检索结果-内蒙古大学图书馆

Towards Open-Vocabulary Video Semantic Segmentation

IEEE Transactions on Multimedia 2025年 27卷 2924-2934页

作者： Li, Xinhao Liu, Yun Sun, Guolei Wu, Min Zhang, Le Zhu, Ce University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Nankai University College of Computer Science Tianjin300350 China ETH Zurich Computer Vision Lab Zurich8092 Switzerland 138632 Singapore

Semantic segmentation in videos has been a focal point of recent research. However, existing models encounter challenges when faced with unfamiliar categories. To address this, we introduce the Open Vocabulary Video Semantic Segmentation (OV-VSS) task, designed to accurately segment every pixel across a wide range of open-vocabulary categories, including those that are novel or previously unexplored. To enhance OV-VSS performance, we propose a robust baseline, OV2VSS, which integrates a spatial-temporal fusion module, allowing the model to utilize temporal relationships across consecutive frames. Additionally, we incorporate a random frame enhancement module, broadening the model's understanding of semantic context throughout the entire video sequence. Our approach also includes video text encoding, which strengthens the model's capability to interpret textual information within the video context. Comprehensive evaluations on benchmark datasets such as VSPW and Cityscapes highlight OV-VSS's zero-shot generalization capabilities, especially in handling novel categories. The results validate OV2VSS's effectiveness, demonstrating improved performance in semantic segmentation tasks across diverse video datasets. © 1999-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

MOPO-HBT: A movie poster dataset for title extraction and recognition

引用

Multimedia Tools and Applications 2024年第18期83卷 54545-54568页

作者： Ghosh, Mridul Roy, Sayan Saha Banik, Bivan Mukherjee, Himadri Obaidullah, Sk Md Roy, Kaushik Dept. of Computer Science Shyampur Siddheswari Mahavidyalaya Howrah India Dept. of Computer Science & Engineering Aliah University Kolkata India Dept. of Electronics & Electrical Communication Engineering IIT Kharagpur Kharagpur India TISA Lab Dept. of Computer Science West Bengal State University Barasat India

Real-world images often encompass embedded texts that adhere to disparate disciplines like business, education, and amusement, to name a few. Such images are graphically rich in terms of font attributes, color distribution, foreground-background similarity, and component organization. This aggravates the difficulty of recognizing texts from these images. Such characteristics are very prominent in the case of movie posters. One of the first pieces of information on movie posters is the title. Automatic recognition of movie titles from images can aid in efficient indexing as well as information conveyance. However, it is accompanied by other texts like the names of actors, producers, taglines, dates, etc. Though the organization of components is somewhat similar across different film industries like Tollywood (West Bengal), Bollywood (Mumbai), and Hollywood (Los Angeles), the graffiti patterns differ in multifarious instances. To address the problem of movie title understanding, we propose a dataset named MOvie POsters-Hollywood Bollywood Tollywood (MOPO-HBT) that encompasses movie posters from the aforementioned industries. The entire dataset is publicly available (http://***/11564) for research purposes. The baseline results of title identification and recognition were obtained with a CNN-based (Convolutional Neural Network) approach, wherein the titles were extracted using the M-EAST (Modified-Efficient and Accurate Scene Text) detector model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Key Agreement and Management Scheme Based on Blockchain for 5G-Enabled Vehicular Networks

引用

China communications 2025年第3期22卷 270-287页

作者： Wang Zhihua Wang Shuaibo Wang Haofan Li Jiaze Yao Yizhe Wang Yongjian Yang Xiaolong School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Cyber Science and Engineering Zhengzhou UniversityZhengzhou 449001China Lab of National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing 100029China

5G technology has endowed mobile communication terminals with features such as ultrawideband access,low latency,and high reliability transmission,which can complete the network access and interconnection of a large number of devices,thus realizing richer application scenarios and constructing 5G-enabled vehicular ***,due to the vulnerability of wireless communication,vehicle privacy and communication security have become the key problems to be solved in vehicular ***,the large-scale communication in the vehicular networks also makes the higher communication efficiency an inevitable *** order to achieve efficient and secure communication while protecting vehicle privacy,this paper proposes a lightweight key agreement and key update scheme for 5G vehicular networks based on ***,the key agreement is accomplished using certificateless public key cryptography,and based on the aggregate signature and the cooperation between the vehicle and the trusted authority,an efficient key updating method is proposed,which reduces the overhead and protects the privacy of the vehicle while ensuring the communication ***,by introducing blockchain and using smart contracts to load the vehicle public key table for key management,this meets the requirements of vehicle traceability and can dynamically track and revoke misbehaving ***,the formal security proof under the eck security model and the informal security analysis is conducted,it turns out that our scheme is more secure than other authentication schemes in the vehicular *** analysis shows that our scheme has lower overhead than existing schemes in terms of communication and computation.

关键词： blockchain certificateless public key cryptography 5G vehicular networks key agreement key management

来源：评论

学校读者我要写书评

暂无评论

Soft-GNN:towards robust graph neural networks via self-adaptive data utilization

引用

Frontiers of computer science 2025年第4期19卷 1-12页

作者： Yao WU Hong HUANG Yu SONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China College of Information and Communication National University of Defense TechnologyWuhan 430019China Department of Computer Science and Operations Research Universitéde MontréalMontreal H3C 3J7Canada

Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high ***,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with *** presents a challenge in learning robust GNNs under noisy *** address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in *** approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global *** better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more *** evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关键词： graph neural networks node classification label noise robustness

来源：评论

学校读者我要写书评

暂无评论

New Systematic MDS Array Codes with Two Parities

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the communications Society 2024年 5卷 6329-6342页

作者： Ma, Lan Zhou, Liyang Liu, Shaoteng Chen, Xiangyu Sun, Qifu University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Huawei Technologies Company Ltd. Network Technology Lab Shenzhen518000 China

Row-diagonal parity (RDP) code is a classical (k + 2, k) systematic maximum distance separable (MDS) array code with k ≤ L - 1 under sub-packetization level l = L - 1, where L is a prime integer. When k = L-1, its encoding requires 2 - 2/k XORs per original data bit, which exactly achieves theoretical optimal lower bound. In this paper, we present three new constructions of (k+2, k) systematic MDS array codes. First, under sub-packetization level l = 4, we novelly design a (17, 15) array code C1, where k can reach the largest possible value to satisfy the MDS property. Moreover, when k ≤ 7, the encoding complexity of its subcodes can exactly achieve the theoretical optimal 2 - 2/k XORs per original data bit, and likewise, the decoding complexity of the subcodes with k ≤ 4 is also exactly optimal. Under sub-packetization level l = L - 1 with certain primes L, the second construction yields an MDS array code C2 with k ≤ L(L-1)/2, and the encoding complexity of C2 is also exactly optimal for k = L-1, 2L-3. Furthermore, based on bit permutation, the third MDS array code C3 is obtained with k ≤ L(L-1) under sub-packetization level l = 2(L-1) with certain primes L. In particular, as an extension of C2, C3 exactly achieves the optimal encoding complexity for k = 2(2L - 3), which does not hold for other array codes in the literature. © 2020 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Development of LiFi System for communication and Control in Hilly Regions 6

Development of LiFi System for Communication and Control in ...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Dabral, Adarsh Gusain, Raj Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Computer Science Engineering Dehradun India Propagation Research Lab Department of Electronics and Communication Engineering Dehradun India Department of Electronics and Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350306613

In hilly regions where cable distribution is challenging and costly traditional communication systems often face difficulties. LiFi technology emerges as a promising solution in such contexts, leveraging communication through visible light. It uses light as a medium to provide data speeds that surpass those of Wi-Fi, This research paper presents an approach for a communication system specifically designed for hilly terrains using Light Fidelity (LiFi) technology. The proposed paper start with an introduction of LiFi technology and advantages of it over conventional communication methods in these regions. However, it also acknowledges the inherent limitations of Li-Fi, such as its low range, which is especially relevant in hilly topographies. The main body of the paper details the system's architecture, comprising a transmitter for sending data, a receiver to receive data, and dual operation: text for sending massage and operate devices, and audio for communication. To underscore its practicality, the system is showcased through two applications: an SOS emergency feature for hilly terrains and a device activation/deactivation application. In conclusion, the paper provides an in-depth examination of how this tailored system functions and its potential benefits for communities and operations in hilly landscapes. © 2024 IEEE.

关键词： Arduino Hilly region communication methods Laser LiFi Microcontroller Remote Station communication

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based classification,detection,and segmentation of tomato leaf diseases:A state-of-the-art review

Artificial Intelligence in Agriculture

引用

Artificial Intelligence in Agriculture 2025年第2期15卷 192-220页

作者： Aritra Das Fahad Pathan Jamin Rahman Jim Md Mohsin Kabir M.F.Mridha Department of Computer Science and Engineering American International University-BangladeshDhaka 1229Bangladesh Institute of Information and Communication Technology Shahjalal University of Science and TechnologySylhet 3114Bangladesh Advanced Machine Intelligence Research Lab Dhaka 1207Bangladesh Bangladesh University of Business and Technology DhakaBangladesh

The early identification and treatment of tomato leaf diseases are crucial for optimizing plant productivity,efficiency and *** by the farmers poses the risk of inadequate treatments,harming both tomato plants and *** of disease diagnosis is essential,necessitating a swift and accurate response to misdiagnosis for early *** regions are ideal for tomato plants,but there are inherent concerns,such as weather-related *** diseases largely cause financial losses in crop *** slow detection periods of conventional approaches are insufficient for the timely detection of tomato *** learning has emerged as a promising avenue for early disease *** study comprehensively analyzed techniques for classifying and detecting tomato leaf diseases and evaluating their strengths and *** study delves into various diagnostic procedures,including image pre-processing,localization and *** conclusion,applying deep learning algorithms holds great promise for enhancing the accuracy and efficiency of tomato leaf disease diagnosis by offering faster and more effective results.

关键词： Deep learning Tomato leaf disease Classification Detection Segmentation Imaging

来源：评论

学校读者我要写书评

暂无评论

BrainPST: Pre-training Stacked Transformers for Dynamic Brain Functional Network Analysis

BrainPST: Pre-training Stacked Transformers for Dynamic Brai...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Hu, Jinlong Huang, Yangmin Zhuo, Yi Dong, Shoubin South China University of Technology Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350337488

Deep learning methods have been applied for dynamic brain functional network analysis recently. However, they are usually restricted by the complex spatio-temporal dynamics and the limited labeled data. In this paper, we proposed a stacked Transformer neural network, namely BrainPST, to capture spatio-temporal patterns for dynamic brain functional network classification. BrainPST model integrated spatial and temporal information by stacking two Transformers: one for learning snapshot networks and the other for learning sequence of functional connections. Unlike recent models, BrainPST was designed to pre-train the stacked Transformer network by leveraging unlabeled existing brain imaging data. A pre-training framework with designed pre-training strategies was proposed to learn general spatio-temporal representations from the unlabeled brain networks, and to fine-tune the pre-trained model in downstream tasks. BrainPST is a conceptually simple and effective model. The results of experiments showed the BrainPST model without pre-training achieved comparative performance with the recent models, and the pre-trained BrainPST obtained new state-of-the-art performance. The pre-trained BrainPST improved 3.92% of AUC compared with the model without pre-training. © 2023 IEEE.

关键词： Classification Dynamic brain functional networks Pre-training Transformer

来源：评论

学校读者我要写书评

暂无评论

Transformer and Snowball Graph Convolution Learning for Brain Functional Network Analysis

Transformer and Snowball Graph Convolution Learning for Brai...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Hu, Jinlong Huang, Yangmin Dong, Shoubin South China University of Technology Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350337488

Advanced deep learning methods, especially graph neural networks (GNNs), are increasingly expected to learn from brain functional network data and predict brain disorders. In this paper, we proposed a novel Transformer and snowball encoding networks (TSEN) for brain functional network classification, which introduced Transformer architecture with graph snowball connection into GNNs for learning whole-graph representation. TSEN combined graph snowball connection with graph Transformer by snowball encoding layers, which enhanced the power to capture multi-scale information and global patterns of brain functional networks. TSEN also introduced snowball graph convolution as position embedding in Transformer structure, which was a simple yet effective method for capturing local patterns naturally. We evaluated the proposed model by two large-scale brain functional network datasets from autism spectrum disorder and major depressive disorder respectively, and the results demonstrated that TSEN outperformed the state-of-the-art GNN models and the graph-transformer based GNN models. © 2023 IEEE.

关键词： Brain disorders Graph neural networks Snowball graph convolutional networks Transformer

来源：评论

学校读者我要写书评

暂无评论

Prediction of Potential Repurposed Drugs against SARS-CoV-2 based on Text Mining and Molecular Docking Analysis 6

Prediction of Potential Repurposed Drugs against SARS-CoV-2 ...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Zhou, Jie Xu, Yi-Qing Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798400707674

Many research papers focusing the relationships between drugs and coronavirus-related protein interactions are indexed in the PubMed database. These studies provide a reference for predicting potential repurposed drugs against SARS-CoV-2. Drug repurposing, the most efficient strategy to quickly deploy new effective therapeutic drugs against SARS-CoV-2, can shorten the time and reduce the cost compared to de novo drug discovery. The purpose of this study was to predict potential repurposed drugs and drug pairs against SARS-CoV-2 using text mining and molecular docking analysis. We first constructed a coronavirus-related protein names list and a drug names list using the relevant protein and drug databases. We also constructed a qualifier list. A crawler program was implemented to retrieve the desired parts from the relevant papers in the PubMed database using records from the three query lists. Based on these extracted parts, we constructed a document set, a document drug names set, and a document protein names set. Then, we used the method proposed in our previous work to calculate the document vector of each document in the document set and the TF, IDF, and TF-IDF values. We calculated the vectors of each drug and protein in the document drug names set and document protein names set based on the document vectors. The cosine similarity between the protein vector and drug vector was calculated and the score of the pair of protein and drug was defined by the cosine similarity. Next, we selected the protein-drug pairs that scored above a given threshold as the predicted interactions for coronavirus-related protein-drug pairs and then extracted all the drugs from these predicted interactions and combined them to form distinct drug pairs. Finally, the drugs with PubChem 3D structure were simulated by a molecular docking tool with the four recently identified important SARS-CoV-2 proteins, and the drug pairs were simulated by the molecular docking tool with the SARS-CoV-2

关键词： Coronavirus

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：