Proceedings of the 2021 3rd Asia Pacific Information Technology Conference最新文献_第2页

SlowFast Convolution LSTM Networks for Dynamic Gesture Recognition 用于动态手势识别的慢速卷积LSTM网络

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449375

Xunlei Zhang, Tie Yun, L. Qi

{"title":"SlowFast Convolution LSTM Networks for Dynamic Gesture Recognition","authors":"Xunlei Zhang, Tie Yun, L. Qi","doi":"10.1145/3449365.3449375","DOIUrl":"https://doi.org/10.1145/3449365.3449375","url":null,"abstract":"Computer vision-based gesture recognition is gradually becoming a popular research direction in the field of human-computer interaction (HCI). However, there are various challenges in the extraction of gesture features, such as complex backgrounds, light changes and shadows. Dynamic gesture recognition aims to identify ongoing gestures from a continuous sequence of gestures, which makes it difficult to accurately extract features about continuous gestures due to not knowing the start frame and stop frame of each gesture instance. In order to overcome the various challenges in the dynamic gesture recognition task, we propose a deep architecture for the recognition of dynamic gestures by applying the SlowFast pathways and convolution LSTM to gesture recognition. End-to-end feature extraction of dynamic gestures is performed through the SlowFast pathways, avoiding the complex feature extraction process. Due to the long time span of dynamic gestures, the motion feature of gestures also play an important role in the specific connotations of gestures, hence the introduction of convolution LSTM to capture the movement information of gestures. The proposed architecture is verified on the ChaLearn LAP large-scale isolated gesture dataset (IsoGD). The results show the validity of our proposed architecture.","PeriodicalId":188200,"journal":{"name":"Proceedings of the 2021 3rd Asia Pacific Information Technology Conference","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133444815","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

A Path of Roses and Financial Literacy: Exploring the Usability of UK's Digital Banking Services to Improve Younger Adult Adoption 玫瑰之路和金融素养:探索英国数字银行服务的可用性，以提高年轻人的采用率

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449369

Kushwanth Koya, David Jones

{"title":"A Path of Roses and Financial Literacy: Exploring the Usability of UK's Digital Banking Services to Improve Younger Adult Adoption","authors":"Kushwanth Koya, David Jones","doi":"10.1145/3449365.3449369","DOIUrl":"https://doi.org/10.1145/3449365.3449369","url":null,"abstract":"Digital retail banking is a prominent method for customers to interact with their banks. However, over the last decade the banking industry has experienced a slowing of digital retail banking adoption rates worldwide, especially in younger adults. Scholars attribute this adoption slowdown on the dissimilar growth of adoption rates and development maturity of digital retail banking applications, where the adoption rates have summited faster than development maturity. As UK banks are advancing their capabilities in digital banking, to the extent of replacing traditional branches with self-service kiosks, it becomes essential to design usable applications for customers. In retail banking, younger customers tend to continue banking as they age with the institution of their first business, hence it becomes essential for banking institutions to provide mature digital services to attract and retain the digital natives. A focussed survey and interviews conducted by the research team indicates that younger adults find the current user-interfaces impede cognitive and visual access to information and are not user-specific. Additionally, it was also found that their lack of financial knowledge and information deters them from using various features and products provided digitally by the banks. Therefore, it appears that inculcation of accessible financial information and user-specificities into the design of digital banking applications, in addition to offering giveaways could improve user adoption rates in young adults.","PeriodicalId":188200,"journal":{"name":"Proceedings of the 2021 3rd Asia Pacific Information Technology Conference","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122641589","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

Affine Transform for Skew Correction Based on Generative Adversarial Network Method for Multi-Camera Person Re-Identification 基于生成对抗网络的斜校正仿射变换多相机人物再识别

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449380

Ziyang Ni, J. Pei, Yang Zhao

{"title":"Affine Transform for Skew Correction Based on Generative Adversarial Network Method for Multi-Camera Person Re-Identification","authors":"Ziyang Ni, J. Pei, Yang Zhao","doi":"10.1145/3449365.3449380","DOIUrl":"https://doi.org/10.1145/3449365.3449380","url":null,"abstract":"In intelligent video surveillance system, person re-identification is a key technology. In order to address the problem, the decrease in performance of person Re-Id lead by the skew pedestrian images, this paper proposes the affine transform for skew correction based on generative adversarial network (GAN) method for multi-camera person re-identification (Re-Id). Firstly, an effective GAN is proposed to guide the spatial transformer network (STN) to learn affine transform parameters for skew correction in an adversarial way, and STN is adopted as the preprocessing model for Re-Id to reduce influence of variations in person posture. Then, features are extracted by a deep convolutional neural network from input images which are corrected by STN, and finally results can be obtained by measuring similarity between features. Besides, in the proposed GAN, a classification model and related loss functions are introduced to reduce the damage to the key features of pedestrian during skew correction. The effectiveness of the proposed method is verified by experiments conducted on the skew pedestrian dataset.","PeriodicalId":188200,"journal":{"name":"Proceedings of the 2021 3rd Asia Pacific Information Technology Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130653990","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

Movilizer Application with Genre and Rating Classification Using NW-KNN Method 用NW-KNN方法进行类型和等级分类的电影应用

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449371

V. C. Mawardi, Cindy Winata, J. Hendryli

引用次数: 1

Customer Journey Mapping of a Public Mobile Application: The Case Study of a State Electricity Enterprise 公共移动应用的客户旅程映射:以某国有电力企业为例

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449372

S. Ramjan, K. Campiranon

引用次数: 0

Generative Image Inpainting for Large-Scale Edge Area 大规模边缘区域的生成图像绘制

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449379

Jiayi Liang, Xueming Li

{"title":"Generative Image Inpainting for Large-Scale Edge Area","authors":"Jiayi Liang, Xueming Li","doi":"10.1145/3449365.3449379","DOIUrl":"https://doi.org/10.1145/3449365.3449379","url":null,"abstract":"In recent years, applying deep learning to computer vision is a very popular research direction, and a number of models with amazing effects have appeared. Deep learning-based approaches for end-to-end image inpainting have shown promise results. Recent research has made great progress in repairing rectangular and free-form areas but there are still many problems and room for improvement. For example, artifacts, blur and color missing still exist among the completion results of the large-scale border area. In this paper, we propose an end-to-end GAN-based image inpainting method, which has a better effect on the large boundary area. Our model is a two-stage adversarial network. The first stage completes the corresponding edge image, and the second stage uses the edge image generated in the first stage as a prior to complete the color image. We added parallel residual blocks to the edge completion network, and for the image completion network we replace the original residual blocks with multi-scale dilated convolution fusion blocks. Besides, a content loss based on DenseNet is added to the second stage. Experiments on multiple publicly available datasets show that our results have better effects on larger edge areas and can increase the average PSNR (Peak Signal to Noise Ratio) and SSIM (Structural Similarity Index).","PeriodicalId":188200,"journal":{"name":"Proceedings of the 2021 3rd Asia Pacific Information Technology Conference","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116312563","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

Data Model For Bigdata System For Multimedia 多媒体大数据系统的数据模型

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449368

J. Bobulski, M. Kubanek

引用次数: 1

An Improved Method of Dynamic Path Modification for Nonholonomic Mobile Robot 一种改进的非完整移动机器人动态路径修正方法

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449381

Linan Yin, Mengxu Zhang, Jianhui Wang, Xiangchuan Gao, Jinyuan Shen

{"title":"An Improved Method of Dynamic Path Modification for Nonholonomic Mobile Robot","authors":"Linan Yin, Mengxu Zhang, Jianhui Wang, Xiangchuan Gao, Jinyuan Shen","doi":"10.1145/3449365.3449381","DOIUrl":"https://doi.org/10.1145/3449365.3449381","url":null,"abstract":"The TEB (timed elastic band) algorithm optimizes the path generated by the global planner to obtain a time-optimal trajectory that can avoid obstacles and satisfy the kinematics and dynamics constraints of the robots. In TEB algorithm, backward is often used to adjust the direction, which makes the trajectory not smooth enough. For differential driving robot, it is more convenient to rotate in situ to adjust direction. Excessive rates of change in acceleration can cause the torque output of the robot chassis motor to abruptly change, subjecting the robot to shock oscillation. In the improved TEB algorithm, the velocity constraint is modified and the specific jerk constraint is constructed. The improved TEB algorithm is simulated on the Stage simulation platform and implemented on a real differential driving robot. The experimental results show that the improved TEB algorithm can generate smoother forward trajectory without backward for wheeled differential driving robot, and the trajectory has good obstacle avoidance effect. Meanwhile, the algorithm can better solve the shock oscillation problem of the robot.","PeriodicalId":188200,"journal":{"name":"Proceedings of the 2021 3rd Asia Pacific Information Technology Conference","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128981006","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

Image Saliency Detection via Multi-Feature and Manifold-Space Ranking 基于多特征和流形空间排序的图像显著性检测

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449378

Xiaoli Li, Huaici Zhao, Yunpeng Liu

引用次数: 1

Research on Application of Information Management Technology in Computer Big Data System 信息管理技术在计算机大数据系统中的应用研究

Proceedings of the 2021 3rd Asia Pacific Information Technology Conference Pub Date : 2021-01-15 DOI: 10.1145/3449365.3449366

Wenjun Ji

引用次数: 3