Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Xiangbo Su"'
Publikováno v:
ICPR
An essential yet challenging issue in crowd counting is the diverse background variations under complicated real-life environments, which makes attention based methods favorable in recent years. However, most existing methods only rely on first-order
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36fe960f50a2233713b9c9074f763766
https://doi.org/10.1109/icpr48806.2021.9412883
https://doi.org/10.1109/icpr48806.2021.9412883
Publikováno v:
Journal of Real-Time Image Processing. 15:583-596
Kernelized correlation filter (KCF) is a kind of efficient method for real-time tracking, but remains being challenged by the drifting problem due to inaccurate localization caused by the scale variation and wrong candidate selection. In this paper,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b4a0fa188eb04dadd778a198ecb03f7
https://doi.org/10.1007/s11554-018-0758-z
https://doi.org/10.1007/s11554-018-0758-z
Publikováno v:
IEEE transactions on neural networks and learning systems. 30(2)
Video classification has been extensively researched in computer vision due to its wide spread applications. However, it remains an outstanding task because of the great challenges in effective spatial-temporal feature extraction and efficient classi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf27300850487ba062a559c15dd7fcad
https://pubmed.ncbi.nlm.nih.gov/29994406
https://pubmed.ncbi.nlm.nih.gov/29994406
Compression artifacts reduction (CAR) is a challenging problem in the field of remote sensing. Most recent deep learning based methods have demonstrated superior performance over the previous hand-crafted methods. In this paper, we propose an end-to-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9f44bc62d3fd7f6675adacb14941f75
http://arxiv.org/abs/1804.00256
http://arxiv.org/abs/1804.00256
Publikováno v:
Cloud Computing and Security ISBN: 9783319486734
ICCCS (2)
ICCCS (2)
Kernelized Correlation Filter (KCF) is one of state-of-the-art trackers. However, KCF suffers from the drifting problem due to inaccurate localization caused by the scale variation and wrong candidate selection. In this paper, we propose a new method
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::06b6571d3ed601771f0b9d33c71ef635
https://doi.org/10.1007/978-3-319-48674-1_50
https://doi.org/10.1007/978-3-319-48674-1_50