检索结果-内蒙古大学图书馆

Learning referee evaluation and assessing action quality from coarse to fine in diving sport

Neurocomputing 2025年

作者： Hong-Ming Qiu Hong-Bo Zhang Qing Lei Jing-Hua Liu Ji-Xiang Du Department of Computer Science and Technology Huaqiao University Xiamen 361021 China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen 361021 China Key Laboratory of Computer Vision and Machine Learning (Huaqiao University) Fujian Province University Xiamen 361021 China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen 361021 China

Intelligently assessing the quality of athletic performances in sports scenarios remains a fascinating challenge in computer vision. However, unraveling the subtle distinctions between two similar actions in videos and mapping those video representations to quality scores remain significant obstacles. To address these challenges, this work redefines the paradigm of quality score estimation from traditional relative quality score prediction to relative referee score prediction. To make this shift, a cross-feature fusion module rooted in Transformer-based video representation is introduced, to improve pairwise video feature learning in the realm of action quality assessment. Then, a novel contrastive action parsing decoder module generates mid-level representations to effectively connect visual features with detailed quality scores. Both modules utilize cross-attention mechanisms; the former refines the pairwise video features to represent the differences between video pairs, while the latter updates the input queries corresponding to each referee’s evaluation. Finally, to achieve precise quality score estimation, we introduce a meticulous coarse-to-fine decision process, integrating a score classifier and offset regressor. After validation on challenging diving datasets, including MTL-AQA, FineDiving, and TASD-2, the experimental results show that the proposed approach demonstrates effectiveness and feasibility when compared with state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mixture of Experts-Enabled Parallel Scheduling and Processing for Vehicular Generative AI Services

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Xie, Gaochang Xiong, Zehui Xie, Renchao Deng, Xiumei Guo, Song Guizani, Mohsen Han, Zhu Beijing University of Posts and Telecommunication State Key Laboratory of Networking and Switching Technology Beijing 100876 China Purple Mountain Laboratories Nanjing 211111 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Mohammad Bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates University of Houston Department of Electrical and Computer Engineering Houston 77004 TX United States Kyung Hee University Department of Computer Science and Engineering Seoul 446-701 South Korea

Foundation models (FMs) have revolutionized generative AI (GAI) lifecycle with their pre-trained intelligence capabilities. While the recent success of web-based models like GPT-4 has spurred interest in extending FMs to edge scenarios like the Internet of Vehicles (IoV), challenges such as data privacy, network congestion, and limited edge resource awareness hinder the direct application of cloud-based FMs. To address these challenges, this paper reconfigures the mixture of experts (MoE) architecture to deploy Transformer-based FM experts across vehicles for distributed GAI inference. Specifically, we propose an MoE-empowered vehicular FM system with two key innovations: a physical gating network that dynamically adapts to wireless environments, and a vehicle-to-vehicle (V2V) communication-based expert parallelism mechanism to enhance efficiency and resource utilization. Then, we formulate the communication, computation, and memory models for analyzing inference latency. Furthermore, to optimize the computational resource allocation for enhancing inference performance, we establish a Stackelberg game and propose the Gradient Ascent and Evolutionary Optimization-based Competitive Pricing and Allocation (GECPA) algorithm, which balances resource allocation and usage costs by combining the rapid convergence of gradient ascent with the broader exploration capability of evolutionary optimization. Simulation results demonstrate the superior parallel processing efficiency and reduced latency of the proposed MoE-based FM inference scheme. Compared with the best-performing benchmark algorithm, GECPA improves the average utility of infrastructure vehicles by up to 2.01 times, reduces inference latency by 16.58%, and increases the successful execution rate of GAI tasks by 10.66%, thereby achieving a better balance between efficiency and incentive compatibility in dynamic IoV environments. © 2015 IEEE.

关键词： expert parallelism foundation models (FMs) Generative AI (GAI) Internet of Vehicles (IoV) mixture of experts (MoE) resource allocation

来源：评论

学校读者我要写书评

暂无评论

TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences

arXiv

引用

arXiv 2023年

作者： Liu, Yuequn Cai, Ruichu Chen, Wei Qiao, Jie Yan, Yuguang Li, Zijian Zhang, Keli Hao, Zhifeng School of Computer Science Guangdong University of Technology Guangzhou China Peng Cheng Laboratory Shenzhen China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates Huawei Noah's Ark Lab Huawei Paris France College of Science Shantou University Shantou China

Learning Granger causality from event sequences is a challenging but essential task across various applications. Most existing methods rely on the assumption that event sequences are independent and identically distributed (i.i.d.). However, this i.i.d. assumption is often violated due to the inherent dependencies among the event sequences. Fortunately, in practice, we find these dependencies can be modeled by a topological network, suggesting a potential solution to the non-i.i.d. problem by introducing the prior topological network into Granger causal discovery. This observation prompts us to tackle two ensuing challenges: 1) how to model the event sequences while incorporating both the prior topological network and the latent Granger causal structure, and 2) how to learn the Granger causal structure. To this end, we devise a unified topological neural Poisson auto-regressive model with two processes. In the generation process, we employ a variant of the neural Poisson process to model the event sequences, considering influences from both the topological network and the Granger causal structure. In the inference process, we formulate an amortized inference algorithm to infer the latent Granger causal structure. We encapsulate these two processes within a unified likelihood function, providing an end-to-end framework for this task. Experiments on simulated and real-world data demonstrate the effectiveness of our approach. Copyright © 2023, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

GSLB: the graph structure learning benchmark 23

GSLB: the graph structure learning benchmark

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zhixun Li Liang Wang Xin Sun Yifan Luo Yanqiao Zhu Dingshuo Chen Yingtao Luo Xiangxin Zhou Qiang Liu Shu Wu Jeffrey Xu Yu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences and Department of Automation University of Science and Technology of China Department of Automation University of Science and Technology of China School of Cyberspace Security Beijing University of Posts and Telecommunications Department of Computer Science University of California Los Angeles Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of Learning on Small Data: Generalization, Optimization, and Challenge

arXiv

引用

arXiv 2022年

作者： Cao, Xiaofeng Bu, Weixin Huang, Shengjun Zhang, Minling Tsang, Ivor W. Ong, Yew Soon Kwok, James T. The School of Artificial Intelligence Jilin University Changchun130012 China The MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China The School of Computer Science and Engineering Southeast University Nanjing210096 China Ministry of Education China The Australian Artificial Intelligence Institute University of Technology SydneyNSW2008 Australia Singapore The School of Computer Science and Engineering Nanyang Technological University Nanyang Avenue Singapore639798 Singapore Artificial Intelligence Scientist of A∗STAR Singapore The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Learning on big data brings success for artificial intelligence (AI), but the annotation and training costs are expensive. In future, learning on small data that approximates the generalization ability of big data is one of the ultimate purposes of AI, which requires machines to recognize objectives and scenarios relying on small data as humans. A series of learning topics is going on this way such as active learning and few-shot learning. However, there are few theoretical guarantees for their generalization performance. Moreover, most of their settings are passive, that is, the label distribution is explicitly controlled by finite training resources from known distributions. This survey follows the agnostic active sampling theory under a PAC (Probably Approximately Correct) framework to analyze the generalization error and label complexity of learning on small data in model-agnostic supervised and unsupervised fashion. Considering multiple learning communities could produce small data representation and related topics have been well surveyed, we thus subjoin novel geometric representation perspectives for small data: the Euclidean and non-Euclidean (hyperbolic) mean, where the optimization solutions including the Euclidean gradients, non-Euclidean gradients, and Stein gradient are presented and discussed. Later, multiple learning communities that may be improved by learning on small data are summarized, which yield data-efficient representations, such as transfer learning, contrastive learning, graph representation learning. Meanwhile, we find that the meta-learning may provide effective parameter update policies for learning on small data. Then, we explore multiple challenging scenarios for small data, such as the weak supervision and multi-label. Finally, multiple data applications that may benefit from efficient small data representation are surveyed. Copyright © 2022, The Authors. All rights reserved.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Local Global Transformer for Point Clouds Analysis

SSRN

引用

SSRN 2023年

作者： Li, Dilong Zheng, Shenghong Chen, Ziyi Li, Xiang Wang, Lanying Du, Jixiang College of Computer Science and Technology Fujian Key Laboratory of Big Data Intelligence and Security Xiamen Key Laboratory of Computer Vision and Pattern Recognition Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University FJ Xiamen361021 China School of Economics and Finance Huaqiao University FJ Quanzhou362021 China Department of Geography and Environmental Management University of Waterloo WaterlooONN2L 3G1 Canada

Transformer networks have demonstrated remarkable performance in point cloud analysis. However, achieving a balance between local regional context and global long-range context learning remains a significant challenge. In this paper, we propose a Hierarchical Local Global Transformer Network (LGTNet), designed to capture local and global contexts in a hierarchical manner. Specifically, we employ serial local and global Transformers to learn the inner-group and cross-group self-attention, respectively. Besides, we propose a geometric moment-based position encoding for local Transformer, enabling the embedding of comprehensive local geometric relationship. Additionally, we also introduce a global feature pooling module that extracts the global features from each encoder layers. Extensive experimental results demonstrate that LGTNet achieves state-of-the-art performance on ShapeNetPart and ScanObjectNN datasets. This approach effectively enhances the understanding of point cloud scenes, thereby facilitating the use of point cloud data in remote sensing applications. © 2023, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Group-specific discriminant analysis reveals statistically validated sex differences in lateralization of brain functional network

arXiv

引用

arXiv 2024年

作者： Zhou, Shuo Luo, Junhao Jiang, Yaya Wang, Haolin Lu, Haiping Gong, Gaolang Department of Computer Science University of Sheffield Sheffield United Kingdom Centre for Machine Intelligence University of Sheffield Sheffield United Kingdom State Key Laboratory of Cognitive Neuroscience and Learning IDG/McGovern Institute for Brain Research Beijing Normal University Beijing China Beijing Key Laboratory of Brain Imaging and Connectomics Beijing Normal University Beijing China Chinese Institute for Brain Research Beijing China

Lateralization is a fundamental feature of the human brain, where sex differences have been observed. Conventional studies in neuroscience on sex-specific lateralization are typically conducted on univariate statistical comparisons between male and female groups. However, these analyses often lack effective validation of group specificity. Here, we formulate modeling sex differences in lateralization of functional networks as a dual-classification problem, consisting of first-order classification for left vs. right functional networks and second-order classification for male vs. female models. To capture sex-specific patterns, we develop the Group-Specific Discriminant Analysis (GSDA) for first-order classification. The evaluation on two public neuroimaging datasets demonstrates the efficacy of GSDA in learning sex-specific models from functional networks, achieving a significant improvement in group specificity over baseline methods. The major sex differences are in the strength of lateralization and the interactions within and between lobes. The GSDA-based method is generic in nature and can be adapted to other group-specific analyses such as handedness-specific or disease-specific analyses. © 2024, CC BY-NC-SA.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices

arXiv

引用

arXiv 2024年

作者： Zeng, Hongye Zou, Ke Chen, Zhihao Gao, Yuchong Chen, Hongbo Zhang, Haibin Zhou, Kang Wang, Meng Goh, Rick Siow Mong Liu, Yong Jiang, Chang Zheng, Rui Fu, Huazhu School of Information Science and Technology ShanghaiTech University Shanghai China Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai China University of Chinese Academy of Sciences Beijing China National Key Laboratory of Fundamental Science on Synthetic Vision College of Computer Science Sichuan University Chengdu China College of Intelligence and Computing Tianjin University Tianjin China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Beth Israel Deaconess Medical Center Harvard Medical School Boston United States Institute of High Performance Computing Agency for Science Technology and Research Singapore Singapore Department of Orthopedics Zhongshan Hospital Fudan University Shanghai China Shanghai Engineering Research Center of Intelligent Vision and Imaging Shanghai China

Handheld ultrasound devices face usage limitations due to user inexperience and cannot benefit from supervised deep learning without extensive expert annotations. Moreover, the models trained on standard ultrasound device data are constrained by training data distribution and perform poorly when directly applied to handheld device data. In this study, we propose the Training-free Image Style Alignment (TISA) framework to align the style of handheld device data to those of standard devices. The proposed TISA can directly infer handheld device images without extra training and is suited for clinical applications. We show that TISA performs better and more stably in medical detection and segmentation tasks for handheld device data. We further validate TISA as the clinical model for automatic measurements of spinal curvature and carotid intima-media thickness. The automatic measurements agree well with manual measurements made by human experts and the measurement errors remain within clinically acceptable ranges. We demonstrate the potential for TISA to facilitate automatic diagnosis on handheld ultrasound devices and expedite their eventual widespread use. © 2024, CC BY-NC-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Precise Hip Protection System with Multi-scale Fall Warning Algorithm Based on Offset Displacement

A Precise Hip Protection System with Multi-scale Fall Warnin...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Qiangqiang Chen Yanan Diao Yaping Wang Yumin Chen Yunkun Ning Guanglin Li Guoru Zhao CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Research Center for Neural Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China College of Computer Science and Technology Xiamen University of Technology China Department of Neurology Shenzhen Second People's Hospital Shenzhen China

Falls occur frequently in daily life and the damage to the body is irreversible. Therefore, it is crucial to implement timely and effective warning and protection systems for falls to minimize the damage caused by falls. Currently, the fall warning algorithm has shortcomings such as low recognition rates for falls and fall-risk movements and insufficient lead-time, the time before the subject impacts the floor, making it difficult for falling protection devices to function effectively. In this study, a multi-scale falls warning algorithm based on offset displacement is built, and a hip protection system is designed. The performance of the algorithm and the system is validated using 150 falling and 500 fall-risk actions from 10 volunteers. The results showed that the recognition accuracy for falling actions is 98.7% and the recognition accuracy for fall-risk actions is 99.4%, with an average lead-time of 402ms. The protection rate for falling movements reached 98.7%. This proposed algorithm and hip protection system have the potential to be applied in elderly communities, hospitals, and homes to reduce the damage caused by *** Relevance— This study provides important reference for clinicians in analyzing fall behaviors to patients at risk of falls in clinical settings, offering valuable technical support for ensuring the safety of patients in danger of falling. It also contributes to further promoting the development of falling-prevention medical devices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Subject Decision Confidence Estimation from EEG Signals Using Spectral-Spatial-Temporal Adaptive GCN with Domain Adaptation

Cross-Subject Decision Confidence Estimation from EEG Signal...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Rong-Fei Gu Rui Li Wei-Long Zheng Bao-Liang Lu Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China RuiJin-Mihoyo Laboratory Clinical Neuroscience Center RuiJin Hospital Shanghai Jiao Tong University School of Medicine Shanghai China

The study of the human decision-making process has long been a valuable field for both scientific research and practical application. Towards knowing and taking control of the decision-making process, evaluating the reliability of human decisions objectively plays an important role. Various studies have demonstrated that the confidence level of humans during the decision-making process is an important factor that reflects the correctness of decisions. In literature, several deep learning based methods have been developed to estimate decision confidence using Electroencephalography (EEG). Among these approaches, the spectral-spatial-temporal adaptive graph convolutional neural network (SST-AGCN) stands out. However, SST-AGCN focuses on specific subjects, and may lead to less efficiency in cross-subject situations, which are more common in application scenarios. In this paper, we propose a deep learning model called SST-AGCN with Domain Adaptation (SST-AGCN-DA) for cross-subject decision confidence estimation. To examine the effectiveness of our proposed model, we compare our SST-AGCN-DA with the original SST-AGCN, three typical domain adaption algorithms in the field, and the SST-AGCN with Domain Generalization (SST-AGCN-DG), which is another transfer learning model we developed in this paper. We conduct cross-subject confidence estimation experiments on an EEG dataset collected under a text-based decision-making task. The averaged results of leave-one-out cross-validation come out that the F1-scores of our proposed SST-AGCN-DA and SST-AGCN-DG are 79.45% and 77.04%, respectively, while the original SST-AGCN and the best of the existing domain adaptation algorithms are 74.15% and 74.25%, respectively.

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：