Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Duansheng Chen"'
Publikováno v:
PLoS ONE, Vol 11, Iss 8, p e0161808 (2016)
To achieve effective visual tracking, a robust feature representation composed of two separate components (i.e., feature learning and selection) for an object is one of the key issues. Typically, a common assumption used in visual tracking is that th
Externí odkaz:
https://doaj.org/article/1b03f16b1e914095b55645d799ef2c5b
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 13:1-17
Label imbalance and the insufficiency of labeled training samples are major obstacles in most methods for counting people in images or videos. In this work, a sparse representation-based semi-supervised regression method is proposed to count people i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::110966557181cc5c783c05ceae9448f5
https://doi.org/10.1145/3106156
https://doi.org/10.1145/3106156
Publikováno v:
International Journal of Applied Electromagnetics and Mechanics. 52:999-1006
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2059265f6adfbec34ce0bfb303400c4c
https://doi.org/10.3233/jae-162187
https://doi.org/10.3233/jae-162187
Publikováno v:
Sensors, Vol 19, Iss 19, p 4129 (2019)
Sensors (Basel, Switzerland)
Sensors (Basel, Switzerland)
The fields of human activity analysis have recently begun to diversify. Many researchers have taken much interest in developing action recognition or action prediction methods. The research on human action evaluation differs by aiming to design compu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8291bb289d70c0ccf13293699cf67e86
https://www.mdpi.com/1424-8220/19/19/4129
https://www.mdpi.com/1424-8220/19/19/4129
Autor:
Zhen Cui, Yingju Shen, Tian Wang, Duansheng Chen, Hong-Bo Zhang, Xiangnan Yang, Bineng Zhong, Cheng Wang, Xiaopeng Hong
Publikováno v:
Neurocomputing. 215:118-127
Object tracking has a wide range of applications and great efforts have been spent to build the object appearance model using image features encoded in a vector as observations. Since a video or image sequence is intrinsically a multi-dimensional mat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed441125912951db526270043248b7de
https://doi.org/10.1016/j.neucom.2015.09.138
https://doi.org/10.1016/j.neucom.2015.09.138
Publikováno v:
Multimedia Tools and Applications. 76:16767-16782
The cartoon-like stylization of color video images is one of the major types of non-photorealistic rendering. It has broad applications in the entertainment industry due to its lively style, flexible form, and autonomous creation. Our video cartooniz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e8602b7092dc3b5283a35f76731817d
https://doi.org/10.1007/s11042-016-3951-8
https://doi.org/10.1007/s11042-016-3951-8
Publikováno v:
IET Computer Vision. 10:528-536
In this study, the authors investigate the possibility of boosting action recognition performance by exploiting the associated scene context. Towards this end, the authors model a scene as a mid-level `middle layer' in order to bridge action descript
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2125949f29f184e9c67a5e3e42d52d52
https://doi.org/10.1049/iet-cvi.2015.0420
https://doi.org/10.1049/iet-cvi.2015.0420
Publikováno v:
Applied Soft Computing. 38:1088-1098
Object appearance model is a crucial module for object tracking and numerous schemes have been developed for object representation with impressive performance. Traditionally, the features used in such object appearance models are predefined in a hand
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d05e7e8e374b46da882e3d599e1d1a55
https://doi.org/10.1016/j.asoc.2015.06.048
https://doi.org/10.1016/j.asoc.2015.06.048
Autor:
Wenming Zheng, Shu-Juan Peng, Zhen Cui, Jin Gou, Xin Liu, Xie Weibo, Hong-Bo Zhang, Yingju Shen, Ji-Xiang Du, Jing Wang, Bineng Zhong, Duansheng Chen, Yan Chen, Tian Wang
Publikováno v:
Neurocomputing. 151:710-718
In this paper, we study the challenging problem of tracking single object in a complex dynamic scene. In contrast to most existing trackers which only exploit 2D color or gray images to learn the appearance model of the tracked object online, we take
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c50a45b73854cddf1b321d74b1ee132d
https://doi.org/10.1016/j.neucom.2014.06.083
https://doi.org/10.1016/j.neucom.2014.06.083
Publikováno v:
Journal of Software. 10:20-31
Semantic similarity measurement of multilingual words is a challenging problem in data mining, information extraction, information retrieval, etc. This paper introduces an algorithm to measure the semantic similarity of Chinese-English bilingual word
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::261846715586f7c8291bd72c075d9b57
https://doi.org/10.17706/jsw.10.1.20-31
https://doi.org/10.17706/jsw.10.1.20-31