检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhang, Qin Liang, Zhuoluo Ngueilbaye, Alladoumbaye Liu, Han Zhou, Hong Huang, Joshua Zhexue College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Guangzhou University China

The recent emergence of time series contrastive clustering methods can be categorized into two classes. The first class uses contrastive learning for universal representations, which can be effective in various downstream tasks, but overlooks important categorical information and clustering objectives, leading to unsuitable models. The second class incorporates contrastive learning into clustering objectives but fails to fully explore potential connections and structures between time series data. To this end, we propose the "Time Series Graph-augmented Contrastive Clustering (TSGCC) method", a graph-augmented contrastive learning framework aiming to create cluster-friendly features and assignments by iteratively optimizing contrastive loss. The method uses a weighted KNN graph to build positive and negative sample pairs, projecting the instances into a feature space with the dimensionality number of clusters. Experimental results demonstrate that TSGCC outperforms 18 advanced time-series clustering methods on the 36 representatives out of the 128 UCR benchmarks, achieving the best clustering results on 12 datasets, with the highest average rank (3.22) of RI and the second-highest average rank (3.89) of NMI among 18 clustering methods. We further compared our method with recent approaches on the entire set of 128 UCR datasets, demonstrating our method's broad applicability and effectiveness. © 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

Multi-view aggregation and multi-relation alignment for few-shot fine-grained recognition

引用

Expert Systems with Applications 2025年 283卷

作者： Chen, Jiale Xu, Feng Lyu, Xin Zeng, Tao Li, Xin Chen, Shangjing College of Computer Science and Software Engineering Hohai University Nanjing210024 China School of Computer Engineering Jiangsu Ocean University Lianyungang222005 China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing211106 China

Few-shot fine-grained recognition (FS-FGR) aims to recognize nuanced categories with a limited number of labeled samples that were not encountered during training. Previous work has made significant progress by enhancing the learning of foreground refined regions and the alignment of consistent semantics. However, the detrimental impact of insufficient background diversity on constructing representative category prototypes has been overlooked. Meanwhile, the alignment of semantically consistent features has been hampered by the reliance on singular metrics, resulting in suboptimal feature extraction. To address the limitations above, a novel framework with multi-view aggregation and multi-relation alignment (MVRA) is proposed. In this framework, we strive to refine category prototypes by generating and consolidating multiple views from limited learnable samples. Specifically, we generate foreground-refined views, pinpointing discriminative regions, and background-obfuscated views, broadening the landscape of background diversity. Further, without relying on the entire prior, a global label assignment module is designed to automatically assign reliable labels to the query set samples. Finally, armed with these credible labels, the multi-relation alignment module harnesses the enriched views and their semantic congruencies, facilitating robust feature extraction. The effectiveness and outstanding performance of MVRA are evaluated through extensive experiments conducted on three fine-grained benchmark datasets. © 2025

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

What Makes Good In-Context Demonstrations for Code Intelligence Tasks with LLMs? 23

What Makes Good In-Context Demonstrations for Code Intellige...

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated software engineering

作者： Shuzheng Gao Xin-Cheng Wen Cuiyun Gao Wenxuan Wang Hongyu Zhang Michael R. Lyu School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong China School of Big Data and Software Engineering Chongqing University China

ISBN: (纸本)9798350329964

Pre-trained models of source code have gained widespread popularity in many code intelligence tasks. Recently, with the scaling of the model and corpus size, large language models have shown the ability of in-context learning (ICL). ICL employs task instructions and a few examples as demonstrations, and then inputs the demonstrations to the language models for making predictions. This new learning paradigm is training-free and has shown impressive performance in various natural language processing and code intelligence tasks. However, the performance of ICL heavily relies on the quality of demonstrations, e.g., the selected examples. It is important to systematically investigate how to construct a good demonstration for code-related tasks. In this paper, we empirically explore the impact of three key factors on the performance of ICL in code intelligence tasks: the selection, order, and number of demonstration examples. We conduct extensive experiments on three code intelligence tasks including code summarization, bug fixing, and program synthesis. Our experimental results demonstrate that all the above three factors dramatically impact the performance of ICL in code intelligence tasks. Additionally, we summarize our findings and provide takeaway suggestions on how to construct effective demonstrations, taking into account these three perspectives. We also show that a carefully-designed demonstration based on our findings can lead to substantial improvements over widely-used demonstration construction methods, e.g., improving BLEU-4, EM, and EM by at least 9.90%, 175.96%, and 50.81% on code summarization, bug fixing, and program synthesis, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous Emergency Landing on 3D Terrains: Approaches for Monocular Vision-based UAVs

Autonomous Emergency Landing on 3D Terrains: Approaches for ...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Weiming Du Junmou Lin Binqing Du Uddin Md. Borhan Jianqiang Li Jie Chen College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

With the increasing use of unmanned aerial vehicles (UAVs) in a variety of applications, their safety has become a critical concern. UAVs face numerous emergencies during missions, in these situations, the UAVs need to autonomously find a suitable landing site, plan flight routes, and avoid obstacles in unstructured environments. However, due to the limitations of computing power and sensors, it is challenging to achieve this goal. This research aims to explore the monocular emergency autonomous landing algorithm. Specifically, this work focuses on extracting depth and vision information. A topology information extractor is designed to convert image to graph and assess the connectivity of terrain. Additionally, a depth information extractor is designed to calculate the slope and roughness of the ground. A 3D topology optimizer is designed to optimize the graph by depth information and evaluate the landing suitability by a heuristic strategy. To make the action decision, a hybrid decision network (DGN) based on 3D topology information is proposed. Finally, this work build a simulated scenario based on real scene to verify the efficiency of DGN. The results of the experiment show that DGN outperforms its counterparts in terms of action prediction accuracy and landing success rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative DNNs Inference with Joint Model Partition and Compression in Mobile Edge-Cloud Computing Networks

Collaborative DNNs Inference with Joint Model Partition and ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yaxin Tang Xiuhua Li Hui Li Zhengyi Yang Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Departrnent of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Mobile edge-cloud computing utilizes the computing resources of edge devices and cloud servers to execute complex deep neural networks (DNNs) for collaborative inference. However, many existing collaborative inference methods do not fully consider the limited resources of edge devices, resulting in high inference latency. In this paper, we design an integrated computational framework that combines model partition and compression to reduce inference latency. Specifically, we partition a DNN model at the middle layer and deploy the previous layer on the edge device and the subsequent layer on the cloud server respectively. We propose a collaborative dual-agent reinforcement learning algorithm called CPCDRL to determine partition point and compression ratios. It enables adaptive adjustments of compression ratios based on various partition points, with the overarching goal of minimizing the inference latency across the entire DNN model. The proposed algorithm can significantly reduce computational latency while minimizing accuracy loss compared to the baseline schemes.

关键词： Performance evaluation Adaptation models Computational modeling Simulation Collaboration Artificial neural networks Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Deep Reinforcement Learning for Computation Offloading in Multi-IRS Assisted Mobile Edge Computing Networks

Multi-Agent Deep Reinforcement Learning for Computation Offl...

引用

IEEE Conference on Wireless Communications and Networking

作者： Lingxiao Chen Xiuhua Li Chuan Sun Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Mobile edge computing (MEC) as a potential technology can offload tasks from user devices (UDs) to network edges to alleviate network congestion and reduce task execution delay. However, computation offloading faces two challenges: 1) Poor wireless channel quality causes high transmission delay; 2) Computing tasks may be obtained by eavesdroppers (Eves) during task offloading. Therefore, we consider deploying intel-ligent reflecting surface (IRS) in MEC networks to increase data transmission rate and ensure data transmission security. This paper investigates the issue of joint computation offloading and resource allocation in a multi-IRS assisted MEC network. Our goal is to minimize task execution delay. To address this problem, we propose a multi-agent deep deterministic policy gradient algorithm to determine the optimal offloading strategy for each UD. Simulation results show that the proposed algorithm can significantly reduce task execution delay and ensure data transmission security.

关键词： Wireless communication Multi-access edge computing Simulation Delays data communication Security Resource management

来源：评论

学校读者我要写书评

暂无评论

Competitive and Cooperative Computation Offloading for Intensive Heterogeneous Tasks in Vehicular Edge Computing Networks

Competitive and Cooperative Computation Offloading for Inten...

引用

IEEE International Conference on Communications (ICC)

作者： Yuan Chen Xiuhua Li Guozeng Xu Ling Liu Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Computation offloading is widely used in vehicular edge computing (VEC) networks to satisfy the computational intensity and latency sensitivity requirements. However, many existing offloading algorithms do not comprehensively consider the dynamically changing characteristics of heterogeneous tasks within a roadside unit (RSU), resulting in tasks timeout and being dropped. In this paper, we design a competitive and cooperative computation offloading (C3O) model to reduce task execution latency. Specifically, when intensive heterogeneous tasks are generated, these vehicles jointly compete for the computing resource of a RSU, or they can also offload tasks to the task vehicle (TaV) with free computing resource. Meanwhile, We analyze the latency model of local execution and offloading to RSU or TaV execution and formulate a sequential task offloading decision problem, NP-hard. To address it, we propose a multi-agent reinforcement learning algorithm based on C3O (MARC3O) to intelligently determine the computation offloading policy for each vehicle according to the state of VEC networks. Simulation results demonstrate that the proposed algorithm can significantly reduce task execution latency and improve task completion rates compared with baseline schemes.

关键词： Analytical models Sensitivity Costs Computational modeling Simulation Heuristic algorithms Collaboration

来源：评论

学校读者我要写书评

暂无评论

CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation

arXiv

引用

arXiv 2024年

作者： Zhu, Wenqi Cao, Jiale Xie, Jin Yang, Shuangming Pang, Yanwei The School of Electrical and Information Engineering Tianjin University Tianjin300072 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China The School of Big Data and Software Engineering Chongqing University Chongqing401331 China

Open-vocabulary video instance segmentation strives to segment and track instances belonging to an open set of categories in a videos. The vision-language model Contrastive Language-Image Pre-training (CLIP) has shown robust zero-shot classification ability in image-level open-vocabulary tasks. In this paper, we propose a simple encoder-decoder network, called CLIP-VIS, to adapt CLIP for open-vocabulary video instance segmentation. Our CLIP-VIS adopts frozen CLIP and introduces three modules, including class-agnostic mask generation, temporal topK-enhanced matching, and weighted open-vocabulary classification. Given a set of initial queries, class-agnostic mask generation introduces a pixel decoder and a transformer decoder on CLIP pre-trained image encoder to predict query masks and corresponding object scores and mask IoU scores. Then, temporal topK-enhanced matching performs query matching across frames using the K mostly matched frames. Finally, weighted open-vocabulary classification first employs mask pooling to generate query visual features from CLIP pre-trained image encoder, and second performs weighted classification using object scores and mask IoU scores. Our CLIP-VIS does not require the annotations of instance categories and identities. The experiments are performed on various video instance segmentation datasets, which demonstrate the effectiveness of our proposed method, especially for novel categories. When using ConvNeXt-B as backbone, our CLIP-VIS achieves the AP and APn scores of 32.2% and 40.2% on the validation set of LV-VIS dataset, which outperforms OV2Seg by 11.1% and 23.9% respectively. We will release the source code and models at https://***/zwq456/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

CRANET: CASCADE RESIDUAL ATTENTION NETWORK FOR CROWD COUNTING

CRANET: CASCADE RESIDUAL ATTENTION NETWORK FOR CROWD COUNTIN...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Wu, Zhongyuan Sang, Jun Shi, Ying Liu, Qi Sang, Nong Liu, Xinyue School of Big Data and Software Engineering Chongqing University China School of Artificial Intelligence and Automation Huazhong University of Science and Technology China

ISBN: (纸本)9781665438643

The existing approaches for crowd counting usually estimate a density map with deep convolutional neural network to obtain the crowd counts. Influenced by the background noises, some approaches may result in incorrect pedestrian heads recognition. Therefore, some approaches try to estimate an attention map to mask background noises. However, since the background noises are complex and stochastic, single attention is of incompetence to recognize them. Consequently, we proposed softer, and more reasonable Cascade Residual Attention Network (CRANet), which cascades several effective residual attention modules to mask background noises. Also, due to pixel-level isolation of Euclidean loss, we designed a novel Pyramid Structural Similarity Loss to train our CRANet. The proposed approach was evaluated on three crowd datasets. Experimental results demonstrated that our approach achieves the state-of-the-art. © 2021 IEEE

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Weighted Flat Lattice Transformer-based Knowledge Extraction Architecture for Chinese Named Entity Recognition

A Weighted Flat Lattice Transformer-based Knowledge Extracti...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hengwei Zhang Yuejia Wu Jian-Tao Zhou Inner Mongolia University College of Computer Science Hohhot China Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Named Entity Recognition (NER) is one of the contents of Knowledge Extraction (KE) that transforms data into knowledge representation. However, Chinese NER faces the problem of lacking clear word boundaries that limit the effectiveness of the KE. Although the flat lattice Transformer (FLAT) framework, which converts lattice structure into a flat structure including a set of spans, can effectively improve this problem and obtain advanced results, there still exist the problems of insensitivity to entity importance weights and insufficient feature learning. This paper proposes a weighted flat lattice Transformer architecture for Chinese NER, namely WFLAT. The WFLAT first adds a weight matrix into self-attention calculation, which can obtain finer-grained partitioning of entities to improve experimental performance, and then adopts a multi-layer Transformer encoder with each layer using a multi-head self-attention mechanism. Extensive experimental results on benchmarks demonstrate that our proposed KE model can obtain state-of-the-art performance for the Chinese NER task.

关键词： Representation learning Computational modeling Memory management Lattices Named entity recognition Transforms Knowledge representation

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：