检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ding, Wentao Li, Jianze Zhang, Shuzhong School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen China Department of Industrial and Systems Engineering University of Minnesota MinneapolisMN55455 United States

In this paper, to address the optimization problem on a compact matrix manifold, we introduce a novel algorithmic framework called the Transformed Gradient Projection (TGP) algorithm, using the projection onto this compact matrix manifold. Compared with the existing algorithms, the key innovation in our approach lies in the utilization of a new class of search directions and various stepsizes, including the Armijo, nonmonotone Armijo, and fixed stepsizes, to guide the selection of the next iterate. Our framework offers flexibility by encompassing the classical gradient projection algorithms as special cases, and intersecting the retraction-based line-search algorithms. Notably, our focus is on the Stiefel or Grassmann manifold, revealing that many existing algorithms in the literature can be seen as specific instances within our proposed framework, and this algorithmic framework also induces several new special cases. Then, we conduct a thorough exploration of the convergence properties of these algorithms, considering various search directions and stepsizes. To achieve this, we extensively analyze the geometric properties of the projection onto compact matrix manifolds, allowing us to extend classical inequalities related to retractions from the literature. Building upon these insights, we establish the weak convergence, convergence rate, and global convergence of TGP algorithms under three distinct stepsizes. In cases where the compact matrix manifold is the Stiefel or Grassmann manifold, our convergence results either encompass or surpass those found in the literature. Finally, through a series of numerical experiments, we observe that the TGP algorithms, owing to their increased flexibility in choosing search directions, outperform classical gradient projection and retraction-based line-search algorithms in several *** Codes 15A23, 49M37, 65K05, 90C26, 90C30 Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification

arXiv

引用

arXiv 2025年

作者： Ma, Yi Wang, Shuai Liu, Tianchi Li, Haizhou The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Institute for Infocomm Research A*STAR 138632 Singapore Shenzhen Research Institute of Big data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China

In speaker verification, we use computational method to verify if an utterance matches the identity of an enrolled speaker. This task is similar to the manual task of forensic voice comparison, where linguistic analysis is combined with auditory measurements to compare and evaluate voice samples. Despite much success, we have yet to develop a speaker verification system that offers explainable results comparable to those from manual forensic voice comparison. A novel approach, Explainable Phonetic Trait-Oriented (ExPO) network, is proposed in this paper to introduce the speaker’s phonetic trait which describes the speaker’s characteristics at the phonetic level, resembling what forensic comparison does. ExPO not only generates utterance-level speaker embeddings but also allows for fine-grained analysis and visualization of phonetic traits, offering an explainable speaker verification process. Furthermore, we investigate phonetic traits from within-speaker and between-speaker variation perspectives to determine which trait is most effective for speaker verification, marking an important step towards explainable speaker verification. Our code is available at https://***/mmmmayi/ExPO. Copyright © 2025, The Authors. All rights reserved.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models

arXiv

引用

arXiv 2025年

作者： Su, Jiamin Yan, Yibo Fu, Fangteng Zhang, Han Ye, Jingheng Liu, Xiang Huo, Jiahao Zhou, Huiyu Hu, Xuming The Hong Kong University of Science and Technology Guangzhou China Guangxi Zhuang Autonomous Region Big Data Research Institute China The Hong Kong University of Science and Technology Hong Kong Tsinghua University China

Automated Essay Scoring (AES) plays a crucial role in educational assessment by providing scalable and consistent evaluations of writing tasks. However, traditional AES systems face three major challenges: １ reliance on handcrafted features that limit generalizability, ２ difficulty in capturing fine-grained traits like coherence and argumentation, and ３ inability to handle multimodal contexts. In the era of Multimodal Large Language Models (MLLMs), we propose ESSAYJUDGE, the first multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits. By leveraging MLLMs’ strengths in trait-specific scoring and multimodal context understanding, ESSAYJUDGE aims to offer precise, context-rich evaluations without manual feature engineering, addressing longstanding AES limitations. Our experiments with 18 representative MLLMs reveal gaps in AES performance compared to human evaluation, particularly in discourse-level traits, highlighting the need for further advancements in MLLM-based AES research. Our dataset and code will be available upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning Network Optimization Based on Weight Adaptive

Multi-Task Learning Network Optimization Based on Weight Ada...

引用

International Conference on Behavior, Economic and Social Computing (BESC)

作者： Zizhuo Cao Yidong Li Chuntao Ding Zhuxi Zhang Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education School of Computer Science and Technology Beijing Jiaotong University Beijing China General Logistics Information Center Beijing China

ISBN: (数字)9798331531904

ISBN: (纸本)9798331531911

Multi-task learning has emerged as a significant topic in artificial intelligence research, where a singular network model performs numerous tasks. This approach simultaneously processes multiple related tasks and shared knowledge, enhancing model generalization while increasing efficiency. This methodology provides innovative solutions to complex real-world problems. However, the single-model-based approach for multi-task learning suffers from inter-task interference in practice. Therefore, the exploration of more efficient multi-task learning strategies, aimed at balancing the synergy and conflict among tasks and minimizing the dependence on computational resources, is pivotal for the field's future progress. We propose a strategy that autonomously adjusts both the parameters and structures of the model to alleviate gradient interference in multi-task learning. This method includes integrating a lightweight, weight-adaptive module that enhances the network's ability to process tasks by optimally balancing parameter sharing and isolation. This adaptation enables the model to share common features across tasks while allocating distinct spaces for each task, thereby reducing interference. Our extensive experimental validation indicates that our framework surpasses other multi-task learning approaches, achieving joint optimization of tasks more effectively. This enhancement not only bolsters performance but also maintains an equilibrium between accuracy and inference speed.

关键词： Adaptation models Social computing Computational modeling Interference Learning (artificial intelligence) Computer architecture Multitasking Synchronization Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Intuitive UAV Operation: A Novel dataset and Benchmark for Multi-Distance Gesture Recognition

Intuitive UAV Operation: A Novel Dataset and Benchmark for M...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhenpeng Xu Pan Sun Yu Lu Huilin Ge Meng Li Yingjian Qi College of Big Data and Internet Shenzhen Technology University Shenzhen China College of Applied Science Shenzhen University Shenzhen China College of Automation Jiangsu University Science and Technology Zhenjiang China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

UAV gesture recognition, a novel human-computer interaction form, offers an intuitive approach to controlling UAVs in various environments. However, there is a lack of comprehensive datasets for AI-powered UAV gesture recognition. This paper contributes in several ways: (i) We introduce MD-UHGRD, a unique UAV static gesture dataset with 20, 000 images and annotations, collected from a diverse group of participants in different environmental conditions. This dataset is expected to bridge a significant gap in UAV gesture recognition algorithms. (ii) We propose SA-YOLO, a multifunctional UAV gesture recognition method that not only enables gesture recognition but also includes face and pedestrian tracking, optimizing UAV control in complex scenarios. SA-YOLO incorporates the Spatial Asymptotic Feature Pyramid Network (SAFPN), Scale Pyramid Pooling with Cross Stage Partial Networks Convolution (SPPCSPC), and Space-to-Depth Convolution (SPD-Conv). (iii) Extensive evaluation of SAYOLO on MD-UHGRD establishes it as a benchmark in this domain. Our method demonstrates high accuracy, processing speed, and a compact model size, achieving a 93.2% mean Average Precision (mAP) with 10.3 million parameters and 48 frames per second (FPS). Among competing models, SA-YOLO not only achieves the highest mAP but also maintains a balance in model size and FPS. The database and code are available at: https://***/ijcnn2024/SA-YOLO.

关键词： Pedestrians Accuracy Convolution Tracking Face recognition Neural networks Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

UniMoCo: Unsupervised, Semi-Supervised and Fully-Supervised Visual Representation Learning

UniMoCo: Unsupervised, Semi-Supervised and Fully-Supervised ...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Dai, Zhigang Cai, Bolun Chen, Junying South China University of Technology Key Lab. of Big Data & Intell. Robot MoE School of Software Engineering Guangzhou China Tencent Wechat Ai Guangzhou China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Momentum Contrast (MoCo) achieves great success for unsupervised visual representation learning. However, there are a lot of supervised and semi-supervised datasets, which are already labeled. To fully utilize the label annotations, we propose Unified Momentum Contrast (UniMoCo), which extends MoCo to support arbitrary ratios of labeled data and unlabeled data training. Compared with MoCo, UniMoCo has two modifications as follows: (1) Different from a single positive pair in MoCo, we maintain multiple positive pairs on-the-fly by comparing the query label to a label queue. (2) We propose a Unified Contrastive (UniCon) loss to support an arbitrary number of positives and negatives in a unified pair-wise optimization perspective. Our UniCon is more reasonable and powerful than the supervised contrastive loss in theory and practice. In our experiments, we pre-train multiple UniMoCo models with different ratios of ImageNet labels and evaluate the performance on various downstream tasks. Experiment results show that UniMoCo generalizes well for unsupervised, semi-supervised and fully-supervised visual representation learning. Besides, we surprisingly find that UniMoCo performs best with 60% ImageNet labels for COCO and VOC transfer learning. The code is available: https://***/dddzg/unimoco. © 2022 IEEE.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

An ab initio dataset of size-dependent effective thermal conductivity for advanced technology transistors

引用

Chinese Physics B 2025年第4期34卷 125-130页

作者： Han Xie Ru Jia Yonglin Xia Lei Li Yue Hu Jiaxuan Xu Yufei Sheng Yuanyuan Wang Hua Bao School of Energy and Materials Shanghai Polytechnic UniversityShanghai 201209China Institute of Integrated Circuits Shanghai Polytechnic UniversityShanghai 201209China University of Michigan–Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong UniversityShanghai 200240China CTG Wuhan Science and Technology Innovation Park China Three Gorges CorporationWuhan 430010China Shanghai Thermophysical Properties Big Data Professional Technical Service Platform Shanghai Polytechnic UniversityShanghai 201209China Global Institute of Future Technology Shanghai Jiao Tong UniversityShanghai 200240China

As the size of transistors shrinks and power density increases,thermal simulation has become an indispensable part of the device design ***,existing works for advanced technology transistors use simplified empirical models to calculate effective thermal conductivity in the *** this work,we present a dataset of size-dependent effective thermal conductivity with electron and phonon properties extracted from ab initio *** in-plane and cross-plane thermal conductivity data of eight semiconducting materials(Si,Ge,GaN,AlN,4H-SiC,GaAs,InAs,BAs)and four metallic materials(Al,W,TiN,Ti)with the characteristic length ranging from 5 nm to 50 nm have been *** the absolute value,normalized effective thermal conductivity is also given,in case it needs to be used with updated bulk thermal conductivity in the future.

关键词： size-dependent effective thermal conductivity advanced technology transistors ab initio computations micro/nano-scale heat transfer

来源：评论

学校读者我要写书评

暂无评论

Inverse Quadratic Transform for Minimizing A Sum of Ratios

Inverse Quadratic Transform for Minimizing A Sum of Ratios

引用

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

作者： Yannan Chen Licheng Zhao Yaowen Zhang Kaiming Shen School of Science and Engineering The Chinese University of Hong Kong (Shenzhen) China Shenzhen Research Institute of Big Data China

A major challenge with the multi-ratio Fractional Program (FP) is that the existing methods for the maximization problem typically do not work for the minimization case. We propose a novel technique called inverse quadratic transform for the sum-of-ratios minimization problem. Its main idea is to reformulate the min-FP problem in a form amenable to efficient iterative optimization. Furthermore, this transform can be readily extended to a general cost-function-of-multiple-ratios minimization problem. We also give a Majorization-Minimization (MM) interpretation of the inverse quadratic transform, showing that all those desirable properties of MM can be carried over to the new technique. Moreover, we demonstrate the application of inverse quadratic transform in minimizing the Age-of-Information (AoI) of data networks.

关键词： Transforms Signal processing Minimization Information age Cost function Acoustics Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Gradient Tracking with Multiple Local SGD for Decentralized Non-Convex Learning

Gradient Tracking with Multiple Local SGD for Decentralized ...

引用

IEEE Conference on Decision and Control

作者： Songyang Ge Tsung-Hui Chang School of Science and Engineering The Chinese University of Hong Kong Shenzhen and Shenzhen Research Institute of Big Data Shenzhen China

The stochastic Gradient Tracking (GT) method for distributed optimization, is known to be robust against the inter-client variance caused by data heterogeneity. However, the stochastic GT method can be communication-intensive, requiring a large number of communication rounds of message exchange for convergence. To address this challenge, this paper proposes a new communication-efficient stochastic GT algorithm called the Local Stochastic GT(LSGT) algorithm, which adopts the local stochastic gradient descent (local SGD) technique in the GT method. With LSGT, each agent can perform multiple SGD updates locally within each communication round. Although it is not known previously whether the stochastic GT method can benefit from the local SGD, we establish the conditions under which our proposed LSGT algorithm enjoys the linear speedup brought by local SGD. Compared with the existing work, our analysis requires less restrictive conditions on the mixing matrix and algorithm stepsize. Moreover, it reveals that the local SGD does not only reserve the resilience of the stochastic GT method against the data heterogeneity but also speeds up reducing the tracking error reduction in the optimization process. The experimental results demonstrate that the proposed LSGT exhibits improved convergence speed and robust performance in various heterogeneous environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Enhanced Hybrid Whale Optimization Algorithm with Inverse Learning Strategy and Lévy Flight Mechanism

Research on Enhanced Hybrid Whale Optimization Algorithm wit...

引用

Computer Engineering and Intelligent Control (ICCEIC) International Conference on

作者： Danyang Guo Yinghao Zheng Jiaxin Lu Sihua Liang Tuyin Chen Jialin Yang Chao Zhou School of Robotics Engineering Guangzhou City University of Technology China School of Materials Science and Engineering Guilin University of Electronic Technology China School of Big Data and Computing Guangdong Baiyun University China

In recent years, bio-inspired optimization algorithms have attained significant success in addressing complex global optimization issues. Nonetheless, a single bio-inspired search strategy may struggle to handle diverse and intricate problems. To surmount this constraint, this paper introduces an enhanced hybrid whale algorithm (MEHWOA) based on reverse learning strategy and Lévy flight mechanism improvement. This approach amalgamates the global search capabilities of the gray wolf algorithm with the local search prowess of the whale algorithm, further augmenting the convergence speed and optimization accuracy of MEHWOA by incorporating reverse learning strategy and Lévy flight mechanism. To assess the performance of MEHWOA, we conducted experiments on 23 general benchmark test functions and compared it with original gray wolf (GWO), whale (WOA), particle swarm (PSO), and sparrow search (SSA) optimization algorithms. The experimental outcomes reveal that MEHWOA exhibits faster convergence speed and superior accuracy across various test functions, including unimodal, multimodal, and composite benchmark test functions. These findings corroborate that MEHWOA possesses considerable potential for solving complex global optimization problems.

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：