检索结果-内蒙古大学图书馆

lab.l distribution learning for scene text detection

Frontiers of computer Science 2023年第6期17卷 5-12页

作者： Haoyu MA Ningning LU Junjun MEI Tao GUAN Yu ZHANG Xin GENG School of Computer Science and Engineering and the Key Lab of Computer Network and Information Integration(Ministry of Education)Southeast UniversityNanjing 211189China ZTE Corporation Nanjing 210012China

Recently,segmentation-based scene text detection has drawn a wide research interest due to its flexibility in describing scene text instance of arbitrary shapes such as curved ***,existing methods usually need complex post-processing stages to process ambiguous lab.ls,i.e.,the lab.ls of the pixels near the text boundary,which may belong to the text or *** this paper,we present a framework for segmentation-based scene text detection by learning from ambiguous *** use the lab.l distribution learning method to process the lab.l ambiguity of text annotation,which achieves a good performance without using additional post-processing *** on benchmark datasets demonstrate that our method produces better results than state-of-the-art methods for segmentation-based scene text detection.

关键词： scene text detection multi-task learning lab.l distribution learning

来源：评论

学校读者我要写书评

暂无评论

Calibration Bottleneck: Over-compressed Representations are Less Calibratable 41

Calibration Bottleneck: Over-compressed Representations are ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Deng-Bao Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Lab. of Computer Network and Information Integration Southeast University MOE China

Although deep neural networks have achieved remarkable success, they often exhibit a significant deficiency in reliable uncertainty calibration. This paper focus on model calibratability, which assesses how amenable a model is to be well recalibrated post-hoc. We find that the widely used weight decay regularizer detrimentally affects model calibratability, subsequently leading to a decline in final calibration performance after post-hoc calibration. To identify the underlying causes leading to poor calibratability, we delve into the calibratability of intermediate features across the hidden layers. We observe a U-shaped trend in the calibratability of intermediate features from the bottom to the top layers, which indicates that over-compression of the top representation layers significantly hinders model calibratability. Based on the observations, this paper introduces a weak classifier hypothesis, i.e., given a weak classification head that has not been over-trained, the representation module can be better learned to produce more calibratable features. Consequently, we propose a progressively layer-peeled training (PLP) method to exploit this hypothesis, thereby enhancing model calibratability. Our comparative experiments show the effectiveness of our method, which improves model calibration and also yields competitive predictive performance. Copyright 2024 by the author(s)

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Meta Meeting Mountain based opportunistic message forwarding strategy

A Meta Meeting Mountain based opportunistic message forwardi...

引用

作者： Tu, Jinbin Wang, Yun Liu, Yichuan Li, Qing School of Computer Science and Engineering Southeast University Nanjing China Key Lab of Computer Network and Information Integration MOE Nanjing China

The opportunistic network is a type of ad hoc network that relies on the chance encounters between nodes to transmit messages. It also uses store-and-carry-forward techniques for data transfer between nodes. Developing effective message forwarding strategies based on opportunistic network characteristics and node behavior poses a significant challenge. In this paper, we delve into the mobility and social characteristics of nodes using historical encounter information. Furthermore, we calculate the migration degree and community relations to build the Meta Meeting Mountain, which representing node encounter characteristics. Moreover, we introduce the concept of Forwarding Degree to measure the nodes’ ability to deliver messages, enhancing the predictability of message delivery. Furthermore, a new forwarding strategy is proposed, which is equipped with Meta Meeting Mountain and Forwarding degree to improve the delivery rate. Our experimental scenarios include Infocom06, Rome taxi, and Helsinki. Therefore, the impact of buffer size and TTL is discussed in detail regarding the different opportunistic routing algorithms. Finally, extensive experimental results show that the proposed algorithm outperforms UBPR, MaxProp, PRoPHET, Spray And Wait and RAPAR in terms of delivery rate in the above scenarios by 127.905%, 93.7525%, 138.6888%, 175.3663%, and 281.4625%, respectively, while keeping the hopcount value less than 5. © 2023 Elsevier B.V.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

DP-GenFL: a local differentially private federated learning system through generative data

引用

Science China(information Sciences) 2023年第8期66卷 275-276页

作者： Jun LI Kang WEI Chuan MA Feng SHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Communication Engineering Hainan University

With the rapid development of the Internet of Things(Io T),the amount of data from intelligent devices is propagating at unprecedented scales. Meanwhile, machine learning(ML),which relies heavily on such data, is revolutionizing many aspects of our lives [1]. However, conventional centralized ML offers little scalab.lity for efficiently processing this huge amount of data.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

T-Sorokin: A General Mobility Model in Opportunistic networks 26

T-Sorokin: A General Mobility Model in Opportunistic Network...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Tu, Jinbin Li, Qing Wang, Yun Southeast University Key Lab of Computer Network and Information Integration Moe School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350331684

The opportunistic networks are a kind of ad hoc networks that rely on the chance of nodes meeting to transmit messages. Acting as an effective supplement to 4G and 5G networks in some special scenarios where hardware devices are limited, the opportunistic networks have a significant application in health monitoring, warning broadcasting, disaster relief, and so on. The mobility model is one of the research focuses on the opportunistic networks. On the basis of the social mobility theory proposed by Sorokin, a general mobility model, which is suited for various scenarios, called T-Sorokin is proposed. This model is described as a seven-tuple and implemented on the Opportunistic network Environment simulator and fits both Infocom06 and Rome taxi data set, which includes different areas ranging from hotel to city and different mobile units ranging from person to taxi. The results of experiments demonstrate that the T-Sorokin model has the advantage of generality, simplicity, and accuracy. It can simply establish movement tracks close to real data under different scenarios. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of UAV Deployment and Task Computation Offloading Decision in UAV-assisted Edge Computing network 25

Joint Optimization of UAV Deployment and Task Computation Of...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data Science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Liu, Yichuan Tu, Jinbin Wang, Yun School of Computer Science and Engineering Southeast University Key Lab of Computer Network and Information Integration Moe Nanjing China

ISBN: (纸本)9798350330014

The UAVs' deployment decision and task computation offloading decision in the UAV-assisted edge computing network significantly impact the operating efficiency of edge network. On the basis of this, the Optimization Model for UAV Cluster Deployment and Computation Offloading Decision (OMUCDCOD) is established. The model jointly optimizes the number, location of UAV s, and task computation offloading decision. Different from previous studies, this model regards the terminal devices in the edge network as virtual MEC servers, and introduces the collab.rative computing mode. The task computation offloading decision made can effectively utilize the computing capabilities offered by the edge network. Considering that the two problems of UAV deployment decision and task computation offloading decision are intricately interconnected, we propose a two-layer optimization algorithm combining K-Means and ant colony algorithm (ToKmAc) to solve OMUCDCOD. ToKmAc is divided into upper and lower layers to solve this optimization problem. The upper layer uses K-Means to solve the UAV deployment decision, that is, the number and location of UAVS;the lower layer employs ant colony algorithm to solve computation offloading decision. Finally, extensive experiments verify the effectiveness of OMUCDCOD and ToKmAc. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A common gateway for interoperability in multi-architecture LVC simulation 6

A common gateway for interoperability in multi-architecture ...

引用

6th International Conference on computer information Science and Application Technology, CISAT 2023

作者： Lin, Shichao Wang, Yun School of Computer Science and Engineering Southeast University Nanjing China Key Lab of Computer Network and Information Integration MOE China

ISBN: (纸本)9781510668546

With the development of Live-Virtual-Constructive (LVC) simulation technology, numerous LVC simulation resources have been developed. To construct more large-scale LVC simulation, it is necessary to integrate existing simulation resources. Due to the heterogeneity of LVC resources, the interoperability between heterogeneous simulation resources becomes a major concern. This paper proposes a common gateway in multi-architecture LVC simulation environment that converts messages between different simulation architectures and achieves a level of semantic interoperability. The gateway provides a collection of protocol-independent interfaces for simulation systems to access co-simulation conveniently. To maintain timing consistency in heterogeneous simulation environments, a time synchronization method is employed to coordinate logical time and real time. Experimental results show that the scheme is flexible and can maintain data transmission latency at a millisecond level in LVC simulation environment, which includes High Level Architecture (HLA), Data Distribution Service (DDS), and Distributed Interactive Simulation (DIS). © 2023 SPIE.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Person video alignment with human pose registration

引用

Frontiers of computer Science 2023年第4期17卷 229-231页

作者： Yu ZHANG Zihua WANG Jingyang ZHOU Siya MI School of Computer Science and Engineering and the Key Lab of Computer Network and Information Integration(Ministry of Education)Southeast UniversityNanjing 211189China School of Cyber Science and Engineering Southeast UniversityNanjing 211189China Purple Mountain Laboratories Nanjing 211111China

1 Introduction and main *** alignment,especially human action alignment,is a challenging *** purpose is to develop an algorithm to match the same process so that videos can be *** the progress that has been made in image recognition,it is still a difficult problem for distinguishing from similar frames for alignment without context information.

关键词： alignment video frames

来源：评论

学校读者我要写书评

暂无评论

CLIP4Video-Sampling: Global Semantics-Guided Multi-Granularity Frame Sampling for Video-Text Retrieval

引用

Journal of computer and Communications 2024年第11期12卷 26-36页

作者： Tao Zhang Yu Zhang School of Computer Science and Engineering The Key Lab of Computer Network and Information Integration (Ministry of Education) Southeast University Nanjing China

Video-text retrieval (VTR) is an essential task in multimodal learning, aiming to bridge the semantic gap between visual and textual data. Effective video frame sampling plays a crucial role in improving retrieval performance, as it determines the quality of the visual content representation. Traditional sampling methods, such as uniform sampling and optical flow-based techniques, often fail to capture the full semantic range of videos, leading to redundancy and inefficiencies. In this work, we propose CLIP4Video-Sampling: Global Semantics-Guided Multi-Granularity Frame Sampling for Video-Text Retrieval, a global semantics-guided multi-granularity frame sampling strategy designed to optimize both computational efficiency and retrieval accuracy. By integrating multi-scale global and local temporal sampling and leveraging the CLIP (Contrastive Language-Image Pre-training) model’s powerful feature extraction capabilities, our method significantly outperforms existing approaches in both zero-shot and fine-tuned video-text retrieval tasks on popular datasets. CLIP4Video-Sampling reduces redundancy, ensures keyframe coverage, and serves as an adaptable pre-processing module for multimodal models.

关键词： Video Sampling Multimodal Large Language Model Text-Video Retrieval CLIP Model

来源：评论

学校读者我要写书评

暂无评论

On accuracy rate of community detection and pairing in mobile social network 19

On accuracy rate of community detection and pairing in mobil...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalab.e Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Tu, Jinbin Li, Qing Wang, Yun Southeast University Key Lab of Computer Network and Information Integration School of Computer Science and Engineering Moe Nanjing China

ISBN: (纸本)9798350346558

Mobile Social network(MSN) is an opportunity network that considers the social attributes of nodes, and also uses the 'store-carry-forward' model to carry out data transfer between nodes. The community nature of nodes is an important reference in MSN to select messaging path. In this paper, a new community cluster problem based on our observed pickup strategies for car-hailing is proposed, which is involving community detection and community pairing. Then we formulate it by using T-Sorokin mobility model. The Cluster-First algorithm and Pair-First algorithm are proposed based on the defined community dependency metric to maximize the accuracy rate. Simulation experimental results show that both CFA and PFA can effectively solve this problem with an accuracy rate of over 70%. And it is concluded that cluster-first is superior to pair-first for this considered problem. © 2022 IEEE.

关键词： Data transfer

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：