Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Mei Chee Leong"'
Publikováno v:
Applied Sciences, Vol 10, Iss 2, p 557 (2020)
This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D convolutional neural networks (CNNs), 3D CNNs can be applied directly on consecutive frames to extract
Externí odkaz:
https://doaj.org/article/9973a0446d414e51aca0107454db7e77
Fine-grained human action recognition is a core research topic in computer vision. Inspired by the recently proposed hierarchy representation of fine-grained actions in FineGym and SlowFast network for action recognition, we propose a novel multi-tas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee5391c4c364d5efcf74c7b9d26078e0
http://arxiv.org/abs/2110.05853
http://arxiv.org/abs/2110.05853
Autor:
Liyuan Li, Hui Li Tan, Nicolas Gauthier, Joo-Hwee Lim, Ying Sun, Mei Chee Leong, Yi Cheng, Fen Fang, Qianli Xu
Publikováno v:
ICIP
Cobots that can work in human workspaces and adapt to human need to understand and respond to human’s inquiry and instruction. In this paper, we propose new question answering (QA) task and dataset for human-robot collaboration on task-oriented ope
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2ee2e3c1292e3ed8c776c95c2be0af91
https://doi.org/10.1109/icip40778.2020.9190659
https://doi.org/10.1109/icip40778.2020.9190659
Publikováno v:
Applied Sciences
Volume 10
Issue 2
Applied Sciences, Vol 10, Iss 2, p 557 (2020)
Volume 10
Issue 2
Applied Sciences, Vol 10, Iss 2, p 557 (2020)
This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D convolutional neural networks (CNNs), 3D CNNs can be applied directly on consecutive frames to extract
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::245a75c07f5484969d3e9343d98484d5
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 35(11)
Several studies have been made in finding the faces of an object depicted in a line drawing, but the problem has not been completely solved. Although existing methods can find the correct faces in most cases, there is no mechanism to ascertain that t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40e74e44c91046e1463e88cf7b0daa63
https://pubmed.ncbi.nlm.nih.gov/24051721
https://pubmed.ncbi.nlm.nih.gov/24051721