2022 IEEE International Conference on Consumer Electronics (ICCE)最新文献_第2页

Deep High Dynamic Range Imaging without Motion Artifacts Using Global and Local Skip Connections 使用全局和局部跳过连接的无运动伪影的深度高动态范围成像

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730322

Jaehee Lee, Joongchol Shin, Heunseung Lim, J. Paik

引用次数: 1

Visual and Location Information Fusion for Hierarchical Place Recognition 视觉与位置信息融合的分层位置识别

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730537

Dulmini Hettiarachchi, S. Kamijo

引用次数: 1

An Emotion-Aware Persuasive Architecture to Support Challenging Classroom Situations 一个具有情感意识的有说服力的架构来支持具有挑战性的课堂环境

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730567

Edgar Sarmiento-Calisaya, P. Calcina-Ccori, Álvaro E. Cuno Parari

{"title":"An Emotion-Aware Persuasive Architecture to Support Challenging Classroom Situations","authors":"Edgar Sarmiento-Calisaya, P. Calcina-Ccori, Álvaro E. Cuno Parari","doi":"10.1109/ICCE53296.2022.9730567","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730567","url":null,"abstract":"Nowadays, students face stressful situations that affect their mental health and negatively impact their academic performance. This situation has been exacerbated due to the COVID-19 pandemics. Teaching and learning process stakeholders face two main problems: the lack of awareness of the situations arising from students and the little available information that support the teaching activities. Here, we propose an emotion-aware architecture for persuasive systems in education, identifying challenging classroom situations and promoting mental health through multi-modal persuasive notifications. An important module is emotion inference, which reads real-time physiological data from students through the Empatica E4 wristband. Based on this architecture, we developed the Kusisqa persuasive system, to support students in regulating their negative emotions (They can all lead to stress) during challenging classroom situations. Preliminary results provide insights that teachers achieved an increased awareness of the situations of students and perceived the prototype tool as useful.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127885970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Multi-Exposure Image Fusion Using Cross-Attention Mechanism 基于交叉注意机制的多曝光图像融合

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730511

Byungnam Kim, Hyungjoo Jung, K. Sohn

{"title":"Multi-Exposure Image Fusion Using Cross-Attention Mechanism","authors":"Byungnam Kim, Hyungjoo Jung, K. Sohn","doi":"10.1109/ICCE53296.2022.9730511","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730511","url":null,"abstract":"Multi-exposure fusion (MEF) is a popular method for obtaining high dynamic range (HDR) image from multiple low dynamic range (LDR) images. Even though recent works have employed the convolutional neural networks (CNNs) for solving the MEF problem, there still remain various challenges, such as color distortion and detail loss, due to a limited receptive field. In this paper, we present a cross-attention module for multi-exposure image fusion. Different from existing CNN-based methods that capture the contexts of the local region in the target image, our method adaptively aggregates local features with global dependencies at all positions. Furthermore, we propose a detail compensation module as the feature fusion for restoring the loss (color and detail) in the saturation region. Our proposed network performs a feature extraction with an encoder, a fusion of a cross-attention module and a detail compensation module, and the fused image is reconstructed by a decoder. Experimental results show that compared with the state-of-the-art methods, the proposed method can obtain better performance in both the subjective and objective evaluation, particularly in terms of color expression and detail-preserving.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125660920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

User-Defined Keyword Spotting Utilizing Speech Synthesis for Low-Resource Wearable Devices 基于语音合成的低资源可穿戴设备自定义关键字识别

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730771

Jaebong Lim, Yunju Baek

引用次数: 0

Household Behavior Observation System Utilizing Mesh Sensor Network Consisting of Smart Taps 基于智能水龙头组成的网状传感器网络的家庭行为观察系统

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730301

Ryuichi Inoue, Hiroshi Yamamoto

{"title":"Household Behavior Observation System Utilizing Mesh Sensor Network Consisting of Smart Taps","authors":"Ryuichi Inoue, Hiroshi Yamamoto","doi":"10.1109/ICCE53296.2022.9730301","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730301","url":null,"abstract":"In recent years, the devices focusing on the smart home have rapidly been spreading and have been expected to be applied to the services that support daily life of the residents such as the observation of daily activity of the elderly people living alone and controlling the energy efficiency. To realize the smart home, the system that can recognize daily activities of the residents with high accuracy and low cost is indispensable. The existing studies have proposed the recognition methods using various sensors such as cameras and ultrasonic sensors for estimating the living behavior. However, the existing methods have problems in terms of the privacy and installation cost. Therefore, in this study, we propose and develop a new behavior observation system that estimates daily activities of the residents by placing smart taps supporting the wireless communication on various places at home. The smart tap has a function of measuring and analyzing the power consumption of the connected devices and the received signal strength of radio waves between the smart taps. In addition, the system constructs a mesh network of the smart taps using the Thread, a type of short-range wireless communication, and the location and behavior of the residents are estimated by collecting and analyzing the measurement data. By analyzing only the measurement results of the power consumption of appliances and the received signal strength of the radio wave, the proposed system achieves accurate behavioral estimation with no privacy issues and low installation cost.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134531910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Low-Power Cryptographic Coprocessor Design for the Internet of Things 面向物联网的低功耗加密协处理器设计

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730198

Bruno L. M. T. Silva, Fernando S. Sousa, Gutemberg G. Santos, Danilo F. S. Santos, Marcos R. A. Morais, A. Perkusich

引用次数: 0

Apples vs. Oranges: The QoE Scenario in Consumer IoT Services 苹果与橘子：消费物联网服务的 QoE 场景

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730388

Tashfiq Rahman, Debajyoti Pal, Suree Funilkul, Naphongthawat Photikit

引用次数: 1

Deep Neural Network Based Multi-Channel Speech Enhancement for Real-Time Voice Communication Using Smartphones 基于深度神经网络的智能手机实时语音通信多通道语音增强

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730152

Soonho Baek, Myungho Lee, Han-gil Moon

引用次数: 0

Architecture Exploration and Customization Tool of Deep Neural Networks for Edge Devices 面向边缘设备的深度神经网络架构探索与定制工具

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730351

Seungho Lim, Shin-Hyeok Kang, B. Ko, Jae-hee Roh, Chaemin Lim, Sang-Young Cho

引用次数: 1