Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Siquan Yu"'
Publikováno v:
Frontiers in Neurorobotics, Vol 17 (2024)
There exist various methods for transferring knowledge between neural networks, such as parameter transfer, feature sharing, and knowledge distillation. However, these methods are typically applied when transferring knowledge between networks of equa
Externí odkaz:
https://doaj.org/article/8681934fadf746dab56828b821528054
Publikováno v:
IEEE Access, Vol 9, Pp 82471-82484 (2021)
Palm vein recognition is a high-security biometric. Outside the NIR capture box and contactless palm vein recognition are more popular but challenging. The users feel comfortable outside the NIR capture box but face more optical blurring brought by v
Externí odkaz:
https://doaj.org/article/2bba3bbc084e4977bf0e48640db7d8c5
Publikováno v:
IEEE Access, Vol 8, Pp 160285-160296 (2020)
Image clustering is a complex procedure that is significantly affected by the choice of the image representation. Generally speaking, image representations are generated by using handcraft features or trained neural networks. When dealing with high d
Externí odkaz:
https://doaj.org/article/154b8fafbd9e46d0bd57fca20ca2e5e4
Publikováno v:
IEEE Access, Vol 5, Pp 22433-22442 (2017)
This paper proposes a sparse video representation with a deformable spatiotemporal template feature, named as active trace template. An active trace is the motion track of an active spatial feature, which moves in a certain velocity. To accommodate g
Externí odkaz:
https://doaj.org/article/064040604361442e858a5481d571c6bf
Publikováno v:
Science China Information Sciences. 66
Publikováno v:
IEEE Access, Vol 9, Pp 82471-82484 (2021)
Palm vein recognition is a high-security biometric. Outside the NIR capture box and contactless palm vein recognition are more popular but challenging. The users feel comfortable outside the NIR capture box but face more optical blurring brought by v
Publikováno v:
2021 IEEE International Conference on Unmanned Systems (ICUS).
Publikováno v:
RCAR
Image clustering is a fundamental problem in computer vision domains. In this survey, we provide a comprehensive overview of image clustering. Specifically, we first discuss the applications of image clustering across various domains. Then, we summar
Publikováno v:
Mathematical Problems in Engineering, Vol 2019 (2019)
Underwater object recognition in sonar images, such as mine detection and wreckage detection of a submerged airplane, is a very challenging task. The main difficulties include but are not limited to object rotation, confusion from false targets and c
Publikováno v:
Mathematical Problems in Engineering, Vol 2021 (2021)
Image clustering is a complex procedure, which is significantly affected by the choice of image representation. Most of the existing image clustering methods treat representation learning and clustering separately, which usually bring two problems. O