检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availability of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly available image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are available at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

FPGA Optimal Implementation of PRINCE against Power Analysis Attacks

FPGA Optimal Implementation of PRINCE against Power Analysis...

引用

ISCC 2017-the 5th International Conference on information Science and Cloud computing

作者： Yi Zou Lang Li College of Computer Science and Technology Hengyang Normal University Hunan Provincial Key Laboratory of Intelligent Information Processing and Application College of Computer Science and Technology Hengyang Normal University

The algorithm PRINCE proposed in ASIACRYPT 2012 is a lightweight cipher, currently suitable for the implementation on RFID Smart Card of the Io T. It's studied to achieve the optimal implementation of PRINCE encryption algorithm, and to add a fixed random mask to enhance the anti power attacking ability of PRINCE. In this paper, we constructed the same operations into a module called Prince Round, and used counter to control the Prince Round module, while the same round operation runs repeatedly. As a result, it can save registers and effectively reduce the amount of computation. Furthermore, we used a special method by adding the random mask to S-box. The experimental results show that the optimized PRINCE occupies area 9.8% fewer than original PRINCE on FPGA and the encryption with a fixed random mask can run correctly. Last but not least, our research is the first one about the implementation of PRINCE algorithm on FPGA, and can serve as a reference for further application of IOT encryption.

关键词： Matrix FPGA Optimal Implementation of PRINCE against Power Analysis Attacks

来源：评论

学校读者我要写书评

暂无评论

A Flexible Two-Stage Constrained Multi-Objective Evolutionary Algorithm Based on Autonomic Regulation

SSRN

引用

SSRN 2022年

作者： Zou, Juan Luo, Jian Liu, Yuan Yang, Shengxiang Zheng, Jinhua Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Computer science College of Xiangtan University Hunan Province Xiangtan China Faculty of Informational Engineering University of Xiangtan Xiangtan411105 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

The core element in solving constrained multi-objective problems (CMOPs) with evolutionary algorithms is simultaneously balancing objective optimization and constraint satisfaction. The di ffi culty of maintaining this balance increases significantly for existing algorithms when dealing with complex CMOPs because various complex feasible regions often make CMOPs with very di ff erent characteristics. To address this issue, we propose a more flexible two-stage evolutionary algorithm based on autonomic regulation (ARCMO), which can e ff ectively control evolutionary trends to adapt to complex CMOPs. Specifically, the first stage performs a fast global search and passes the population information to the second stage. The second stage consists of two dynamically complementary sub-processes: named exploration subprocess and convergence subprocess. The ratio of these two sub-processes is dynamically adjusted according to the information from the first stage to adapt to CMOPs with di ff erent complexities. Experiments on several recently proposed benchmark suites and real-world application problems show that ARCMO is more adaptable than the contender algorithms when solving di ff erent complex CMOPs. © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Large Generative Model-assisted Talking-face Semantic Communication System

arXiv

引用

arXiv 2024年

作者： Jiang, Feibo Tu, Siwei Dong, Li Pan, Cunhua Wang, Jiangzhou You, Xiaohu Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratoryof Artificial Intelligence Hunan University of Technology and Business Changsha China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The National Mobile Communications Research Laboratory Southeast University Nanjing China The Purple Mountain Laboratories Nanjing China

The rapid development of generative Artificial Intelligence (AI) continually unveils the potential of Semantic Communication (SemCom). However, current talking-face SemCom systems still encounter challenges such as low bandwidth utilization, semantic ambiguity, and diminished Quality of Experience (QoE). This study introduces a Large Generative Model-assisted Talking-face Semantic Communication (LGM-TSC) System tailored for the talking-face video communication. Firstly, we introduce a Generative Semantic Extractor (GSE) at the transmitter based on the FunASR model to convert semantically sparse talking-face videos into texts with high information density. Secondly, we establish a private Knowledge Base (KB) based on the Large language Model (LLM) for semantic disambiguation and correction, complemented by a joint knowledge base-semantic-channel coding scheme. Finally, at the receiver, we propose a Generative Semantic Reconstructor (GSR) that utilizes BERTVITS2 and SadTalker models to transform text back into a highQoE talking-face video matching the user’s timbre. Simulation results demonstrate the feasibility and effectiveness of the proposed LGM-TSC system. Copyright © 2024, The Authors. All rights reserved.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Systematic Resource Allocation in Cloud RAN with Caching as a Service under Two Timescales

Systematic Resource Allocation in Cloud RAN with Caching as ...

引用

作者： Tang, Jianhua Quek, Tony Q. S. Chang, Tsung-Hui Shim, Byonghyo Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Normal University Changsha410081 China Institute of New Media and Communications Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore487372 Singapore Department of Electronic Engineering Kyung Hee University Yongin17104 Korea Republic of School of Science and Engineering Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China Department of Electrical and Computer Engineering Institute of New Media and Communications Seoul National University Seoul08826 Korea Republic of

Recently, cloud radio access network (C-RAN) with caching as a service (CaaS) was proposed to merge the functionalities of communication, computing, and caching (CCC) together. In this paper, we dissect the interactions of CCC in C-RAN with CaaS from two dimensions: physical resource dimension and time dimension. In the physical resource dimension, we identify how to segment the baseband unit (BBU) pool resources (i.e., computation and storage) into different types of virtual machines (VMs). In the time dimension, we address how the long-term resource segmentation in the BBU pool impacts on the short-term transmit beamforming at the remote radio heads. We formulate the problem as a stochastic mixed-integer nonlinear programming (SMINLP) to minimize the system cost, including the server cost, VM cost and wireless transmission cost. After a series of approximation, including sample average approximation, successive convex approximation, and semidefinite relaxation, the SMINLP is approximated as a global consensus problem. The alternating direction method of multipliers (ADMM) is utilized to obtain the solution in a parallel fashion. Simulation results verify the convergence of our proposed algorithm, and also confirm that the proposed scheme is more cost-saving than that without considering the integration of CCC. © 1972-2012 IEEE.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

A dynamic multi-objective evolutionary algorithm based on Niche prediction strategy

引用

Applied Soft computing 2023年 142卷

作者： Zheng, Jinhua Zhang, Bo Zou, Juan Yang, Shengxiang Hu, Yaru Hunan Engineering Research Center of Intelligent System Optimization and Security Xiangtan University Hunan Province Xiangtan411105 China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education of China Xiangtan University Hunan Province Xiangtan411105 China Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University Hunan Province Xiangtan411105 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

In reality, many multi-objective optimization problems are dynamic. The Pareto optimal front (PF) or Pareto optimal solution (PS) of these dynamic multi-objective problems (DMOPs) changes as the environment change. Therefore, solving such problems requires an optimization algorithm that can quickly track the PF or PS after an environment change. Prediction-based response mechanism is a common method used to deal with environmental changes, which is commonly known as center point-based prediction. However, if the predicted direction of the center point is inaccurate, the predicted population will be biased towards one side. In this paper, we propose a niche prediction strategy based on center and boundary points (PCPB) to solve the dynamic multi-objective optimization problems, which consists of three steps. After environmental changes are detected, the first step is to divide the niche, dividing different individuals in the PS into different niche populations. The second step is to independently predict different niches, and select individuals with good convergence and distribution in the niche to predict the individuals that will produce the next generation. Finally, some different individuals are randomly generated in the next possible PS area to ensure the diversity of the population. To verify whether our proposed strategy is effective and competitive, PCPB was compared with five state-of-the-art strategies. The experimental results show that PCPB performed competitively in solving dynamic multi-objective optimization problems, which proves that our algorithm has good competitiveness. © 2023 Elsevier B.V.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Controlling Expressivity using Input Codes in Neural Network based TTS

Controlling Expressivity using Input Codes in Neural Network...

引用

Asian Conference on Affective computing and intelligent Interaction (ACII Asia)

作者： Xiaolian Zhu Lei Xie Xiao Chen Xiaoyan Lou Xuan Zhu Xingjun Tan Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University Xi’an Hebei University of Economics and Business Shijiazhuang China Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University Xi’an China Language Computing Lab Samsung R&D Institute of China Beijing China

ISBN: (纸本)9781538653128

This paper presents a study on the use of input codes in the neural network acoustic modeling for expressive TTS. Specifically, we use different kinds of input codes, augmented with the linguistic features, as the input of a BLSTM-based acoustic model, to control the expressivity of the synthesized speech. The input codes, in one-hot representation, include dialogue code, sentiment code and sentence position code. The dialogue code indicates whether the text is a dialogue or narration in an audiobook story. The sentiment code is obtained from a sentiment analysis tool, which labels each sentence as positive, negative and neutral. The sentence position code indicates the position of the sentence in the paragraph. We believe these codes are highly related to the expressiveness of the audiobook speech. Experiments on the data from the Blizzard Challenge 2017 demonstrate the effectiveness of the use of input codes in the neural network approach for expressive TTS.

关键词： Neural networks Linguistics Acoustics Hidden Markov models Speech synthesis Adaptation models Speech coding

来源：评论

学校读者我要写书评

暂无评论

Distributed resource scheduling for large-scale MEC systems: A multi-agent ensemble deep reinforcement learning with imitation acceleration

arXiv

引用

arXiv 2020年

作者： Jiang, Feibo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Key Laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of Commerce Changsha China Department of Computer and Information Sciences Northumbria University United Kingdom School of Computer Sciences and Electrical Engineering University of Essex ColchesterCO4 3SQ United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom

We consider the optimization of distributed resource scheduling to minimize the sum of task latency and energy consumption for all the Internet of things devices (IoTDs) in a large-scale mobile edge computing (MEC) system. To address this problem, we propose a distributed intelligent resource scheduling (DIRS) framework, which includes centralized training relying on the global information and distributed decision making by each agent deployed in each MEC server. More specifically, we first introduce a novel multi-agent ensemble-assisted distributed deep reinforcement learning (DRL) architecture, which can simplify the overall neural network structure of each agent by partitioning the state space and also improve the performance of a single agent by combining decisions of all the agents. Secondly, we apply action refinement to enhance the exploration ability of the proposed DIRS framework, where the near-optimal state-action pairs are obtained by a novel Lvy flight search. Finally, an imitation acceleration scheme is presented to pre-train all the agents, which can significantly accelerate the learning process of the proposed framework through learning the professional experience from a small amount of demonstration data. Extensive simulations are conducted to demonstrate that the proposed DIRS framework is efficient and outperforms the existing benchmark schemes. Copyright © 2020, 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

A Better Variant of self-attention for image caption

SSRN

引用

SSRN 2022年

作者： Chen, Haorong Shi, YueXiang Guo, Lijun Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiangtan University China School of Computer and Cyberspace Security Xiangtan University China Hunan Ordnance and Light Weapons Research Institute Co. Ltd China

The image description task aims to describe the content contained in the image using natural language. In the research field of computer vision and natural language processing, the image description task has attracted extensive attention from the academic community, especially after adding the attention mechanism, especially the self attention, which plays an increasingly important role in vision and natural language processing, Self attention updates the features of each location by calculating the weighted sum of features using the paired affinity of all locations. However, this ignores the potential correlation between different samples. In this paper, a new attention mechanism is proposed. Query and key are traditional inputs, while its Value is an external, small, and learnable shared memory, which can be realized by using the linkage layer and the normalization layer;It conveniently replaces the self attention in the existing popular architecture. External concerns have linear complexity and implicitly consider the correlation between all data samples. In this paper, we add our method to image capture to improve the accuracy of the image description model based on attention fusion. The model was evaluated on MSCOCO and Flickr30k datasets. The Cider score of MSCOCO datasets reached 130.7, which was superior to similar image description generation models. © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

UWB SAR image segmentation algorithm based on polynomial analysis of statistical distribution

UWB SAR image segmentation algorithm based on polynomial ana...

引用

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Wang Yuming Jin Tian Luo Chaopeng College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computhing and Language Information Processing Science and Technology on Near-Surface Detection Laboratory Hunan Normal University Changsha R.P.China College of Electronic Science and Technology Science and Technology on Near-Surface Detection Laboratory National University of Defense Technology Changsha R.P.China Science and Technology on Near-Surface Detection Laboratory Wuxi China

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

Aimed at the segmentation problem of ultrawideband synthetic aperture radar (UWB SAR) image, a novel algorithm based on polynomial analysis of statistical distribution is proposed in this letter. Firstly, we estimate the probability density function (PDF) for each pixel via sparse decomposition of which the dictionary consists of orthogonal polynomials (OP). Secondly, the weighting coefficients of corresponding OP are used to segment image using their maximum value. The experimental results validate the efficiency of this algorithm.

关键词： Image segmentation Probability density function Synthetic aperture radar Radar polarimetry Signal processing algorithms Scattering Statistical distributions

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

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

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：