检索结果-内蒙古大学图书馆

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

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

A fault-tolerant multicast tree approach based on the family hierarchy tunnel

A fault-tolerant multicast tree approach based on the family...

引用

16th International Conference on Mechatronics Technology, ICMT 2012

作者： Zhou, Yan-Ling Shen, Yu-Feng Key Lab. of Network and Intelligent Information Processing Department of Computer Science and Technology University Hefei Anhui China Computer Science and Technology Anhui Sanlian University Hefei Anhui China

ISBN: (纸本)9787900769428

Fault-tolerant recovery in Multicast communication is an important issue. An ideal multicast fault-tolerant approach can save network resources, reduce the delay and cost, realize quick recovery. In this paper, we propose a new multicast fault-tolerant approach-FH-TFTM based on proposed multicast fault-tolerant algorithms. It can go over problems faced in traditional approaches, for example node failure, unpredictable problems, time delay, network cost and loop avoidance. FH-TFTM can reduce consuming network resources, and carry out effectively setting up backup paths.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

RoKEPG: RoBERTa and Knowledge Enhancement for Prescription Generation of Traditional Chinese Medicine

RoKEPG: RoBERTa and Knowledge Enhancement for Prescription G...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Pu, Hua Mi, Jiacong Lu, Shan He, Jieyue Southeast University School of Computer Science and Engineering Key Lab of Computer Network and Information Integration Moe Jiangsu Nanjing210018 China Nanjing Fenghuo Tiandi Communication Technology Co. Ltd Jiangsu Nanjing China

ISBN: (纸本)9798350337488

Traditional Chinese medicine (TCM) prescription is the most critical form of TCM treatment, and uncovering the complex nonlinear relationship between symptoms and TCM is of great significance for clinical practice and assisting physicians in diagnosis and treatment. Although there have been some studies on TCM prescription generation, these studies consider a single factor and directly model the symptom-prescription generation problem mainly based on symptom descriptions, lacking guidance from TCM knowledge. To this end, we propose a RoBERTa and Knowledge Enhancement model for Prescription Generation of Traditional Chinese Medicine (RoKEPG). RoKEPG is firstly pre-trained by our constructed TCM corpus, followed by fine-tuning the pre-trained model, and the model is guided to generate TCM prescriptions by introducing four classes of knowledge of TCM through the attention mask matrix. Experimental results on the publicly availab.e TCM prescription dataset show that RoKEPG improves the F1 metric by about 2% over the baseline model with the best results. © 2023 IEEE.

关键词： Deep learning Pre-trained language models Traditional Chinese medicine prescription generation

来源：评论

学校读者我要写书评

暂无评论

Improving efficiency of security schemes in automated trust negotiation

Improving efficiency of security schemes in automated trust ...

引用

2nd International Workshop on Education Technology and computer Science, ETCS 2010

作者： Liu, Bailing Lu, Hongwei Zhao, Yizhu Ge, Feng College of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Key Lab. of Information Network Security Ministry of Public Security Shanghai China

ISBN: (纸本)9780769539874

Automated trust negotiation (ATN) is an approach that establishes mutual trust between strangers wishing to share resources or conduct business by gradually requesting and disclosing digitally signed credentials. When designing security schemes and systems in ATN, the negotiation efficiency, which is a desirable property, is not considered sufficiently. In this paper, a useful model of P.E. evaluation is proposed to enhance negotiation efficiency by improving the efficiency of security schemes used in ATN. The useful model of P.E. evaluation is responsible for choosing a most appropriate policy among several alternative policies that can advance a negotiation at the same time, which makes the negotiation more efficient. © 2010 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of optimal antenna scheme in transmit diversity systems

Performance analysis of optimal antenna scheme in transmit d...

引用

2010 6th International Conference on Natural Computation, ICNC'10

作者： Wang, Yong Li, Hui Wang, Xiyuan Key Lab. of Computer Network and Information Security School of Telecommunications Engineering Xidian University Xi'an China Science Research Department Xidian University Xi'an China

ISBN: (纸本)9781424459612

The performance of transmit antenna selection is investigated. The exact closed-form expressions for the average BER and average SNR in MRT systems and EGT systems are proposed. The minimum number of increased transmit antennas sufficient to compensate the performance loss for using part of transmit antennas is analyzed. The validity of the performance analysis is demonstrated by computer simulation. © 2010 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

dptCry: an approach to decrypting ransomware WannaCry based on API hooking

引用

CCF Transactions on networking 2019年第3-4期2卷 207-216页

作者： Guang Cheng Chunsheng Guo Yongning Tang Southeast University Key Lab of Computer Network and Information Integration (Southeast University) Ministry of Education Illinois State University

来源：评论

学校读者我要写书评

暂无评论

VGI as a dynamically updating data source in location-based services in urban environments

VGI as a dynamically updating data source in location-based ...

引用

2nd International Workshop on Ubiquitous Crowdsourcing, UbiCrowd'11, Co-located with UbiComp 2011

作者： Mooney, Peter Sun, Huabo Yan, Lei Department of Computer Science National University of Ireland Maynooth Co. Kildare Ireland Beijing Key Lab. of Spatial Information Integration and Its Applications Peking University Beijing 100871 China

ISBN: (纸本)9781450309271

Urban environments, or living cities, share the characteristic of a high degree of organized complexity. This complexity arises from the components of the urban fabric: streets, shops, offices, houses, pedestrian zones, green spaces, plazas, parking lots, transportation networks, natural features, etc. Citizens in urban spaces are using location-based services (LBS) on their mobile devices in ever increasing numbers. The collection of spatial data and information on large urban spaces, by traditional methods of mapping and geographical survey, is expensive and resource intensive. These methods cannot capture the dynamic nature of urban environments within an acceptable time-frame for use in LBS. Volunteered Geographic information (VGI) is a recent phenomenon where citizens and/or other groups collect geographic information using smartphones, GPS, etc. In this paper we discuss how crowdsouring and VGI can be used as a complement/addition, or in some cases a replacement, to traditionally generated sources of spatial data and information. © 2011 ACM.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

KGAPG: Knowledge-Aware Neural Group Representation Learning for Attentive Prescription Generation of Traditional Chinese Medicine

KGAPG: Knowledge-Aware Neural Group Representation Learning ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shuchen Li Wei Wang Jieyue He Key Lab of Computer Network & Information Integration MOE Southeast University Nanjing China

ISBN: (纸本)9781665429825

Prescriptions play an essential role in the process of Traditional Chinese Medicine (TCM) diagnosis and treatment. Prescription generation is to generate a set of herbs to treat the symptoms of a patient by analyzing the relationship between symptoms and herbs. Although there have been a couple of studies to generate prescriptions, they have ignored the implicit relationship between the different symptoms of the patients. In addition, abundant semantic information and interpretability of the knowledge graph can help to portray the complicated relationships between the various modules of TCM. Therefore, this paper proposes a Knowledge-Aware neural Group representation learning model for Attentive Prescription Generation of Traditional Chinese Medicine (KGAPG), which regards the prescription generation task as a group recommendation problem. More specifically, multiple symptoms of a patient are considered as a symptom group and the complicated semantic information between symptoms and herbs can be captured by the knowledge graph. The syndrome information of multiple symptoms which is summarized by a group aggregation method based on the attention mechanism is applied to simulate the actual process of TCM diagnosis and treatment. The experiment results demonstrate that KGAPG is effective on a TCM prescription benchmark dataset, and its evaluation indicators of Precision, Recall and NDCG exceed other state-of-the-art methods.

关键词： Representation learning Conferences Semantics Benchmark testing Task analysis Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Coherent depth test scheme in FreePipe

Coherent depth test scheme in FreePipe

引用

作者： Liu, Fang Huang, Mengcheng Liu, Xuehui Wu, En-Hua SuperComputing Center Computer Network Information Center Chinese Academy of Sciences China State Key Lab. of Computer Sciences Institute of Software Chinese Academy of Sciences China University of Macau China

ISBN: (纸本)9781450304597

This paper presents a rasterization rendering pipeline namely FreePipe. The system builds a bridge between the traditional graphics pipelines and the general purpose computing architecture CUDA by taking advantages of both sides. The core of FreePipe is a z-buffer based rasterizer entirely implemented in CUDA. The graphics pipeline can be easily mapped to the CUDA programming model with each stage fully open to the programmers. Within this flexible architecture, we propose a coherent depth test scheme for concurrent capture of both depth and color attributes using the atomicCAS operation in CUDA. The scheme can be easily extended to multiple level for efficient rendering of order independent transparency, which has significant performance improvement over the state-of-the-art methods based on traditional graphics pipelines. Copyright © 2010 by the Association for Computing Machinery, Inc.

关键词： Rasterization

来源：评论

学校读者我要写书评

暂无评论

The extended FDH sequences

The extended FDH sequences

引用

作者： Ma, WenPing He, YeFeng Sun, Shaohui Education Key Lab. of Computer Network and Information Security Xidian University Xi'an 710071 China Datang Mobile Communications Equipment Co. Lid. China

A new construction method for polyphase sequences with two-valued periodic auto- and crosscorrelation functions is proposed. This method gives L families of polyphase sequences for each prime length L which is bigger than three. For each family of sequences, the out-of-phase auto- and crosscorrelation functions are proved to be constant and asymptotically reach the Sarwate bound. Furthermore, it is shown that sequences of each family are mutually orthogonal. Copyright © 2010 The Institute of Electronics, information and Communication Engineers.

关键词： Autocorrelation Crosscorrelation Polyphase sequences

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：