Zobrazeno 1 - 10
of 337
pro vyhledávání: '"Ji‐Xiang Du"'
Publikováno v:
Complex & Intelligent Systems, Vol 9, Iss 2, Pp 1963-1974 (2022)
Abstract Can a computer evaluate an athlete’s performance automatically? Many action quality assessment (AQA) methods have been proposed in recent years. Limited by the randomness of video sampling and the simple strategy of model training, the per
Externí odkaz:
https://doaj.org/article/cac89957cad041319064c265b40ff1fe
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2020, Iss 1, Pp 1-14 (2020)
Abstract This paper proposes a new neural network learning method to improve the performance for action recognition in video. Most human action recognition methods use a clip-level training strategy, which divides the video into multiple clips and tr
Externí odkaz:
https://doaj.org/article/e1ef2cd9d32940b1b86896ab05a4985d
Publikováno v:
Intelligent Automation & Soft Computing. 36:3243-3256
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5e9f3c4d0c71ebfdceedc8415d143fbb
https://doi.org/10.32604/iasc.2023.035812
https://doi.org/10.32604/iasc.2023.035812
Publikováno v:
Computing & Informatics; 2024, Vol. 43 Issue 2, p482-504, 23p
Publikováno v:
Multimedia Tools and Applications. 81:39453-39470
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b14ac6782dce2ff36d09791ffc29d66c
https://doi.org/10.1007/s11042-022-13146-x
https://doi.org/10.1007/s11042-022-13146-x
Publikováno v:
The Visual Computer. 39:2191-2203
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a6bf9deec79ec02a07c7f8d2bf21f81e
https://doi.org/10.1007/s00371-022-02473-7
https://doi.org/10.1007/s00371-022-02473-7
Publikováno v:
IEEE Transactions on Artificial Intelligence. 3:254-264
In this paper, a new vision- and grating-sensor-based intelligent unmanned settlement (IUS) system is proposed for convenience stores to automatically recognize the shopping behavior of customers, record their identities, and generate invoices. First
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::43bd21e6b237112edcd92181698bb5f8
https://doi.org/10.1109/tai.2021.3116227
https://doi.org/10.1109/tai.2021.3116227
Autor:
Hong‐Bo Zhang, Qing Lei, Duan‐Sheng Chen, Bi‐Neng Zhong, Jialin Peng, Ji‐Xiang Du, Song‐Zhi Su
Publikováno v:
IET Computer Vision, Vol 10, Iss 6, Pp 528-536 (2016)
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 de
Externí odkaz:
https://doaj.org/article/1b12e7bad87e45bab8b071340ebc5d31
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 18:1-18
The local key features in video are important for improving the accuracy of human action recognition. However, most end-to-end methods focus on global feature learning from videos, while few works consider the enhancement of the local information in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3e8830cd6f57c1459c3f6830abb92734
https://doi.org/10.1145/3485665
https://doi.org/10.1145/3485665
Publikováno v:
Journal of Sensors, Vol 2021 (2021)
Multiperson pose estimation is an important and complex problem in computer vision. It is regarded as the problem of human skeleton joint detection and solved by the joint heat map regression network in recent years. The key of achieving accurate pos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d60f4b7dc6f469b92556b2ac996f71a
https://doi.org/10.1155/2021/1484218
https://doi.org/10.1155/2021/1484218