DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nguyen, Anh H. | ko |
dc.contributor.author | Tran, Huyen T. T. | ko |
dc.contributor.author | Truong Cong Thang | ko |
dc.contributor.author | Ro, Yong Man | ko |
dc.date.accessioned | 2020-06-25T03:20:30Z | - |
dc.date.available | 2020-06-25T03:20:30Z | - |
dc.date.created | 2020-06-11 | - |
dc.date.created | 2020-06-11 | - |
dc.date.issued | 2018-10 | - |
dc.identifier.citation | IEEE 7th Global Conference on Consumer Electronics (GCCE), pp.114 - 115 | - |
dc.identifier.issn | 2378-8143 | - |
dc.identifier.uri | http://hdl.handle.net/10203/274883 | - |
dc.description.abstract | Recent state-of-the-art systems for human action recognition are computationally intensive due to the use of full-length videos and complex network structures. This study aims to develop sampling strategies as well as simple network structure to boost inference time of recognition. Especially, auto-correlation sequence, which shows the similarity between a video and a lagged version of itself, is adopted to extract the most essential segment of the video without information loss. The proposed method considerably reduces inference time while keeping comparable recognition accuracy. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Fast Recognition of Human Actions Using Autocorrelation Sequence | - |
dc.type | Conference | - |
dc.identifier.wosid | 000459859500030 | - |
dc.identifier.scopusid | 2-s2.0-85060289624 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 114 | - |
dc.citation.endingpage | 115 | - |
dc.citation.publicationname | IEEE 7th Global Conference on Consumer Electronics (GCCE) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Nara, JAPAN | - |
dc.identifier.doi | 10.1109/GCCE.2018.8574820 | - |
dc.contributor.localauthor | Ro, Yong Man | - |
dc.contributor.nonIdAuthor | Nguyen, Anh H. | - |
dc.contributor.nonIdAuthor | Tran, Huyen T. T. | - |
dc.contributor.nonIdAuthor | Truong Cong Thang | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.