检索结果-内蒙古大学图书馆

BPCoach: Exploring Hero Drafting in Professional MOBA Tournaments via Visual Analytics

Proceedings of the ACM on Human-computer Interaction 2024年第CSCW1期8卷 1-31页

作者： Liu, Shiyi Ma, Ruofei Zhao, Chuyi Li, Zhenbang Xiao, Jianpeng Li, Quan School of Information Science and Technology ShanghaiTech University Shanghai China Department of Computer Science Tufts University MedfordMA United States Guangzhou Qucheng Culture Media Co. Guangzhou China School of Information Science and Technology ShanghaiTech University Shanghai Engineering Research Center of Intelligent Vision and Imaging Shanghai China

Hero drafting for multiplayer online arena (MOBA) games is crucial because drafting directly affects the outcome of a match. Both sides take turns to "ban"/"pick" a hero from a roster of approximately 100 heroes to assemble their drafting. In professional tournaments, the process becomes more complex as teams are not allowed to pick heroes used in the previous rounds with the "best-of-N" rule. Additionally, human factors including the team's familiarity with drafting and play styles are overlooked by previous studies. Meanwhile, the huge impact of patch iteration on drafting strengths in the professional tournament is of concern. To this end, we propose a visual analytics system, BPCoach, to facilitate hero drafting planning by comparing various drafting through recommendations and predictions and distilling relevant human and in-game factors. Two case studies, expert feedback, and a user study suggest that BPCoach helps determine hero drafting in a rounded and efficient manner. © 2023 Copyright held by the owner/author(s).

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Knowledge Extraction from Technical Reports Based on Large Language Models: An Exploratory Study 15

Knowledge Extraction from Technical Reports Based on Large L...

引用

15th International Conference on Information and Knowledge Technology, IKT 2024

作者： Bakhtiari, Parsa Bashiri, Hassan Khalilipour, Alireza Nasiripour, Masoud Challenger, Moharram Department of Computer Engineering Hamedan University of Technology Hamedan Iran Department of Computer Science University of Antwerp Flanders Make Strategic Research Center Antwerp Belgium

ISBN: (纸本)9798331522254

Organizations and companies possess a vast amount of documents generated over the years. These documents contain valuable information and knowledge that can be instrumental in resolving ambiguities and challenges experts face. Information retrieval and knowledge management systems are tools for extracting documents relevant to users’ informational needs, addressing part of the knowledge extraction challenge from these document collections. With the emergence of generative artificial intelligence and large language models that exhibit strong capabilities in understanding textual documents, knowledge extraction solutions have shifted towards utilizing these models. Large language models possess general knowledge obtained from pre-training methods, and there are various approaches to infuse domain-specific knowledge into the general understanding of the language model. This research first examines the possible techniques for fine-tuning a large language model in a specific domain. We then train the model using fine-tuning methods on a collection of documents and technical reports from the industry. Finally, we measure the improvement in the large language model’s capability to extract domain-specific knowledge. © 2024 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Deep Ensemble Learning with Frame Skipping for Face Anti-Spoofing 12

Deep Ensemble Learning with Frame Skipping for Face Anti-Spo...

引用

12th International Conference on Image Processing Theory, Tools and Applications, IPTA 2023

作者： Muhammad, Usman Hoque, Md Ziaul Oussalah, Mourad Laaksonen, Jorma University of Oulu Center for Machine Vision and Signal Analysis Finland Aalto University Department of Computer Science Finland

ISBN: (纸本)9798350325416

Face presentation attacks, also known as spoofing attacks, pose a substantial threat to biometric systems that rely on facial recognition systems, such as access control systems, mobile payments, and identity verification systems. To mitigate the spoofing risk, several video-based methods have been presented in the literature that analyze facial motion in successive video frames. However, estimating the motion between adjacent frames is a challenging task and requires high computational cost. In this paper, we rephrase the face anti-spoofing task as a motion prediction problem and introduce a deep ensemble learning model with a frame skipping mechanism. In particular, the proposed frame skipping adopts a uniform sampling approach by dividing the original video into video clips of fixed size. By doing so, every nth frame of the clip is selected to ensure that the temporal patterns can easily be perceived during the training of three different recurrent neural networks (RNNs). Motivated by the performance of individual RNNs, a meta-model is developed to improve the overall detection performance by combining the prediction of individual RNNs. Extensive experiments were performed on four datasets, and state-of-the-art performance is reported on MSU-MFSD (3.12%), Replay-Attack (11.19%), and OULU-NPU (12.23%) databases by using half total error rates (HTERs) in the most challenging cross-dataset testing scenario. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

LEARNING SEMANTIC PROXIES FROM VISUAL PROMPTS FOR PARAMETER-EFFICIENT FINE-TUNING IN DEEP METRIC LEARNING

arXiv

引用

arXiv 2024年

作者： Ren, Li Chen, Chen Wang, Liqiang Hua, Kien Department of Computer Science University of Central Florida United States Center for Research in Computer Vision

Deep Metric Learning (DML) has long attracted the attention of the machine learning community as a key objective. Existing solutions concentrate on fine-tuning the pre-trained models on conventional image datasets. As a result of the success of recent pre-trained models trained from larger-scale datasets, it is challenging to adapt the model to the DML tasks in the local data domain while retaining the previously gained knowledge. In this paper, we investigate parameter-efficient methods for fine-tuning the pre-trained model for DML tasks. In particular, we propose a novel and effective framework based on learning Visual Prompts (VPT) in the pre-trained vision Transformers (ViT). Based on the conventional proxy-based DML paradigm, we augment the proxy by incorporating the semantic information from the input image and the ViT, in which we optimize the visual prompts for each class. We demonstrate that our new approximations with semantic information are superior to representative capabilities, thereby improving metric learning performance. We conduct extensive experiments to demonstrate that our proposed framework is effective and efficient by evaluating popular DML benchmarks. In particular, we demonstrate that our fine-tuning method achieves comparable or even better performance than recent state-of-the-art full fine-tuning works of DML while tuning only a small percentage of total parameters. Code is available at https://***/Noahsark/ParameterEfficient-DML. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Probing quantum causality with geometric asymmetry in spatial-temporal correlations

引用

science China(Information sciences) 2024年第9期67卷 294-305页

作者： Yu MENG Zheng-Hao LIU Zhikuan ZHAO Peng YIN Yi-Tao WANG Wei LIU Zhi-Peng LI Yuan-Ze YANG Zhao-An WANG Jin-Shi XU Shang YU Jian-Shun TANG Chuan-Feng LI Guang-Can GUO CAS Key Laboratory of Quantum Information University of Science and Technology of China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Department of Computer Science Eidgen?ssische Technische Hochschule Zürich Hefei National Laboratory Department of Physics Imperial College London Research Center for Quantum Sensing Zhejiang Lab

Causation promotes the understanding of correlation to an advanced stage by elucidating its underlying mechanism. Although statisticians have specified the possible causal relations among correlations,inferring causal structures is impossible from only the observed correlations in the classical world. Quantum correlations encapsulating the most defining aspects of quantum physics have taken a new turn for the causal inference problem — the two-point spatial and temporal quantum correlations with observationally discernible characteristics correspond exactly to the two most basic causal structures. However, a direct causal interpretation for quantum correlations has only been established in very limited cases. Here, we explore to what extent quantum correlations promote causal inference. Theoretically, we have found that the distinguishable causal regime of two-point Pauli correlations can be expanded from a single value to an asymmetric interval, and the causal structures determining the quantum correlations can be interpreted by a simple distance criterion. Experimentally, we have devised and implemented a versatile non-unital quantum channel in an optical architecture to directly observe such an asymmetric interval. The setup enabled quantum causal inference without any requirement of active intervention, which is impossible in the classical realm. Our work facilitates the identification of causal links among quantum variables and provides insight into characterizing causation and spatial-temporal correlation in quantum mechanics.

关键词： causality quantum information quantum channel channel-state duality non-unital channel

来源：评论

学校读者我要写书评

暂无评论

Decentralizing Social Data: A Blockchain-Based Approach to Transparent and Trustworthy Social Networks 5

Decentralizing Social Data: A Blockchain-Based Approach to T...

引用

5th IEEE Middle East and North Africa COMMunications Conference, MENACOMM 2025

作者： El Ghor, Hussein Nakhal, Bilal Nasr, Sara Daher, Mohamad MUBS University ARCAS Research Center Faculty of Arts and Sciences Beirut Lebanon Beirut Arab University Mathematics and Computer Science Department Beirut Lebanon Lebanese University Faculty of Science Department of Computer Science Beirut Lebanon AUT University Department of Computer Science and Information Technology Beirut Lebanon

ISBN: (纸本)9798331519957

The rise of online social network (OSN) platforms has revealed pivotal issues with regards to data transparency and the concerns on the user's consent. Users are barely aware of how their data is used. To this end, this paper investigates the notion of applying blockchain technology for decentralizing social data, thus bringing more privacy and trust to the abstract concept of OSN platforms. We propose a Blockchain-Based Distributed Social Network System (B2DSN) that uses Hyperledger Fabric and InterPlanetary File System (IPFS) to secure sovereignty rights of data and offer greater control to users' data subjects. Hyperledger fabric is used to collect friends and data that are analyzed from social networks. We integrate consensus and verification methods directly within topic-based communities to provide trustworthiness of OSN platforms and eliminate the dissemination of rumors, and fake news. The feasibility of B2DSN is proved based on the integration of decentralized overlay network data flow, data sovereignty and verification and topic-based communities. The experimental simulation for data integrity demonstrates that the B2DSN model based on blockchain is feasible in securing and verifying the authenticity of social data even for large-scale OSNs. © 2025 IEEE.

关键词： Blockchain hyperledger fabric IPFS privacy Social network transparency

来源：评论

学校读者我要写书评

暂无评论

Metasurfaces for next-generation wireless communication systems

引用

National science Review 2023年第8期10卷 17-19页

作者： Younes Ra'di Nikita Nefedkin Petar Popovski Andrea Alù Department of Electrical Engineering and Computer Science Syracuse University Photonics Initiative Advanced Science Research Center City University of New York Department of Electronic Systems Aalborg University Physics Program Graduate Center City University of New York

The pace of development in the world of 5G communication systems has proven to be much more demanding than previous generations, with 5G-Advanced seemingly around the corner [1]. Extensive research is already underway to structure the next generation of wireless systems(i.e. 6G), which may potentially enable an unprecedented level of human–machine interaction [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure Transmission of Compressed Medical Image Sequences on Communication Networks Using Motion Vector Watermarking

引用

computers, Materials & Continua 2024年第3期78卷 3283-3301页

作者： Rafi Ullah Mohd Hilmi bin Hasan Sultan Daud Khan Mussadiq Abdul Rahim Computer and Information Sciences Department Universiti Teknologi PETRONASBandar Seri Iskandar Perak32610Malaysia Department of Computer Science National University of TechnologyIslamabad46000Pakistan Interdisciplinary Research Center for Intelligent Secure Systems King Fahd University of Petroleum and MineralsDammam31261Saudi Arabia

Medical imaging plays a key role within modern hospital management systems for diagnostic *** methodologies are extensively employed to mitigate storage demands and enhance transmission speed,all while upholding image ***,an increasing number of hospitals are embracing cloud computing for patient data storage,necessitating meticulous scrutiny of server security and privacy ***,considering the widespread availability of multimedia tools,the preservation of digital data integrity surpasses the significance of compression *** response to this concern,we propose a secure storage and transmission solution for compressed medical image sequences,such as ultrasound images,utilizing a motion vector watermarking *** watermark is generated employing an error-correcting code known as Bose-Chaudhuri-Hocquenghem(BCH)and is subsequently embedded into the compressed sequence via block-based motion *** the process of watermark embedding,motion vectors are selected based on their magnitude and phase *** embedding watermarks,no specific spatial area,such as a region of interest(ROI),is used in the *** embedding of watermark bits is dependent on motion *** reversible watermarking allows the restoration of the original image sequences,we use the irreversible watermarking *** reason for this is that the use of reversible watermarks may impede the claims of ownership and legal *** restoration of original data or images may call into question ownership or other legal *** peak signal-to-noise ratio(PSNR)and structural similarity index(SSIM)serve as metrics for evaluating the watermarked image *** all images,the PSNR value exceeds 46 dB,and the SSIM value exceeds *** results substantiate the efficacy of the proposed technique in preserving data integrity.

关键词： Block matching algorithm(BMA) compression full-search algorithm motion vectors ultrasound image sequence watermarking

来源：评论

学校读者我要写书评

暂无评论

Segmented-Based and Segmented-Free Approach for COVID-19 Detection 5th

Segmented-Based and Segmented-Free Approach for COVID-19 D...

引用

5th International Conference on Computational Intelligence in Communications and Business Analytics, CICBA 2023

作者： Lasker, Asifuzzaman Ghosh, Mridul Das, Sahana Obaidullah, Sk Md Chakraborty, Chandan Goncalves, Teresa Roy, Kaushik Department of Computer Science and Engineering Aliah University Kolkata700160 India Department of Computer Science Shyampur Siddheswari Mahavidyalaya Howrah711312 India School of Computer Science Swami Vivekananda University Kolkata700121 India Department of Computer Science and Engineering National Institute of Technical Teachers’ Training and Research Kolkata700106 India Computer Science Department and ALGORITMI Center University of Évora Évora Portugal Department of Computer Science West Bengal State University Barasat700126 India

ISBN: (纸本)9783031488788

According to WHO, lung infection is one of the most serious problems across the world, especially for children under five years old and older people over sixteen years old. In this study, we designed a deep learning-based model to aid medical practitioners in their diagnostic process. Here, U-Net based segmentation framework is considered to get the region of interest (ROI) of the lung area from the chest x-ray images. Two standard deep learning models and a developed CNN model comprise this framework. A deep ensemble framework method is presented to detect COVID-19 disease from a collection of chest X-ray images of disparate cases in both segment-free and segmented-based lung images. Different public datasets were used for segmentation and classification to test the system’s robustness. The performance of segmentation and classification approaches returns promising outcomes compared to the state-of-the-art. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Leveraging user-item interactions and hotel characteristics for hotel recommendations in Indonesia with graph neural networks 9th

Leveraging user-item interactions and hotel characteristics ...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Panarto, Francis Alexander Phanghegar, Tyrone Matthew Gunardi, Vincent Cenggoro, Tjeng Wawan Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia

Travelers usually check information about the destination before they decide to go. However, sometimes the information is too much to handle and causes confusion. A filtering mechanism is needed to help them make their choices. The solution is to implement a recommendation system;some common techniques that are used for this are Collaborative Filtering and content-based filtering, but both techniques have their flaws. Therefore, we propose a solution to combine those two methods through Graph Neural Network architectures to help fix their flaws. The proposed method will be used for recommending hotels in Indonesia using the HotelRec dataset as the base dataset and hotel features acquired from the TripAdvisor API. We use several GNN architectures, such as GCN, LightGCN, GraphSAGE, and GAT, to implement our approach. Then, we compare it to several baseline models, such as SVD and NeuMF, which are common baselines in recommendation systems. The performance of these models is calculated based on three metrics: HitRate@K, NDCG@K, and Recall@K. Based on the result of this experiment, we found that incorporating hotel features into the learning process of the model, accompanied by user-item interactions, boosted the model's performance by at least 20% in all metrics, especially in datasets with a smaller number of interactions. © 2024 The Authors.

关键词： Collaborative filtering

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：