检索结果-内蒙古大学图书馆

Exocentric to Egocentric Image Generation Via Parallel Generative Adversarial Network

学校读者我要写书评

暂无评论

Exocentric to Egocentric Image Generation Via Parallel Gener...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Gaowen Liu Hao Tang Hugo Latapie Yan Yan Department of Computer Science Texas State University USA Chief Technology & Architecture Office Cisco USA

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Cross-view image generation has been recently proposed to generate images of one view from another dramatically different view. In this paper, we investigate exocentric (third-person) view to egocentric (first-person) view image generation. This is a challenging task since egocentric view sometimes is remarkably different from exocentric view. Thus, transforming the appearances across the two views is a nontrivial task. To this end, we propose a novel Parallel Generative Adversarial Network (P-GAN) with a novel cross-cycle loss to learn the shared information for generating egocentric images from exocentric view. We also incorporate a novel contextual feature loss in the learning procedure to capture the contextual information in images. Extensive experiments on the Exo-Ego datasets [1] show that our model outperforms the state-of-the-art approaches.

关键词：

Gamma-Ray Burst Light Curve Reconstruction: A Comparative Machine and Deep Learning Analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kaushal, A. Manchanda, A. Dainotti, M.G. Deepu, A. Naqi, S. Felix, J. Indoriya, N. Magesh, S.P. Gupta, H. Gupta, K. Madhan, A. Hartmann, D.H. Pollo, A. Bogdan, M. Prochaska, J.X. Fraija, N. Debnath, D. Department of Computer Science and Engineering UIET-H Panjab University Punjab 146001 India Department of Physics Indian Institute of Technology Telangana Hyderabad502284 India National Astronomical Observatory of Japan 2 Chome-21-1 Osawa Mitaka Tokyo181-8588 Japan Department of Astronomical Sciences The Graduate University for Advanced Studies SOKENDAI Shonankokusaimura Miura District Kanagawa Hayama240-0115 Japan Nevada Center for Astrophysics University of Nevada 4505 Maryland Parkway Las VegasNV89154 United States Space Science Institute 4765 Walnut Street Suite B BoulderCO80301 United States Department of Ocean Engineering and Naval Architecture Indian Institute of Technology West Bengal Kharagpur721302 India KNIT Uttar Pradesh Sultanpur228118 India Indian Institute of Technology Kharagpur721302 India Department of Electrical Engineering and Computer Science IISER Madhya Pradesh Bhopal462066 India Indian Institute of Technology Madras600036 India MIT WPU School of Computer Science & Engineering Pune411038 India Department of Computer Science PSIT College Uttar Pradesh Kanpur209305 India Visveswaraya Technological University Karnataka Belagavi590018 India Department of Physics and Astronomy Clemson University ClemsonSC29634 United States Astronomical Observatory of Jagiellonian University in Kraków Orla 171 Kraków30-244 Poland National Centre for Nuclear Research Warsaw02-093 Poland Department of Mathematics University of Wroclaw Wroclaw50-384 Poland University of California Santa Cruz 1156 High Street Santa CruzCA95064 United States National Autonoma University of Mexico Circuito Interior Mexico City04510 Mexico NIT Tripura Agartala799046 India

Gamma-Ray Bursts (GRBs), observed at large redshifts, are probes of the evolution of the Universe and can be used as cosmological tools. To this end, we need tight (with small dispersion) correlations among key parameters. To reduce such a dispersion, we will mitigate gaps in light curves (LCs), including the plateau region, key to building the two-dimensional Dainotti relation between the end time of plateau emission (Ta) to its luminosity (La). We reconstruct LCs using nine models: Multi-Layer Perceptron (MLP), Bi-Mamba, Fourier Transform, Gaussian Process–Random Forest Hybrid (GP-RF), Bidirectional Long Short-Term Memory (Bi-LSTM), Conditional GAN (CGAN), SARIMAX-based Kalman filter, Kolmogorov–Arnold Networks (KANs), and Attention U-Net. These methods are compared to the Willingale model (W07) over a sample of 545 GRBs. MLP and Bi-Mamba outperform other methods, with MLP reducing the plateau parameter uncertainties by 25.9% for log Ta, 28.6% for log Fa, and 37.7% for α (the post-plateau slope in the W07 model), achieving the lowest 5-fold cross validation (CV) mean squared error (MSE) of 0.0275. Bi-Mamba achieved the lowest uncertainty of parameters, a 33.3% reduction in log Ta and log Fa and a 41.9% in α, but with a higher MSE of 0.130. Bi-Mamba brings the lowest outlier percentage for log Ta and log Fa (2.70%), while MLP carry α outliers to 0.900%. The other methods yield MSE values ranging from 0.0339 to 0.174. These improvements in parameter precision are needed to use GRBs as standard candles, investigate theoretical models, and predict GRB redshifts through machine learning. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset

学校读者我要写书评

暂无评论

Egok360: A 360 Egocentric Kinetic Human Activity Video Datas...

IEEE International Conference on Image Processing

作者： Keshav Bhandari Mario A. DeLaGarza Ziliang Zong Hugo Latapie Yan Yan Department of Computer Science Texas State University USA Chief Technology & Architecture Office Cisco USA

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Recently, there has been a growing interest in wearable sensors which provides new research perspectives for 360 ° video analysis. However, the lack of 360 ° datasets in literature hinders the research in this field. To bridge this gap, in this paper we propose a novel Egocentric (first-person) 360° Kinetic human activity video dataset (EgoK360). The EgoK360 dataset contains annotations of human activity with different sub-actions, e.g., activity Ping-Pong with four sub-actions which are pickup-ball, hit, bounce-ball and serve. To the best of our knowledge, EgoK360 is the first dataset in the domain of first-person activity recognition with a 360° environmental setup, which will facilitate the egocentric 360 ° video understanding. We provide experimental results and comprehensive analysis of variants of the two-stream network for 360 egocentric activity recognition. The EgoK360 dataset can be downloaded from https://***/.

关键词： Convolution Activity recognition Cameras Three-dimensional displays Kinetic theory Optical distortion Distortion

Tuning Electrocatalytic Properties of Bismuthene by Heteroatom Decoration Toward Overall Water Splitting

学校读者我要写书评

暂无评论

ChemistrySelect 2025年第21期10卷

作者： Yue-Han Ji Jun-Miao Zhang Xiang-Yu Leng Liang-Ze Zhu Bei-Bei Xiao School of Energy and Power Engineering Jiangsu University of Science and Technology Zhenjiang Jiangsu 212003 China Jangho Architecture College Northeastern University Shenyang Liaoning Province 110167 China Department of Computer and Science Technology LyuLiang University LyuLiang Shanxi 033000 China

Developing of effective electrocatalysts for overall water splitting is of importance for the achievement of hydrogen energy cycling. In this work, hydrogen evolution and oxygen evolution of the defective bismuthene with decoration of a transition metal atom have been fully investigated via density functional theory calculations. The results indicate that the fixation of transition metal dopant into defective bismuthene is achieved via the interaction between the Bi sp band and TM sd band. Wherein, Sc@Bi, Ti@Bi, Zn@Bi, Y@Bi, Rh@Bi, Pd@Bi, Ag@Bi, Pt@Bi, and Au@Bi are thermodynamically stable according to the data of the formation energy. Furthermore, Sc@Bi, Ti@Bi, Y@Bi, Rh@Bi, Pd@Bi, and Pt@Bi have good performances toward hydrogen evolution, and the overpotentials η HER are 0.11, 0.22, 0.30, 0.13, 0.27, and 0.01 V, respectively. Furthermore, the optimal candidates toward oxygen evolution are Rh@Bi and Pt@Bi, endowed with the overpotentials η OER of 0.66 and 0.36 V, respectively. Therefore, Pt@Bi and Rh@Bi are bifunctional-active toward overall water splitting. These findings indicate that bismuthene could provide a new platform to explore high-efficiency electrocatalysts in overall water splitting.

关键词： Bismuthene Density functional theory Electrocatalysis Water splitting

Constrained Optimization with Decision-Dependent Distributions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Zifan Liu, Changxin Parisini, Thomas Zavlanos, Michael M. Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden The Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom The Department of Engineering and Architecture University of Trieste Trieste34127 Italy The KIOS Research and Innovation Center of Excellence University of Cyprus NicosiaCY-1678 Cyprus The Department of Mechanical Engineering and Materials Science Duke University DurhamNC United States

In this paper we deal with stochastic optimization problems where the data distributions change in response to the decision variables. Traditionally, the study of optimization problems with decision-dependent distributions has assumed either the absence of constraints or fixed constraints. This work considers a more general setting where the constraints can also dynamically adjust in response to changes in the decision variables. Specifically, we consider linear constraints and analyze the effect of decision-dependent distributions in both the objective function and constraints. Firstly, we establish a sufficient condition for the existence of a constrained equilibrium point, at which the distributions remain invariant under retraining. Morevoer, we propose and analyze two algorithms: repeated constrained optimization and repeated dual ascent. For each algorithm, we provide sufficient conditions for convergence to the constrained equilibrium point. Furthermore, we explore the relationship between the equilibrium point and the optimal point for the constrained decision-dependent optimization problem. Notably, our results encompass previous findings as special cases when the constraints remain fixed. To show the effectiveness of our theoretical analysis, we provide numerical experiments on both a market problem and a dynamic pricing problem for parking based on real-world data. Copyright © 2023, The Authors. All rights reserved.

关键词： Constrained optimization

Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ignatov, Andrey Timofte, Radu Chiang, Cheng-Ming Kuo, Hsien-Kai Xu, Yu-Syuan Lee, Man-Yu Lu, Allen Cheng, Chia-Ming Chen, Chih-Cheng Yong, Jia-Ying Shuai, Hong-Han Cheng, Wen-Huang Jia, Zhuang Xu, Tianyu Zhang, Yijian Bao, Long Sun, Heng Zhang, Diankai Gao, Si Liu, Shaoli Wu, Biao Zhang, Xiaofeng Zheng, Chengjian Lu, Kaidi Wang, Ning Sun, Xiao Wu, HaoDong Liu, Xuncheng Zhang, Weizhan Yan, Caixia Du, Haipeng Zheng, Qinghua Wang, Qi Chen, Wangdu Duan, Ran Duan, Ran Sun, Mengdi Zhu, Dan Chen, Guannan Cho, Hojin Kim, Steve Yue, Shijie Li, Chenghua Zhuge, Zhengyang Chen, Wei Wang, Wenxu Zhou, Yufeng Cai, Xiaochen Cai, Hengxing Xu, Kele Liu, Li Cheng, Zehua Lian, Wenyi Lian, Wenjing Computer Vision Lab ETH Zurich Switzerland AI Witchlabs Switzerland University of Wuerzburg Germany MediaTek Inc. Taiwan National Yang Ming Chiao Tung University Taiwan Video Algorithm Group Camera Department Xiaomi Inc. China Audio & Video Technology Platform Department ZTE Corp. China China School of Computer Science and Technology Xi'an Jiaotong University China MIGU Video Co. Ltd China BOE Technology Group Co. Ltd. China GenGenAI Korea Republic of North China University of Technology China Institute of Automation Chinese Academy of Sciences China State Key Laboratory of Computer Architecture Institute of Computing Technology China 4Paradigm Inc. Beijing China National University of Defense Technology Changsha China University of Oxford Oxford United Kingdom Uppsala University Sweden Northeastern University China

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of lowbitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt/30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper. Copyright © 2022, The Authors. All rights reserved.

关键词： Energy utilization

Identifying users with wearable sensors based on activity patterns 11

学校读者我要写书评

暂无评论

Identifying users with wearable sensors based on activity pa...

11th International Conference on Emerging Ubiquitous Systems and Pervasive Networks, EUSPN 2020

作者： Ehatisham-Ul-Haq, Muhammad Malik, Maryam Naseer Azam, Muhammad Awais Naeem, Usman Khalid, Asra Ghazanfar, Mustansar Ali Department of Computer Engineering University of Engineering and Technology Taxila Punjab47050 Pakistan Whitecliffe Technologies Wellington New Zealand School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom School of Engineering and Computer Science Victoria University of Wellington New Zealand School of Architecture Computing and Engineering University of East London United Kingdom

We live in a world where ubiquitous systems surround us in the form of automated homes, smart appliances and wearable devices. These ubiquitous systems not only enhance productivity but can also provide assistance given a variety of different scenarios. However, these systems are vulnerable to the risk of unauthorized access, hence the ability to authenticate the end-user seamlessly and securely is important. This paper presents an approach for user identification given the physical activity patterns captured using on-body wearable sensors, such as accelerometer, gyroscope, and magnetometer. Three machine learning classifiers have been used to discover the activity patterns of users given the data captured from wearable sensors. The recognition results prove that the proposed scheme can effectively recognize a user's identity based on his/her daily living physical activity patterns. © 2020 The Authors. Published by Elsevier B.V.

关键词： Wearable sensors

Cerebral micro-bleeding identification based on a nine-layer convolutional neural network with stochastic pooling

学校读者我要写书评

暂无评论

Cerebral micro-bleeding identification based on a nine-layer...

作者： Wang, Shuihua Sun, Junding Mehmood, Irfan Pan, Chichun Chen, Yi Zhang, Yu-Dong School of Computer Science and Technology Henan Polytechnic University Jiaozuo China School of Architecture Building and Civil Engineering Loughborough University Loughborough United Kingdom Department of Informatics University of Leicester Leicester United Kingdom Department of Computer Science and Engineering College of Electronics and Information Engineering Sejong University Seoul Korea Republic of School of Computer Science and Technology Nanjing Normal University Nanjing China School of Business Nanjing Normal University Nanjing China Jiangsu Laboratory of Lake Environment Remote Sensing Technologies Huaiyin Institute of Technology Huaian China

Cerebral micro-bleedings are small chronic brain hemorrhages caused by structural abnormalities of the small vessels. CMBs can be found from individuals with stroke at memory clinics and even healthy elderly people. CMBs indicate hemorrhage-prone pathological states. Research shows that CMBs are associated with an increased risk of future ischemic stroke, intra-cerebral hemorrhage (ICH), dementia, and death. Considering that CMBs severely influence people's life, it is necessary to identify the CMBs in an early stage to prevent from further deterioration and to help people live a healthy life. In this paper, we proposed using CNN with stochastic pooling for the CMB detection. CNN has good performance in image and video recognition, recommender system, and nature language processing. Based on the collected subject, the experiment result shows that the six-convolution layer and three fully-connected layer CNN, nine-layers in total, achieved sensitivity, specificity, accuracy, and precision as 97.22%, and 97.35%, 97.28%, and 97.35% in average of ten runs, which shows better performance than five state-of-the-art methods. © 2019 John Wiley & Sons, Ltd.

关键词： Convolution

Solving the multiplication problem of a large language model system using a graph-based method

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tuncer, Turker Dogan, Sengul Baygin, Mehmet Barua, Prabal Datta Hafeez-Baig, Abdul Tan, Ru-San Chakraborty, Subrata Acharya, U. Rajendra Department of Digital Forensics Engineering Technology Faculty Firat University Elazig Turkey Department of Computer Engineering Faculty of Engineering and Architecture Erzurum Technical University Erzurum Turkey University of Southern Queensland Australia School of Management and Enterprise University of Southern Queensland ToowoombaQLD Australia Department of Cardiology National Heart Centre Singapore Singapore169609 Singapore Duke-NUS Medical School Singapore169857 Singapore School of Science and Technology Faculty of Science Agriculture Business and Law University of New England ArmidaleNSW2351 Australia Center for Advanced Modelling and Geospatial Information Systems Faculty of Engineering and IT University of Technology Sydney SydneyNSW2007 Australia School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia

The generative pre-trained transformer (GPT)-based chatbot software ChatGPT possesses excellent natural language processing capabilities but is inadequate for solving arithmetic problems, especially multiplication. Its GPT structure uses a computational graph for multiplication, which has limited accuracy beyond simple multiplication operations. We developed a graph-based multiplication algorithm that emulated human-like numerical operations by incorporating a ×10k operator, where k represents the maximum power to base 10 of the larger of two input numbers. Our proposed algorithm attained 100% accuracy for 1,000,000 large number multiplication tasks, effectively solving the multiplication challenge of GPT-based and other large language models. Our work highlights the importance of blending simple human insights into the design of artificial intelligence algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Blending