检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Xiaoliang Shen, Furao Han, Feng Zhao, Jian Nie, Changhai National Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Face recognition (FR) technology plays a crucial role in various applications, but its vulnerability to adversarial attacks poses significant security concerns. Existing research primarily focuses on transferability to different FR models, overlooking the direct transferability to victim's face images, which is a practical threat in real-world scenarios. In this study, we propose a novel adversarial attack method that considers both the transferability to the FR model and the victim's face image, called NeRFTAP. Leveraging Neural Radiance Fields (NeRF)-based 3D Generative Adversarial Network (GAN), we generate new view face images for the source and target subjects to enhance transferability of adversarial patches. We introduce a style consistency loss to ensure the visual similarity between the adversarial UV map and the target UV map under a 0-1 mask, enhancing the effectiveness and naturalness of the generated adversarial face images. Extensive experiments and evaluations on various FR models demonstrate the superiority of our approach over existing attack techniques. Our work provides valuable insights for enhancing the robustness of FR systems in practical adversarial settings. © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Supervised Contrastive Learning with Prototype Distillation for Data Incremental Learning

SSRN

引用

SSRN 2024年

作者： Yang, Suorong Zhang, Tianyue Xu, Baile Shen, Furao Zhao, Jian State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

The goal of Data Incremental Learning (DIL) is to enable learning from small-scale data batches from non-stationary data streams without clear task divisions. This approach often encounters the issue of catastrophic forgetting in deep neural networks. Meanwhile, practical applications may involve unbalanced data distributions across classes. To address the challenges of DIL, using prototypes as classifiers offers a balance between stability and flexibility. This facilitates the preservation of information from previous classes while evolving to accommodate new ones. Prototypes are particularly effective for classifying separable embeddings in the feature space, as they draw embeddings from the same class closer together while pushing those from different classes further apart. This aligns with the objective of contrastive learning. In this paper, we propose Supervised Contrastive learning with the Prototype Distillation (SCPD) method for the DIL problem. First, we employ supervised contrastive loss (SCL) for model training. To further mitigate the forgetting problem, we introduce the prototype distillation loss, which ensures that features remain close to their corresponding prototypes. Exemplar memory is utilized to store representative samples, enabling the model to maintain performance on previously learned tasks. Moreover, data augmentation techniques are applied to improve the models' robustness and continual learning capability. Experimental results demonstrate that the SCPD model outperforms prior state-of-the-art approaches across several benchmarks, including those with various imbalanced setups. Code will be made publicly available soon. © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Adapting MaryTTS for Synthesizing Sinhalese Speech to Communicate with Children 6

Adapting MaryTTS for Synthesizing Sinhalese Speech to Commun...

引用

6th International Conference on Information technology Research, ICITR 2021

作者： Lakmal, M.A.J.A. Methmini, K.A.D.G. Rupasinghe, D.M.H.M. Hettiarachchi, D.I. Piyawardana, Vijani Senarathna, Manuri Reyal, Shyam Pulasinghe, Koliya Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781665420006

The majority of the Sri Lankan population speak Sinhala, which is also the country's mother tongue. Sinhala is a difficult language to learn by children aged between 1-6 years when compared to other languages. Text to speech system is popular among children who have difficulties with reading, especially those who struggle with decoding. By presenting the words auditorily, the child can focus on the meaning of words instead of spending all their brainpower trying to sound out the words. In Sri Lanka, however, computer systems based on the Sinhala language especially for children are extremely rare. In this situation having a Sinhala text-to-speech technology for communicating with children is a helpful option. Intelligibility should be considered deeply in this system because this is specific for children. Recordings of a native Sinhalese speaker were used to synthesize a natural-sounding voice, rather than a robotic voice. This paper proposes an approach of implementing a Sinhalese text-to-speech system for communicating with children using unit selection and HMM-based mechanisms in the MaryTTS framework. Although a work in progress, the intermediate findings have been presented. © 2021 IEEE.

关键词： Speech

来源：评论

学校读者我要写书评

暂无评论

Automated Sinhala News Platform Based on Machine Learning and Deep Learning 3

Automated Sinhala News Platform Based on Machine Learning an...

引用

3rd International Conference on Advancements in Computing, ICAC 2021

作者： Ashani Malsha, N.P.G. Dulmini Heshani, K. Ransara, R. Kavishka Ayesh Bandara, D.M.D.D. Suriyaa Kumari, P.K. Anuththara Kuruppu, Thilmi Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781665408622

Over the years, newspapers are taken as a major activity in citizens. Due to digitalization, online newspapers get famed, and eventually, it seems to be an ideal adaptation for their busy lifestyle. While there are several Sinhala News platforms, nonetheless, provide an advance and better user experience similar to English news platforms like google news. To fill this gap the proposed news platform, dispense personalized news recommendation based on user behaviors and user emotions. To replace the manual news categorization, the proposed system is armed with automatic news categorization. An automatically unnecessary comment removing feature was also added to the proposed system as an extra feature. The system implementation is based on deep learning, machine learning, NLP, sentimental analysis, and image processing techniques where it can provide a better user experience and a new experience. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Elm Parameter Estimation in View of Maximum Likelihood

SSRN

引用

SSRN 2023年

作者： Yang, Lanzhen Tsang, Eric C.C. Wang, Xizhao Zhang, Chengling School of Computer Science and Engineering Macau University of Science and Technology Taipa China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China College of Mathematics and Information Sciences Hebei University Baoding071002 China

Extreme Learning Machine (ELM) can be considered a probabilistic model, wherein the output is a random variable characterized by its mean and variance, both crucial for assessing and enhancing ELM’s generalization ability. Despite its importance, limited research has been conducted on quantitative variance estimation and the underlying factors that influence connecting weight regularization. In this paper, we establish a connection between the variance and weights of ELM for regression problems, and propose maximum likelihood-based estimations for model parameters. We introduce a novel activation function and an algorithm to generate hidden layer outputs that adhere or approximate a normal distribution, as validated through experiments. Additionally, by leveraging the established relationship, we derive estimators for weights, variance, and confidence intervals of predicted values using Maximum Likelihood Estimation (MLE). The variance estimator enables a quantitative evaluation of generalization, and the link between variance and weights offers a theoretical basis for ELM regularization techniques. © 2023, The Authors. All rights reserved.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Improving Critical Node Detection Using Neural Network-based Initialization in a Genetic Algorithm

arXiv

引用

arXiv 2024年

作者： Liu, Chanjuan Ge, Shike Chen, Zhihan Pei, Wenbin Zhu, Enqiang Mei, Yi Ishibuchi, Hisao The School of Computer Science and Technology Dalian University of Technology 116024 China The Institute of Software Chinese Academy of Science Beijing100190 China The Institute of Computing Science and Technology Guangzhou University Guangzhou510006 China The School of Engineering and Computer Science Victoria University of Wellington Wellington6012 New Zealand The Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

The Critical Node Problem (CNP) is concerned with identifying the critical nodes in a complex network. These nodes play a significant role in maintaining the connectivity of the network, and removing them can negatively impact network performance. CNP has been studied extensively due to its numerous real-world applications. Among the different versions of CNP, CNP-1a has gained the most popularity. The primary objective of CNP-1a is to minimize the pair-wise connectivity in the remaining network after deleting a limited number of nodes from a network. Due to the NP-hard nature of CNP-1a, many heuristic/metaheuristic algorithms have been proposed to solve this problem. However, most existing algorithms start with a random initialization, leading to a high cost of obtaining an optimal solution. To improve the efficiency of solving CNP-1a, a knowledge-guided genetic algorithm named K2GA has been proposed. Unlike the standard genetic algorithm framework, K2GA has two main components: a pretrained neural network to obtain prior knowledge on possible critical nodes, and a hybrid genetic algorithm with local search for finding an optimal set of critical nodes based on the knowledge given by the trained neural network. The local search process utilizes a cut node-based greedy strategy. The effectiveness of the proposed knowledge-guided genetic algorithm is verified by experiments on 26 real-world instances of complex networks. Experimental results show that K2GA outperforms the state-of-the-art algorithms regarding the best, median, and average objective values, and improves the best upper bounds on the best objective values for eight real-world instances. Copyright © 2024, The Authors. All rights reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Classification of IncRNA and mRNA using k-mers and random forest 4

Classification of IncRNA and mRNA using k-mers and random fo...

引用

4th International Conference on Innovative Computing, ICIC 2021

作者： Nadir, Rana M. Mateen, Hafsa Din, Saif U University of Management and Technology Department of Computer Sciences Lahore Pakistan University of Central Punjab Faculty of Information Technology Lahore Pakistan University of Management and Technology Software Engineering Department Lahore Pakistan

ISBN: (纸本)9781665400916

The Long non-coding RNA is involved important biological process in our body but dark part is it also involve in some major deceases like cancer. Very few research is done on long non-coding RNA due to its structural resemblance with mRNA, which is protein coding RNA. A proper distinction model between mRNA and Long non-coding RNA is required to do further research on Long non-coding RNA and its association with ***: First, k-mers with different k values are extracted and directly tested with our model for best selection of k-mers features. Moreover, the k-mers with high accuracy score are combined in one pool and screened with the help of extra tees classifier to identify most relevant features. Furthermore short listed features are given to our random forest (RF) classifier to extract classification results for lncRna and mRna sequences of humans. Finally, over classifier is compared with other machine learning classifiers like State Vector Machine (SVM), Neural Network (NN) and K Nearest Neighbor (KNN). Results proves that our proposed model score highest accuracy, precision, recall and ***: We have established the RF classifier on the bases of combination of 2 and 3 k-mers features, which provides the accuracy of 0.9984. Thus this score is better than Convolutional Neural Network (CNN) based and all previous proposed classification approaches. © 2021 IEEE.

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

Scenario Shared Instance Modeling for Click-through Rate Prediction 25

Scenario Shared Instance Modeling for Click-through Rate Pre...

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1

作者： Dugang Liu Chaohua Yang Yuwen Fu Xing Tang Gongfu Li Fuyuan Lyu Xiuqiang He Zhong Ming College of Computer Science and Software Engineering Shenzhen University Shenzhen Guangdong China FiT Tencent Shenzhen Guangdong China McGill University Montreal Quebec Canada Shenzhen Technology University Shenzhen Guangdong China

ISBN: (纸本)9798400712456

Multi-scenario recommendation (MSR) is a popular training paradigm in industrial platforms for uniformly integrating information from multiple scenarios and serving them simultaneously. A key challenge in MSR research is accurately identifying the commonalities and distinctive information between scenarios. Currently, most existing MSR methods focus on implicitly extracting this information from the architectural level. However, this continues to increase the complexity and training overhead of MSR. Furthermore, the custom components responsible for extracting implicit information in each MSR method are too dependent on the specific MSR architecture and are not easily reused in other methods. Given these challenges, we first show in a motivating experiment that it may be beneficial to explicitly select a reasonable set of shared instances that can affect parameter optimization in all scenarios during the training of MSR, i.e., to explicitly obtain the critical information required for MSR from the data level. Then, this paper proposes SSIM with an adaptive selection network. Specifically, SSIM can be integrated with existing MSR methods in a lightweight way to adaptively select an informative and shareable subset of instances from each scenario to improve recommendations. In particular, the selected multi-scenario shared subset has extraordinary reusability and can be easily saved to benefit model training of various future MSR models. Finally, we evaluate SSIM and demonstrate its effectiveness through experiments on two public multi-scenario benchmarks and an online A/B test.

关键词： adaptive selection

来源：评论

学校读者我要写书评

暂无评论

Syllables to Scenes: Literary-Guided Free-Viewpoint 3D Scene Synthesis from Japanese Haiku

arXiv

引用

arXiv 2025年

作者： Yu, Chunan Han, Yidong Ding, Chaotao Zang, Ying Zhu, Lanyun Chen, Xinhao Li, Zejian Xu, Renjun Chen, Tianrun School of Information Engineering Huzhou University China College of Computer Science and Technology Zhejiang University China College of Software Engineering Zhejiang University China Center for Data Science Zhejiang University China Technology Co. LTD China Singapore University of Technology and Design Singapore School of Humanities Wenzhou University China

In the era of the metaverse, where immersive technologies redefine human experiences, translating abstract literary concepts into navigable 3D environments presents a fundamental challenge in preserving semantic and emotional fidelity. This research introduces HaikuVerse, a novel framework for transforming poetic abstraction into spatial representation, with Japanese Haiku serving as an ideal test case due to its sophisticated encapsulation of profound emotions and imagery within minimal text. While existing text-to-3D methods struggle with nuanced interpretations, we present a literary-guided approach that synergizes traditional poetry analysis with advanced generative technologies. Our framework centers on two key innovations: (1) Hierarchical Literary-Criticism Theory Grounded Parsing (H-LCTGP), which captures both explicit imagery and implicit emotional resonance through structured semantic decomposition, and (2) Progressive Dimensional Synthesis (PDS), a multi-stage pipeline that systematically transforms poetic elements into coherent 3D scenes through sequential diffusion processes, geometric optimization, and real-time enhancement. Extensive experiments demonstrate that HaikuVerse significantly outperforms conventional text-to-3D approaches in both literary fidelity and visual quality, establishing a new paradigm for preserving cultural heritage in immersive digital spaces. Project website at: https://***/ Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Support Vector Machine for Multiclass Classification of Redundant Instances

Support Vector Machine for Multiclass Classification of Redu...

引用

Intelligent Computing and Networking - Proceedings of IC-ICN 2023

作者： Surbakti, Herison Kumar, Athmakuri Naveen Tara, Saikumar Keshta, Ismail khare, Amit Prasad, G.N.R. Faculty of Computing and Digital Technology HELP University Kuala Lumpur Malaysia Senior Software Engineer Glosoft Technologies Pvt Ltd Chennai India Department of ECE BVRIT Hyderabad College of Engineering for Women Hyderabad India Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Department of Technology JIET Institute of Design and Technology Rajasthan Jodhpur India Telangana Hyderabad500091 India

ISBN: (纸本)9789819931767

In recent years, support vector machine has become one of the most important classification techniques in pattern recognition, machine learning, and data mining due to its superior classification effect and solid theoretical base. However, its training time will increase dramatically as the number of samples increases, and training will become more sophisticated when dealing with problems involving multiple classifications. A quick training data reduction approach MOIS appropriate for multi-classification tasks is presented as a solution for the aforementioned issues. While eliminating redundant training samples, the boundary samples that play a vital role are chosen in order to considerably reduce training data and the problem of unequal distribution between categories. The experimental results demonstrate that MOIS may maintain or even improve the classification performance of support vector machines while substantially enhancing training efficiency. On the Opt digit dataset, the suggested method improves classification accuracy from 98.94% to 99.05%, while training time is reduced to 15% of the original;in HCL2000, the proposed method improves classification accuracy from 98.94% to 99.05%. When the accuracy rate is marginally increased (from 99.29% to 99.30%) on the first 100 categories dataset, the training time is dramatically reduced to less than 6% of the original. Additionally, MOIS has a high operational efficiency. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

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：