检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hu, Zhilei Li, Zixuan Xu, Daozhu Bai, Long Jin, Cheng Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China State Key Laboratory of Geo-Information Engineering Xi’an710054 China Xi’an Research Institute of Surveying and Mapping Xi’an710054 China

Event Relation Extraction (ERE) aims to extract multiple kinds of relations among events in texts. However, existing methods singly categorize event relations as different classes, which are inadequately capturing the intrinsic semantics of these relations. To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations. Specifically, ProtoEM extracts event relations in a two-step manner, i.e., prototype representing and prototype matching. In the first step, to capture the connotations of different event relations, ProtoEM utilizes examples to represent the prototypes corresponding to these relations. Subsequently, to capture the interdependence among event relations, it constructs a dependency graph for the prototypes corresponding to these relations and utilized a Graph Neural Network (GNN)-based module for modeling. In the second step, it obtains the representations of new event pairs and calculates their similarity with those prototypes obtained in the first step to evaluate which types of event relations they belong to. Experimental results on the MAVEN-ERE dataset demonstrate that the proposed ProtoEM framework can effectively represent the prototypes of event relations and further obtain a significant improvement over baseline models. Copyright © 2023, 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

CIMI4D: A Large Multimodal Climbing Motion dataset under Human-scene Interactions

CIMI4D: A Large Multimodal Climbing Motion Dataset under Hum...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ming Yan Xin Wang Yudi Dai Siqi Shen Chenglu Wen Lan Xu Yuexin Ma Cheng Wang Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University National Institute for Data Science in Health and Medicine Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University Shanghai Engineering Research Center of Intelligent Vision and Imaging ShanghaiTech University

Motion capture is a long-standing research problem. Although it has been studied for decades, the majority of research focus on ground-based movements such as walking, sitting, dancing, etc. Off- grounded actions such as climbing are largely overlooked. As an important type of action in sports and firefighting field, the climbing movements is challenging to capture because of its complex back poses, intricate human-scene interactions, and difficult global localization. The research community does not have an indepth understanding of the climbing action due to the lack of specific datasets. To address this limitation, we collect CIMI4D, a large rock Climbing Motion dataset from 12 persons climbing 13 different climbing walls. The dataset consists of around 180,000 frames of pose inertial measurements, LiDAR point clouds, RGB videos, high-precision static point cloud scenes, and reconstructed scene meshes. Moreover, we frame-wise annotate touch rock holds to facilitate a detailed exploration of human-scene interaction. The core of this dataset is a blending optimization process, which corrects for the pose as it drifts and is affected by the magnetic conditions. To evaluate the merit of CIMI4D, we perform four tasks which include human pose estimations (with/without scene constraints), pose prediction, and pose generation. The experimental results demonstrate that CIMI4D presents great challenges to existing methods and enables extensive research opportunities. We share the dataset with the research community in http://***/cimi4d/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Optimization and Acceleration Method of Ship Detection Based on Deep Learning

Research on Optimization and Acceleration Method of Ship Det...

引用

China International SAR Symposium (CISS)

作者： Hongnan Tian Yang Gao Lei Liao Yuxuan Bie Wei Hua Hui Wang Beijing R&D Center Shanghai Key Laboratory of Aerospace Milimeter Wave Information Technology Shanghai Academy of Spaceflight Technology Beijing China Territorial spatial data center of rizhao Rizhao China Shanghai Key Laboratory of Aerospace Milimeter Wave Information Technology Shanghai Institute of Satelite Engineering Shanghai China

Synthetic Aperture Radar (SAR), as an all-day and all-weather high-resolution imaging radar, has been more and more widely used in the field of ship detection. However, due to the limitations of computing resources on satellite-based platforms, it is difficult to deploy ship detection models based on deep learning on satellites. In order to solve the above problems, this paper proposes a method based on TensorRT and CUDA co-optimization. Take advantage of the parallel computing advantages of GPU through CUDA parallel computing optimization method. Improve the processing efficiency of image preprocessing. Deploy the trained model through TensorRT and reconstruct the model from both vertical and horizontal aspects. And adjust the number of quantization digits of the model to improve the operating efficiency of the model. Through experiments, after adopting the above optimization strategy, the model achieved an acceleration ratio of 3.19 times in running time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Personalization on Federated Recommendation

arXiv

引用

arXiv 2023年

作者： Zhang, Chunxu Long, Guodong Zhou, Tianyi Yan, Peng Zhang, Zijian Zhang, Chengqi Yang, Bo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China College of Computer Science and Technology Jilin University China Australian Artificial Intelligence Institute FEIT University of Technology Sydney Australia Computer Science and UMIACS University of Maryland United States

Federated recommendation is a new Internet service architecture that aims to provide privacy-preserving recommendation services in federated settings. Existing solutions are used to combine distributed recommendation algorithms and privacy-preserving mechanisms. Thus it inherently takes the form of heavyweight models at the server and hinders the deployment of on-device intelligent models to end-users. This paper proposes a novel Personalized Federated Recommendation (PFedRec) framework to learn many user-specific lightweight models to be deployed on smart devices rather than a heavyweight model on a server. Moreover, we propose a new dual personalization mechanism to effectively learn fine-grained personalization on both users and items. The overall learning process is formulated into a unified federated optimization framework. Specifically, unlike previous methods that share exactly the same item embeddings across users in a federated system, dual personalization allows mild finetuning of item embeddings for each user to generate user-specific views for item representations which can be integrated into existing federated recommendation methods to gain improvements immediately. Experiments on multiple benchmark datasets have demonstrated the effectiveness of PFedRec and the dual personalization mechanism. Moreover, we provide visualizations and in-depth analysis of the personalization techniques in item embedding, which shed novel insights on the design of recommender systems in federated settings. The code is available. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Inducing Desired Equilibrium in Taxi Repositioning Problem with Adaptive Incentive Design

Inducing Desired Equilibrium in Taxi Repositioning Problem w...

引用

IEEE Conference on Decision and Control

作者： Jianhui Li Youcheng Niu Shuang Li Yuzhe Li Jinming Xu Junfeng Wu College of Control Science and Engineering Zhejiang University Hangzhou China School of Data Science The Chinese University of Hong Kong (Shenzhen) Shenzhen China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

We study the problem of designing incentives to induce desired equilibrium in taxi repositioning problems. In this scenario, self-interested idle drivers will update their repositioning strategies with observed payoff. Meanwhile, the platform will adaptively design incentives to induce a better Nash equilibrium for global efficiency. We formulate the problem as a bi-level optimization problem where the incentive designer and idle drivers simultaneously update their decision variables. We prove that drivers' strategies will reach Nash equilibrium, and the incentive designer's objective function will reach optimality under Polyak Lojasiewicz (PL) condition. Furthermore, we derive a sufficient condition for the PL condition to hold for the upper-level objective function and lower-level agents' payoff function. Finally, we demonstrate the efficiency of the proposed method by numerical results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector

arXiv

引用

arXiv 2023年

作者： Zhou, Caixia Huang, Yaping Pu, Mengyang Guan, Qingji Huang, Li Ling, Haibin Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University China School of Control and Computer Engineering North China Electric Power University China Department of Computer Science Stony Brook University United States

Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators. Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias of annotators. In this paper, we propose a novel uncertainty-aware edge detector (UAED), which employs uncertainty to investigate the subjectivity and ambiguity of diverse annotations. Specifically, we first convert the deterministic label space into a learnable Gaussian distribution, whose variance measures the degree of ambiguity among different annotations. Then we regard the learned variance as the estimated uncertainty of the predicted edge maps, and pixels with higher uncertainty are likely to be hard samples for edge detection. Therefore we design an adaptive weighting loss to emphasize the learning from those pixels with high uncertainty, which helps the network to gradually concentrate on the important pixels. UAED can be combined with various encoder-decoder backbones, and the extensive experiments demonstrate that UAED achieves superior performance consistently across multiple edge detection benchmarks. The source code is available at https://***/ZhouCX117/ UAED. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Ssd Optimization Model Based on Shallow Feature Fusion

SSRN

引用

SSRN 2022年

作者： Yang, Zhe Bu, Ziyu Liu, Chunping Provincial Key Laboratory for Computer Information Processing Technology Suzhou215006 China Department of Computer Science and Technology Soochow University Suzhou215006 China Provincial Key Laboratory for Intelligent Engineering in Big Data Suzhou215006 China

Object detection has been an important research branch in the field of computer vision. The single-shot-detection (SSD) is an object detection model based on deep learning, which can achieve a good balance between the detection accuracy and the detection speed, but has the problem of poor recognition accuracy for small objects. To address this limitation , this paper improves the structure of the SSD feature pyramid and upsamples the shallow feature map with small object information and fuses it with the upper feature map, thus enhancing the ability of the shallow feature map to represent detailed information. In this way, not only the overall detection accuracy of the SSD is improved, but also a relatively high detection speed is maintained. The proposed model is verified by experiments on two common datasets, the Pascal VOC and MS COCO datasets. On the PASCAL VOC07+12, MS COCO14, and VOC07+12 + COCO datasets, the improved model achieves the mean average precision values of 80.1% (+3.3% compared with the conventional model), 49.9% (+6.8%), and 82.1% (+3.0%), respectively. Meanwhile, the proposed model can achieve the detection speed of 42.2 frames per second. © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Ssd Optimization Model Based on Shallow Feature Fusion

SSRN

引用

SSRN 2022年

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text

arXiv

引用

arXiv 2023年

作者： Xu, Fangzhi Liu, Jun Lin, Qika Zhao, Tianzhe Zhang, Jian Zhang, Lingling School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D National Engineering lab for Big Data Analytics Xi’an China

Logical reasoning task involves diverse types of complex reasoning over text, based on the form of multiple-choice question answering. Given the context, question and a set of options as the input, previous methods achieve superior performances on the full-data setting. However, the current benchmark dataset has the ideal assumption that the reasoning type distribution on the train split is close to the test split, which is inconsistent with many real application scenarios. To address it, there remain two problems to be studied: (1) How is the zero-shot capability of the models (train on seen types and test on unseen types)? (2) How to enhance the perception of reasoning types for the models? For problem 1, we propose a new benchmark for generalized zero-shot logical reasoning, named ZsLR. It includes six splits based on the three type sampling strategies. For problem 2, a type-aware model TaCo is proposed. It utilizes both the heuristic input reconstruction and the contrastive learning to improve the type perception in the global representation. Extensive experiments on both the zero-shot and full-data settings prove the superiority of TaCo over the state-of-the-art methods. Also, we experiment and verify the generalization capability of TaCo on other logical reasoning dataset. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Research on Freshwater Fish Recognition Based on Improved Random Forest

Research on Freshwater Fish Recognition Based on Improved Ra...

引用

Intelligent Management and Software engineering (IMSE), International Conference on

作者： Xiaorui Zhang Hongming Chen Longqing Zhang Qian Chen Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan China Guangdong University of Science and Technology Dongguan China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China

In this paper, the performance of models based on decision trees and improved random forest is explored for the fish classification problem. Through comparative experiments, the differences in performance in terms of accuracy between these two models are studied. The experiments utilize fish datasets from different ecological environments and geographic regions, containing rich morphological feature information. Firstly, we construct a fish classification model based on decision trees and train and test it on the dataset. This model demonstrates a decent performance in terms of accuracy, achieving a classification accuracy of 79.16%. However, to further enhance classification performance, we introduce the random forest model, which integrates predictions from multiple decision trees. Through cross-validation and parameter tuning, an improved random forest classifier is built. The experimental results illustrate a significant improvement in fish classification tasks with the improved random forest model. Its accuracy reaches 91.88%, showing a 7.5-percentage-point increase compared to the random forest model. Furthermore, we test the generalization performance of the model and find that the improved random forest model also exhibits good classification ability on unseen samples. In summary, this research, by contrasting and analyzing the performance of decision tree models and the improved random forest model, validates the effectiveness and superiority of the random forest in the fish classification problem. This provides essential insights for fields such as ecological environment monitoring and fish resource management, while also offering inspiration for further exploration of the application of other machine learning methods to similar 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：