We propose a method SPGNet for 3D human pose estimation that mixes multi-dimensional re-projection into supervised learning. In this method, the 2D-to-3D-lifting network predicts the global position and coordinates of the 3D human pose. Then, we re-project the estimated 3D pose back to the 2D key points along with spatial adjustments. The loss functions compare the estimated 3D pose with the 3D pose ground truth, and re-projected 2D pose with the input 2D pose. In addition, we propose a kinematic constraint to restrict the predicted target with constant human bone length. Based on the estimation results for the dataset Human3.6M, our approach outperforms many state-of-the-art methods both qualitatively and quantitatively.
{"title":"SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space","authors":"Zihan Wang, Ruimin Chen, Mengxuan Liu, Guanfang Dong, Anup Basu","doi":"10.48550/arXiv.2206.01867","DOIUrl":"https://doi.org/10.48550/arXiv.2206.01867","url":null,"abstract":"We propose a method SPGNet for 3D human pose estimation that mixes multi-dimensional re-projection into supervised learning. In this method, the 2D-to-3D-lifting network predicts the global position and coordinates of the 3D human pose. Then, we re-project the estimated 3D pose back to the 2D key points along with spatial adjustments. The loss functions compare the estimated 3D pose with the 3D pose ground truth, and re-projected 2D pose with the input 2D pose. In addition, we propose a kinematic constraint to restrict the predicted target with constant human bone length. Based on the estimation results for the dataset Human3.6M, our approach outperforms many state-of-the-art methods both qualitatively and quantitatively.","PeriodicalId":211605,"journal":{"name":"International Conference on Smart Multimedia","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132014832","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}
Pub Date : 2022-04-08DOI: 10.48550/arXiv.2204.04272
Xinyao Sun, Yi Lu, Jinghan Sun, Bohao Tang, K. Rehak, Shuyi Zhang
—Due to the rising complexity of the metaverse’s busi- ness logic and the low-latency nature of the metaverse, developers typically encounter the challenge of effectively reading, writing, and retrieving historical on-chain data in order to facilitate their functional implementations at scale. While it is true that accessing blockchain states is simple, more advanced real-world operations such as search, aggregation, and conditional filtering are not available when interacting directly with blockchain networks, particularly when dealing with requirements for on-chain event reflection. We offer Matrix Syncer, the ultimate middleware that bridges the data access gap between blockchains and end-user applications. Matrix Syncer is designed to facilitate the consoli-dation of on-chain information into a distributed data warehouse while also enabling customized on-chain state transformation for a scalable storage, access, and retrieval. It offers a unified layer for both on- and off-chain state, as well as a fast and flexible atomic query. Matrix Syncer is easily incorporated into any infrastructure to aggregate data from various blockchains concurrently, such as Ethereum and Flow. The system has been deployed to support several metaverse projects with a total value of more than $15 million USD.
{"title":"Matrix Syncer - A Multi-chain Data Aggregator For Supporting Blockchain-based Metaverses","authors":"Xinyao Sun, Yi Lu, Jinghan Sun, Bohao Tang, K. Rehak, Shuyi Zhang","doi":"10.48550/arXiv.2204.04272","DOIUrl":"https://doi.org/10.48550/arXiv.2204.04272","url":null,"abstract":"—Due to the rising complexity of the metaverse’s busi- ness logic and the low-latency nature of the metaverse, developers typically encounter the challenge of effectively reading, writing, and retrieving historical on-chain data in order to facilitate their functional implementations at scale. While it is true that accessing blockchain states is simple, more advanced real-world operations such as search, aggregation, and conditional filtering are not available when interacting directly with blockchain networks, particularly when dealing with requirements for on-chain event reflection. We offer Matrix Syncer, the ultimate middleware that bridges the data access gap between blockchains and end-user applications. Matrix Syncer is designed to facilitate the consoli-dation of on-chain information into a distributed data warehouse while also enabling customized on-chain state transformation for a scalable storage, access, and retrieval. It offers a unified layer for both on- and off-chain state, as well as a fast and flexible atomic query. Matrix Syncer is easily incorporated into any infrastructure to aggregate data from various blockchains concurrently, such as Ethereum and Flow. The system has been deployed to support several metaverse projects with a total value of more than $15 million USD.","PeriodicalId":211605,"journal":{"name":"International Conference on Smart Multimedia","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122928713","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}
Pub Date : 2019-12-16DOI: 10.1007/978-3-030-54407-2_44
E. López-Caudana, P. Ponce, Nancy Mazon, Luis Marquez, Ivan Mejia, G. B. Reyes
{"title":"Improving the Attention Span of Elementary School Children in Mexico Through a S4 Technology Platform","authors":"E. López-Caudana, P. Ponce, Nancy Mazon, Luis Marquez, Ivan Mejia, G. B. Reyes","doi":"10.1007/978-3-030-54407-2_44","DOIUrl":"https://doi.org/10.1007/978-3-030-54407-2_44","url":null,"abstract":"","PeriodicalId":211605,"journal":{"name":"International Conference on Smart Multimedia","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127103509","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}
Pub Date : 2019-12-16DOI: 10.1007/978-3-030-54407-2_6
Yingnan Ma, Guanfang Dong, Chenqiu Zhao, A. Basu, Zhengjiang Wu
{"title":"Background Subtraction Based on Principal Motion for a Freely Moving Camera","authors":"Yingnan Ma, Guanfang Dong, Chenqiu Zhao, A. Basu, Zhengjiang Wu","doi":"10.1007/978-3-030-54407-2_6","DOIUrl":"https://doi.org/10.1007/978-3-030-54407-2_6","url":null,"abstract":"","PeriodicalId":211605,"journal":{"name":"International Conference on Smart Multimedia","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124052425","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}
Pub Date : 2019-12-16DOI: 10.1007/978-3-030-54407-2_41
José Martín Molina Espinosa, Jhonattan Miranda, D. Cortés, J. Medina, A. Molina
{"title":"3D Virtual Environments to Support New Product Development: A Mobile Platform Based on an Open Innovation Laboratory Applied in Higher Education","authors":"José Martín Molina Espinosa, Jhonattan Miranda, D. Cortés, J. Medina, A. Molina","doi":"10.1007/978-3-030-54407-2_41","DOIUrl":"https://doi.org/10.1007/978-3-030-54407-2_41","url":null,"abstract":"","PeriodicalId":211605,"journal":{"name":"International Conference on Smart Multimedia","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134073632","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}
Pub Date : 2019-12-16DOI: 10.1007/978-3-030-54407-2_19
Neeraj J. Gadgil, Guan-Ming Su
{"title":"Improving Temporal Stability in Inverse Tone-Mapped High Dynamic Range Video","authors":"Neeraj J. Gadgil, Guan-Ming Su","doi":"10.1007/978-3-030-54407-2_19","DOIUrl":"https://doi.org/10.1007/978-3-030-54407-2_19","url":null,"abstract":"","PeriodicalId":211605,"journal":{"name":"International Conference on Smart Multimedia","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130550933","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}
Pub Date : 2019-12-16DOI: 10.1007/978-3-030-54407-2_11
P. Ponce, E. López, A. Molina
{"title":"Implementing Robotic Platforms for Therapies Using Qualitative Factors in Mexico","authors":"P. Ponce, E. López, A. Molina","doi":"10.1007/978-3-030-54407-2_11","DOIUrl":"https://doi.org/10.1007/978-3-030-54407-2_11","url":null,"abstract":"","PeriodicalId":211605,"journal":{"name":"International Conference on Smart Multimedia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123048203","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：