-on (ASSO) is an anonymous multi-service authentication method for end users. However, existing ASSO schemes suffer from heavy ticket requesting and verifying overheads, limiting their applications in large-scale settings. To address this problem, we propose a novel concept called keyed-verification anonymous credentials with disposable delegation (KVAC-DD) in the multi-verifier setting. Next, we extend KVAC-DD to build an efficient ASSO system, dubbed DkvSSO. The construction of DkvSSO can be instantiated in efficient prime-order groups, avoiding costly operations required in previous ASSO systems. We formally prove the security of our proposed constructions. Extensive experiments show that DkvSSO is significantly more efficient than existing ASSO schemes, making it suitable to be deployed in large-scale settings. © 2025 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

JDC-GCN: joint diversity and consistency graph convolutional network

引用

Neural computing and Applications 2025年 1-17页

作者： Lin, Renjie Yao, Jie Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China

In real-world scenarios, multi-view data comprises heterogeneous features, with each feature corresponding to a specific view. The objective of multi-view semi-supervised classification is to enhance classification performance by leveraging the inherent complementary and consistent information present within diverse views. Nevertheless, many existing frameworks primarily focus on assigning suitable weights to different views while neglecting the importance of consistent information. In this paper, a multi-view semi-supervised classification framework called joint diversity and consistency graph convolutional network (JDC-GCN) is proposed. Firstly, the structure of graph convolutional network is introduced to the multi-view semi-supervised classification, capable of propagating the label information over the topological structure of multi-view data. Secondly, the proposed JDC-GCN captures the complementary and consistent information from multiple views through two indispensable sub-modules, Diversity-GCN and Consistency-GCN, respectively. Finally, the attention mechanism is leveraged to dynamically adjust the weights of various views, allowing us to measure the significance of heterogeneous features and the consistent graph without introducing additional parameters. Comprehensive experiments on eight multi-view datasets are conducted to validate the effectiveness of the JDC-GCN algorithm. The results show that the proposed method exhibits superior classification performance compared to other state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Adaptive Masked Structural Learning for Graph-Level Clustering

引用

IEEE Transactions on Network science and Engineering 2025年第3期12卷 2021-2032页

作者： Yang, Jinbin Cai, Jinyu Zhang, Yunhe Huang, Sujia Wang, Shiping Fuzhou University College of Computer and Data Science Fuzhou350116 China Bank of Quanzhou Company Ltd. Quanzhou362046 China National University of Singapore Institute of Data Science 117602 Singapore Shenzhen Research Institute of Big Data Shenzhen518172 China Chinese University of Hong Kong Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen518172 China

Graph data presents a vast landscape for real-world applications. Current graph-level clustering approaches predominantly utilize graph neural networks to capture the intricate structural information for graph data. However, a significant challenge arises in effectively integrate structural and feature information under the prevalent noise in the real-world scenario. The advent of masking strategies has marked significant strides in boosting model robustness, accommodating incomplete data, and enhancing generalization capabilities. Yet, research attention on leveraging mask strategy for facilitating graph-level clustering is still limited. In this paper, we introduce a novel graph-level clustering method, towards adaptive masked structural learning for graph-level clustering. The method performs adaptive masking through reconstruction loss, and jointly adaptive mask representation learning and clustering in an end-to-end unsupervised framework. The mutual information between maximized the entire graph and substructure representations is also utilized to learn to generate cluster-oriented graph-level representations. Extensive experiments on eight real graph-level benchmark datasets demonstrate the effectiveness and superiority of the proposed method. © 2013 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Successive Interference Cancellation-Enabled Timely Status Update in Linear Multi-hop Wireless Networks

引用

IEEE Transactions on Mobile computing 2025年第06期24卷 5298-5311页

作者： Han, Xinhui Pan, Haoyuan Wang, Zhaorui Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen China Future Network of Intelligence Institute The School of Science and Engineering Shenzhen China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology The College of Computer Science and Software Engineering Shenzhen China

We investigate the timely status update in linear multi-hop wireless networks, where a source tries to deliver status update packets to a destination through a sequence of half-duplex relays. Timeliness is measured by the age of information (AoI) metric. Maintaining a low AoI at the destination typically necessitates frequent transmission of update packets from the source. However, high packet transmission frequency in multi-hop scenarios can result in mutual wireless interference at intermediate relays. Specifically, when an intermediate relay receives wireless signals of a new packet from its previous node, simultaneous transmission of an old packet by its subsequent node to the next hop may cause wireless signals to interfere at the intermediate relay, conventionally leading to packet collision. A key motivation to solve this issue is that the intermediate relay has previously received the old packet (which can thus be forwarded to the subsequent node for further relaying). Hence, successive interference cancellation (SIC) can be employed to mitigate interference of the old packet and recover the new packet. This paper designs an SIC-enabled packet relaying scheme tailored to low AoI. Initially focusing on a three-hop network, we subsequently extend our approach to general multi-hop networks. We model the multi-hop relaying scheme using a Markov chain to derive the theoretical average AoI. Theoretical and simulation results indicate that the SIC-enabled packet relaying scheme significantly reduces the average AoI compared to the non-SIC approaches, owing to an increased packet transmission frequency at the source and the effectiveness of SIC techniques at the relays. © 2002-2012 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defense

引用

IEEE Transactions on Knowledge and data Engineering 2025年第6期37卷 3372-3385页

作者： Li, Wenjie Fan, Kai Zhang, Jingyuan Li, Hui Lim, Wei Yang Bryan Yang, Qiang Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Hong Kong University of Science and Technology Department of Computer Science and Engineering 999077 Hong Kong

Federated Learning (FL) is a promising privacypreserving machine learning paradigm that allows data owners to collaboratively train models while keeping their data localized. Despite its potential, FL faces challenges related to the trustworthiness of both clients and servers, particularly against curious or malicious adversaries. In this paper, we introduce a novel framework named Federated Learning with Low-Dimensional Update Representation and Proximity-Based defense (FLURP), designed to address privacy preservation and resistance to Byzantine attacks in distributed learning environments. FLURP employs LinfSample method, enabling clients to compute the l∞ norm across sliding windows of updates, resulting in a Low-Dimensional Update Representation (LUR). Calculating the shared distance matrix among LURs, rather than updates, significantly reduces the overhead of Secure Multi- Party Computation (SMPC) by three orders of magnitude while effectively distinguishing between benign and poisoned updates. Additionally, FLURP integrates a privacy-preserving, proximitybased defense mechanism utilizing optimized SMPC protocols to minimize communication rounds. Our experiments demonstrate FLURP's effectiveness in countering Byzantine adversaries with low communication and runtime overhead. FLURP offers a scalable framework for secure and reliable FL in distributed environments, facilitating its application in scenarios requiring robust data management and security. © 2025 IEEE.

关键词： Federated 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：