发布求助
文献互助 智能选刊 最新文献

2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)最新文献

筛选
英文 中文
PetGen: Design and Generation of Virtual Pets PetGen:虚拟宠物的设计和生成
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00065
Hongni Ye, Ruoxin You, Kaiyuan Lou, Yili Wen, Xin Yi, Xin Tong
{"title":"PetGen: Design and Generation of Virtual Pets","authors":"Hongni Ye, Ruoxin You, Kaiyuan Lou, Yili Wen, Xin Yi, Xin Tong","doi":"10.1109/ICMEW59549.2023.00065","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00065","url":null,"abstract":"Virtual pets are essential virtual characters in-game narratives and can influence players' sense of immersion. However, the design of virtual pets' appearances is often repetitive work that relies on the designers' experiences without association with the pets' potential personalities. In this work, we propose PetGen, an application that can generate varying virtual pets' appearances following the Five-Factor Model (FFM) based on AI algorithms. The 3D voxel virtual pets' appearances were initialized under four initial archetypes and then underwent recombination, dyeing, and texturing stages, where AI algorithms were applied as filters. We conducted a pilot study to learn users' perceptions of machine-generated pets. The findings revealed that participants preferred the generated pets more than those manually designed. In future work, we will explore other machine learning approaches for 3D voxel object generation, especially virtual pets with more diverse personalities and appearance traits.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"46 15","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120856603","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
Q-YOLOP: Quantization-Aware You Only Look Once for Panoptic Driving Perception Q-YOLOP:量化意识，你只看一次全景驾驶感知
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00015
Chi-Chih Chang, Wei-Cheng Lin, Peide Wang, Shengtao Yu, Yunrong Lu, Kuan-Cheng Lin, Kaiyang Wu
{"title":"Q-YOLOP: Quantization-Aware You Only Look Once for Panoptic Driving Perception","authors":"Chi-Chih Chang, Wei-Cheng Lin, Peide Wang, Shengtao Yu, Yunrong Lu, Kuan-Cheng Lin, Kaiyang Wu","doi":"10.1109/ICMEW59549.2023.00015","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00015","url":null,"abstract":"In this work, we present an efficient and quantization-aware panoptic driving perception model (Q-YOLOP) for object detection, drivable area segmentation, and lane line segmentation, in the context of autonomous driving. Our model employs the Efficient Layer Aggregation Network (ELAN) as its backbone and task-specific heads for each task. We employ a four-stage training process that includes pretraining on the BDD100K dataset, finetuning on both the BDD100K and iVS datasets, and quantization-aware training (QAT) on BDD100K. During the training process, we use powerful data augmentation techniques, such as random perspective and mosaic, and train the model on a combination of the BDD100K and iVS datasets. Both strategies enhance the model's generalization capabilities. The proposed model achieves state-of-the-art performance with an mAP@0.5 of 0.622 for object detection and an mIoU of 0.612 for segmentation, while maintaining low computational and memory requirements.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127380785","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: 8
An Ensemble of Supervised Learning and Image Inpainting for Mura Detection 基于监督学习和图像绘制的村村检测
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00096
Chia-Yu Lin, Tzu-Min Chang, Hao-Yuan Chen, Tzer-jen Wei
{"title":"An Ensemble of Supervised Learning and Image Inpainting for Mura Detection","authors":"Chia-Yu Lin, Tzu-Min Chang, Hao-Yuan Chen, Tzer-jen Wei","doi":"10.1109/ICMEW59549.2023.00096","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00096","url":null,"abstract":"Mura refers to surface defects or areas of uneven brightness that can occur during factory panel production. Mura can vary in size and shape and be categorized as “light Mura” or “serious Mura.” To optimize the repair process, factories aim to differentiate between the two types of Mura before sending the panels for repair. However, current Mura detection models focus only on identifying “nrmal” and “Mura,” resulting in poor performance in distinguishing between light and serious Mura. To address this issue, we propose an ensemble approach called the Ensemble Image Inpainting and Supervised Modeling Mura Detection System (EISMDS), which combines supervised and image inpainting models to differentiate between the two types of Mura. Experimental results show that our approach improves the True Positive Rate (TPR) by 11 % under a high True Negative Rate (TNR) compared to a single supervised detection model.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121897459","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
Exploiting Richness of Learned Compressed Representation of Images for Semantic Segmentation 利用图像学习压缩表示的丰富度进行语义分割
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00091
Ravi Kakaiya, Rakshith Sathish, R. Sethuraman, D. Sheet
{"title":"Exploiting Richness of Learned Compressed Representation of Images for Semantic Segmentation","authors":"Ravi Kakaiya, Rakshith Sathish, R. Sethuraman, D. Sheet","doi":"10.1109/ICMEW59549.2023.00091","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00091","url":null,"abstract":"Autonomous vehicles and Advanced Driving Assistance Systems (ADAS) have the potential to radically change the way we travel. Many such of such vehicles currently rely on segmentation and object detection algorithms to detect and track objects around its surrounding. The data collected from the vehicles are often sent to cloud servers to facilitate continual/life-long learning of these algorithms. Considering the bandwidth constraints, the data is compressed before sending it to servers, where it is typically decompressed for training and analysis. In this work, we propose the use of a learning-based compression Codec to reduce the overhead in latency incurred for the decompression operation in the standard pipeline. We demonstrate that the learned compressed representation can also be used to perform tasks like semantic segmentation in addition to decompression to obtain the images. We experimentally validate the proposed pipeline on the Cityscapes dataset, where we achieve a compression factor up to 66× while preserving the information required to perform segmentation with a dice coefficient of 0.84 as compared to 0.88 achieved using decompressed images while reducing the overall compute by 11%.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128582723","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
Advanced Digitization for Ancient Chinese Guqin Scores Based on Mask R-CNN Algorithm 基于掩模R-CNN算法的古琴谱高级数字化
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00070
Bing Wei, Youdi Wang
{"title":"Advanced Digitization for Ancient Chinese Guqin Scores Based on Mask R-CNN Algorithm","authors":"Bing Wei, Youdi Wang","doi":"10.1109/ICMEW59549.2023.00070","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00070","url":null,"abstract":"This paper announced a novel digitization method for Chinese Guqin scores, to translate all Guqin scores from image version in books to digital version. As one of the global heritages, Guqin kept using its typical score system called Ch'in Tablature (means “reduced notation”, and pronounced as “Jian Zi Pu” in Chinese pinyin) in past over one thousand years, which was created from using typical Chinese characters. However, translating Ch'in Tablature from images to digital version was still not solved. In this paper, the world's first Ch'in Tablature character dataset was created which includes over 12,000 characters, a novel method based on Mask R-CNN algorithm was announced as well. The tests with the initial dataset showed over 95% of success rate for recognizing Ch'in Tablature characters. The technical challenges and future works are also discussed in this paper.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129161536","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
On The Irrelevance of Machine Learning Algorithms and the Importance of Relativity 论机器学习算法的不相关性和相对性的重要性
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00009
Carlos Huertas, Qi Zhao
{"title":"On The Irrelevance of Machine Learning Algorithms and the Importance of Relativity","authors":"Carlos Huertas, Qi Zhao","doi":"10.1109/ICMEW59549.2023.00009","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00009","url":null,"abstract":"Information explosion has brought us a wide range of data formats and machine learning keeps in constant evolution to develop mechanisms to extract knowledge from them. Modern models in the Deep Learning space have proven to be very successful in multiple applications, yet in the tabular space they fail to provide consistent competitive performance. However, in this work we claim model selection can become irrelevant as the key tends to lie in data processing. In this paper we introduce the concept of relativity in feature engineering, a powerful methodology to boost any classifier performance and we provide over 30 different configurations of models and feature engineering designs to prove we can bias any result to help an arbitrary model score best. Our results attribute 600% more value to feature engineering than model selection. In order to validate the effectiveness of our approach, we submitted our work to a live machine learning competition with outstanding results regardless of our model of choice.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124586743","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
Learning Harmony Based on Grammar Analysis and Visualization 基于语法分析和可视化的和谐学习
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00069
Xingda Li, Zhaodong Wang, Yonghe Zheng, Lin Gan
{"title":"Learning Harmony Based on Grammar Analysis and Visualization","authors":"Xingda Li, Zhaodong Wang, Yonghe Zheng, Lin Gan","doi":"10.1109/ICMEW59549.2023.00069","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00069","url":null,"abstract":"This article explores the process of learning composition by analyzing music grammar and utilizing visualization tools. The frequency relationships and characteristics of chords are combined with mathematical tools to establish a correlation analysis method based on mathematical models. This method is not only a visual representation, but also a construction of a mathematical model based on the essential correlation of chords. The article highlights a new mathematical representation of chord characteristics which is constructed by assigning geometric-mathematical definitions to different functional chords, and establishing a correlation between them. The study also examines the process of creating four-part harmony from a given melody, utilizing various grammars and visualization tools. The article aims to simplify and clarify the analysis of basic music theory concepts, including chord progressions, counterpoint, voice leading, and harmonic analysis. The findings offer a practical approach for composition beginners to learn and create music.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124034837","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
FBRA360: A Fuzzy-Based Bitrate Adaptation Scheme for 360° Video Streaming FBRA360:基于模糊的360°视频流比特率自适应方案
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00028
Si-Ze Qian, Yuan Zhang, Tao Lin
{"title":"FBRA360: A Fuzzy-Based Bitrate Adaptation Scheme for 360° Video Streaming","authors":"Si-Ze Qian, Yuan Zhang, Tao Lin","doi":"10.1109/ICMEW59549.2023.00028","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00028","url":null,"abstract":"Bitrate adaptation is a classic research problem in video streaming. In a tile-based 360° video streaming system, the problem becomes even more complicated because the system needs to conduct viewport prediction (VP) except for traditional bitrate selection (BS). Existing methods usually treat VP and BS separately, which is sub-optimal and thus limits performance improvement. Inspired by our observation of the bidirectional dependency between VP and BS, we propose FBRA360, a fuzzy-based low-complexity joint optimization scheme, to tackle this problem. A fuzzy logic controller has been devised to control simultaneously: (1) the weighted combination of VP from individual users' historical trajectory and multi-user attention distribution, and (2) the expected buffer occupancy after each download. Experimental results show that FBRA360 improves the VP accuracy by 16.2% and the video quality by 7.5%, compared with the state-of-the-art algorithms.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121745555","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
Predicting Frags in Tactic Games at KnowledgePit.ai: ICME 2023 Grand Challenge Report 在KnowledgePit预测战术游戏中的分数。ICME 2023大挑战报告
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00006
Andrzej Janusz, D. Ślęzak
{"title":"Predicting Frags in Tactic Games at KnowledgePit.ai: ICME 2023 Grand Challenge Report","authors":"Andrzej Janusz, D. Ślęzak","doi":"10.1109/ICMEW59549.2023.00006","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00006","url":null,"abstract":"We describe a data science competition ICME 2023 Grand Challenge: Predicting Frags in Tactic Games that was organized in association with the IEEE ICME conference series at the KnowledgePit.ai platform. This challenge was the second in a series of competitions related to the analysis of data from a turn-based tactic video game Tactical Troops: Anthracite Shift. We discuss the competition's scope and significance of the considered research problem. We also overview the construction of the baseline solution and the most interesting results obtained by competing teams. We also indicate how the challenge outcomes fit into our future plans related to video game data analytics and the future applications of our KnowledgePit.ai platform.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134422835","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 Fast Gradient Boosting Based Approach for Predicting Frags in Tactic Games 一种基于快速梯度增强的战术博弈中碎片预测方法
2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) Pub Date : 2023-07-01 DOI: 10.1109/ICMEW59549.2023.00007
Haitao Xiao, Jinzhong Yang, Yuling Liu, Junrong Liu, D. Du, Zhigang Lu
{"title":"A Fast Gradient Boosting Based Approach for Predicting Frags in Tactic Games","authors":"Haitao Xiao, Jinzhong Yang, Yuling Liu, Junrong Liu, D. Du, Zhigang Lu","doi":"10.1109/ICMEW59549.2023.00007","DOIUrl":"https://doi.org/10.1109/ICMEW59549.2023.00007","url":null,"abstract":"Predicting the probability of scoring a frag in a tactical video game is a challenging task. It is hard for humans to evaluate the real-time game situation and predict whether a player can score in his/her turn. In this paper, we present a fast gradient boosting based approach to this problem consisting of data analysis, feature engineering, and model construction. Firstly, we analyze the game data and identify the key factors that influence the probability of frag scoring. Then, we extract relevant features from game states metadata and map metadata in the feature engineering stage. Finally, we train and predict the probability of scoring a frag using a gradient boosting based method. Our proposed approach achieves an AUC score of 0.8008 on the whole test set, and only takes 156 seconds for 10-fold cross-validation, demonstrating its effectiveness and efficiency.","PeriodicalId":111482,"journal":{"name":"2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127563982","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
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信