检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Zhong, Yan Wu, Xingyu Zhang, Li Yang, Chenxi Jiang, Tingting School of Mathematical Sciences Peking University Beijing China National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China Department of Computing The Hong Kong Polytechnic University Hong Kong Hefei Institute of Physical Science Chinese Academy of Sciences University of Science and Technology of China Hefei China National Biomedical Imaging Center Peking University Beijing China

Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA *** address this, this paper proposes a novel end-to-end blind IQA method: ***, we first analyze the causal mechanisms in IQA tasks and construct a causal graph to understand the interplay and confounding effects between distortion types, image contents, and subjective human ***, through shifting the focus from correlations to causality, Causal-IQA aims to improve the estimation accuracy of image quality scores by mitigating the confounding effects using a causality-based optimization *** optimization strategy is implemented on the sample subsets constructed by a Counterfactual Division process based on the Backdoor *** experiments illustrate the superiority of Causal-IQA. Copyright 2024 by the author(s)

关键词： Image correlation

来源：评论

学校读者我要写书评

暂无评论

SCBench: A Sports Commentary Benchmark for Video LLMs

arXiv

引用

arXiv 2024年

作者： Ge, Kuangzhi Chen, Lingjun Zhang, Kevin Luo, Yulin Shi, Tianyu Fan, Liaoyuan Li, Xiang Wang, Guanqun Zhang, Shanghang State Key Laboratory of Multimedia Information Processing School of Computer Science Peking University China Department of Computer Science University of Toronto Canada The University of Hong Kong Hong Kong Southern University of Science and Technology China

Recently, significant advances have been made in Video Large Language Models (Video LLMs) in both academia and industry. However, methods to evaluate and benchmark the performance of different Video LLMs, especially their fine-grained, temporal visual capabilities, remain very limited. On one hand, current benchmarks use relatively simple videos (e.g., subtitled movie clips) where the model can understand the entire video by processing just a few frames. On the other hand, their datasets lack diversity in task format, comprising only QA or multi-choice QA, which overlooks the models' capacity for generating in-depth and precise texts. Sports videos, which feature intricate visual information, sequential events, and emotionally charged commentary, present a critical challenge for Video LLMs, making sports commentary an ideal benchmarking task. Inspired by these challenges, we propose a novel task: sports video commentary generation, developed SCBench for Video LLMs. To construct such a benchmark, we introduce (1) SCORES, a six-dimensional metric specifically designed for our task, upon which we propose a GPT-based evaluation method, and (2) CommentarySet, a dataset consisting of 5,775 annotated video clips and ground-truth labels tailored to our metric. Based on SCBench, we conduct comprehensive evaluations on multiple Video LLMs (e.g. VILA, Video-LLaVA, etc.) and chain-of-thought baseline methods. Our results found that InternVL-Chat-2 achieves the best performance with 5.44, surpassing the second-best by 1.04. Our work provides a fresh perspective for future research, aiming to enhance models' overall capabilities in complex visual understanding tasks. Our dataset will be released soon. © 2024, CC BY-NC-ND.

关键词： Footage counters

来源：评论

学校读者我要写书评

暂无评论

Spatial and Contextual Path Network for Image Inpainting

引用

Intelligent Automation & Soft Computing 2024年第2期39卷 115-133页

作者： Dengyong Zhang Yuting Zhao Feng Li Arun Kumar Sangaiah Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China International Graduate Institute of AI National Yunlin University of Science and TechnologyYunlinTaiwan Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon

Image inpainting is a kind of use known area of information technology to repair the loss or damage to the *** feature extraction is the core of image *** enough space for information and a larger receptive field is very important to realize high-precision image ***,in the process of feature extraction,it is difficult to meet the two requirements of obtaining sufficient spatial information and large receptive fields at the same *** order to obtain more spatial information and a larger receptive field at the same time,we put forward a kind of image restoration based on space path and context path *** the space path,we stack three convolution layers for 1/8 of the figure,the figure retained the rich spatial *** the context path,we use the global average pooling layer,where the accept field is the maximum of the backbone network,and the pooling module can provide global context information for the maximum accept *** order to better integrate the features extracted from the spatial and contextual paths,we study the fusion module of the two *** fusionmodule first path output of the space and context path,and then through themass normalization to balance the scale of the characteristics,finally the characteristics of the pool will be connected into a feature vector and calculate the weight *** of images in order to extract context information,we add attention to the context path refinement *** modules respectively from channel dimension and space dimension to weighted images,in order to obtain more effective *** show that our method is better than the existing technology in the quality and quantity of themethod,and further to expand our network to other inpainting networks,in order to achieve consistent performance improvements.

关键词： Image inpainting attention deep learning convolutional network

来源：评论

学校读者我要写书评

暂无评论

A Study of the Haar Spectra of Ternary Bent Functions

A Study of the Haar Spectra of Ternary Bent Functions

引用

International Symposium on Multiple-Valued Logic

作者： Radomir S. Stanković Milena Stanković Claudio Moraga Jaakko T. Astola Mathematical Institute of SASA Belgrade Serbia Department of Computer Science Faculty of Electronic Engineering Niš Serbia Faculty of Computer Science Technical University of Dortmund Dortmund Germany Department of Signal Processing Tampere University of Technology Tampere Finland

ISBN: (数字)9798350343083

ISBN: (纸本)9798350343090

Ternary bent functions are defined in the spectral domain as ternary functions having flat Vilenkin-Chrestenson spectra. This is a global transform in the sense that all function values are involved in computing every spectral coefficient. The paper presents an analysis of characteristics of the spectra of ternary bent functions with respect to the ternary Haar transform, which is a multiresolution and local transform in the above sense. Due to this, it provides a further insight in the structure of ternary bent functions, their characteristics, and mutual relationships.

关键词： Transforms Logic Spectral analysis

来源：评论

学校读者我要写书评

暂无评论

Optimized efficient attention-based network for facial expressions analysis in neurological health care

引用

computers in Biology and Medicine 2024年 179卷 108822-108822页

作者： Munsif, Muhammad Sajjad, Muhammad Ullah, Mohib Tarekegn, Adane Nega Cheikh, Faouzi Alaya Tsakanikas, Panagiotis Muhammad, Khan Sejong University Seoul143-747 Korea Republic of Digital Image Processing Lab Department of Computer Science Islamia College Peshawar25000 Pakistan Department of Computer Science Norwegian University for Science and Technology Gjøvik2815 Norway Department of Computer Science Norwegian University for Science and Technology Gjøvik2815 Norway Institute of Communication and Computer Systems National Technical University of Athens Athens15773 Greece Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul03063 Korea Republic of

Facial Expression Analysis (FEA) plays a vital role in diagnosing and treating early-stage neurological disorders (NDs) like Alzheimer's and Parkinson's. Manual FEA is hindered by expertise, time, and training requirements, while automatic methods confront difficulties with real patient data unavailability, high computations, and irrelevant feature extraction. To address these challenges, this paper proposes a novel approach: an efficient, lightweight convolutional block attention module (CBAM) based deep learning network (DLN) to aid doctors in diagnosing ND patients. The method comprises two stages: data collection of real ND patients, and pre-processing, involving face detection and an attention-enhanced DLN for feature extraction and refinement. Extensive experiments with validation on real patient data showcase compelling performance, achieving an accuracy of up to 73.2%. Despite its efficacy, the proposed model is lightweight, occupying only 3MB, making it suitable for deployment on resource-constrained mobile healthcare devices. Moreover, the method exhibits significant advancements over existing FEA approaches, holding tremendous promise in effectively diagnosing and treating ND patients. By accurately recognizing emotions and extracting relevant features, this approach empowers medical professionals in early ND detection and management, overcoming the challenges of manual analysis and heavy models. In conclusion, this research presents a significant leap in FEA, promising to enhance ND diagnosis and *** code and data used in this work are available at: https://***/munsif200/Neurological-Health-Care. © 2024 Elsevier Ltd

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

来源：评论

学校读者我要写书评

暂无评论

Increasing Degree of Ternary Bent Functions

Increasing Degree of Ternary Bent Functions

引用

International Symposium on Multiple-Valued Logic

作者： Milena Stanković Radomir S. Stanković Claudio Moraga Jaakko T. Astola Department of Computer Science Faculty of Electronic Engineering Niš Serbia Mathematical Institute of SASA Belgrade Serbia Faculty of Computer Science Technical University of Dortmund Dortmund Germany Department of Signal Processing Tampere University of Technology Tampere Finland

ISBN: (数字)9798350343083

ISBN: (纸本)9798350343090

Binary bent functions are often used as a basis for deriving cryptographically interesting sequences. For instance, such sequences are used to secure safe communication among unsafe channels. Ternary bent functions are a mathematically interesting object defined as a direct extension of the concept by referring to definition of binary bent functions in terms of Walsh spectral coefficients. The degree of ternary bent functions is defined as the largest sum of powers of variables in a term in their Generalized Positive-polarity Reed-Muller expressions for ternary functions. In cryptography, the corresponding expression for the binary case is also called the Algebraic Normal Form (ANF). It is supposed that bent functions with larger degrees are more suitable for practical applications. We present a way to increase the degree of ternary bent functions by using a particular class of FFT-like permutation matrices implementing certain well suited substitutions of variables.

关键词： Transforms Matrices Cryptography Logic

来源：评论

学校读者我要写书评

暂无评论

Multi-party secure communication using blockchain over 5G

Multi-party secure communication using blockchain over 5G

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Archana, K. Kareem, Z.H. Al-Farhani, Liwa H. Bagyalakshmi, K. Jenvi, Ignatia K. Majella Kumar, Ashok Department of Computer Engineering Pimpri Chinchwad College of Engineering and Research Maharashtra Pune India Medical Instrumentation Techniques Engineering Department Al-Mustaqbal University College Babylon Iraq System Analysis Control and Information Processing dep Academy of Engineering RUDN University Moscow Russia Sri Ranganathar Institute of Engineering and Technology Coimbatore India Mathematics Department Saveetha School of Engineering SIMATS Saveetha Nagar Chennai India Department of Computer Science Banasthali Vidyapith Rajasthan Banasthali India

ISBN: (纸本)9781032669663

One of the most critical problems facing the blockchain technology industry right now is how to protect the privacy of users’ data on the blockchain in a way that is both effective and cheap. Based on the Pedersen commitment and the Schnorr protocol, this study comes up with a secure multi-party computing protocol (BPLSM). By making the structure of the protocol and doing formal proof calculations, it has been shown that the protocol can be used in the blockchain network to combine private messages for efficient signing while keeping people’s identities secret. Furthermore, by looking at the nature and security of the protocol, it is also possible to find that the BPLSM protocol on the blockchain has a low cost of computing and a high level of information secrecy. Furthermore, it was found that the BPLSM protocol takes less time to check than the current mainstream BLS signature in a simple multi-party transaction with a fixed number of participants. © 2024 The Author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Framework for Stock Market Operations: IPOs, Trading, and Dividend Distribution

Blockchain-Based Framework for Stock Market Operations: IPOs...

引用

IEEE International Conference on Cloud Computing technology and science (CloudCom)

作者： Muhammad Sharshar Kareem Elzeky Menna Othman SeifAldin Khaled Hosam Moubarak Walid Gomaa Department of Computer Science Center for Secure Cyber-Physical Systems (C2PS) Khalifa University UAE Department of Natural Language Processing MBZUAI UAE Department of Computer Engineering Cyber-Physical Lab Egypt-Japan University of Science and Technology Egypt Accounting Department Egypt-Japan University of Science and Technology Egypt

ISBN: (数字)9798331507589

ISBN: (纸本)9798331507596

This study examines blockchain technology's potential to enhance the stock market by offering a decentralized alternative to the traditional system. The study explores the challenges of the current traditional stock market, such as long settlement times, weak transparency, dependency on centralized clearing houses, and heightened fees. The proposed novel system leverages blockchain technology to create a fully decentralized stock market encompassing all fundamental operations from Initial Public Offerings (IPOs) to stock trading and extending to distributing profits or dividends. It connects all market participants through an Ethereum consortium blockchain fuelled by smart contracts. This approach replaces traditional intermediaries like brokers with automated regulations, ensuring more rapid transaction settlements, reduced operational errors and fees, and strengthened security measures. The proposed blockchain-based system, consisting of four smart contracts for IPO, stock exchange, dividend distribution, and participant management, demonstrates remarkable performance, showing promise in efficiently handling the current load of the largest stock markets like the London Stock Exchange (LSE). Through theoretical and practical testing, the system achieved a remarkable throughput of 120 transactions per second and latency or finality of just 4 seconds, underscoring its capability to significantly enhance the efficiency of stock market operations. 1 1 The implementation code is available via GitHub upon request.

关键词： Cloud computing Smart contracts Transforms Throughput Regulation Blockchains Security Stock markets Testing Software development management

来源：评论

学校读者我要写书评

暂无评论

Anime Sketch Colourization Using Enhanced Pix2pix GAN 1

引用

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Mudhalwadkar, Nikhil Prashant Mokayed, Hamam Alkhaled, Lama Shivakumara, Palaiahnakote Hum, Yan Chai Lulea Tekniska Universitet Lulea Sweden Centre of Image and Signal Processing Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia Department of Mechatronics and Biomedical Engineering Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Petaling Jaya Malaysia

ISBN: (数字)9783031476341

ISBN: (纸本)9783031476334

Coloring manga sketches is challenging due to the wide gap between the meaning of color and sketches. Unlike Western comics, Japanese manga sketch does not provide color, rather they are in binary form using a screening technique. These styles differ in how regions are filled, but converting between them is a difficult task that is typically done manually. This paper aims to develop a method for coloring Japanese manga composed of sketches and dialogue. Coloring is considered a challenging and time-consuming task for creators. The proposed method proposes using a pix2pix GAN (Generative Adversarial Network) to color a manga sketch when given as input. Additionally, an alternative approach is suggested, which involves modifying the generator loss function to improve the performance. This paper aims to automate the process of coloring a single sketch, with the potential to extend the research in the future to apply the colors consistently across multiple manga strips. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Generative adversarial networks

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：