Zobrazeno 1 - 10
of 428
pro vyhledávání: '"Hongxun Yao"'
Publikováno v:
Sensors, Vol 23, Iss 9, p 4425 (2023)
Hybrid models which combine the convolution and transformer model achieve impressive performance on human pose estimation. However, the existing hybrid models on human pose estimation, which typically stack self-attention modules after convolution, a
Externí odkaz:
https://doaj.org/article/41f88e39899a4627bda0eebebcb01c00
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2020, Iss 1, Pp 1-13 (2020)
Abstract We present a novel approach to non-rigid object tracking in this paper by deriving an adaptive data-driven kernel. In contrast with conventional kernel-based trackers which suffer from the constancy of kernel shape as well as scale and orien
Externí odkaz:
https://doaj.org/article/e7ba36df0829422e93028ae7a723248b
Publikováno v:
Agriculture, Vol 12, Iss 6, p 892 (2022)
Yield prediction is of great significance in agricultural production. Remote sensing technology based on unmanned aerial vehicles (UAVs) offers the capacity of non-intrusive crop yield prediction with low cost and high throughput. In this study, a wi
Externí odkaz:
https://doaj.org/article/6587183cef4047598f3d3f17ae5124dd
Publikováno v:
Complexity, Vol 2019 (2019)
In this paper, we propose a novel deep model for unbalanced distribution Character Recognition by employing focal loss based connectionist temporal classification (CTC) function. Previous works utilize Traditional CTC to compute prediction losses. Ho
Externí odkaz:
https://doaj.org/article/8fc834f8bc5c4bb5ab5c93873dee3364
Publikováno v:
IET Computer Vision, Vol 9, Iss 5, Pp 691-698 (2015)
In this study, the authors propose a collaborative composition model for automatically recommending suitable positions and poses in the scene of photography taken by amateurs. By analysing aesthetic‐aware features, the authors' strategy jointly tak
Externí odkaz:
https://doaj.org/article/37e3587504ab4277ae86a969ab56ac5c
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2010 (2010)
We propose a novel feature, local histogram of figure/ground segmentations, for robust and efficient background subtraction (BGS) in dynamic scenes (e.g., waving trees, ripples in water, illumination changes, camera jitters, etc.). We represent each
Externí odkaz:
https://doaj.org/article/6a95883abc994709a92be6f0eb0e5180
Publikováno v:
International Journal of Computer Vision. 131:1566-1583
Autor:
Dilin Liu, Hongxun Yao
Publikováno v:
Multimedia Tools and Applications.
Publikováno v:
Multimedia Tools and Applications.
Publikováno v:
Multimedia Tools and Applications.