Zobrazeno 1 - 10
of 138
pro vyhledávání: '"Dong, Jingming"'
Autor:
Gao, Yu, Han, Zhitao, Zhai, Guangpeng, Song, Liguo, Dong, Jingming, Yang, Shaolong, Pan, Xinxiang
Publikováno v:
In Journal of the Taiwan Institute of Chemical Engineers April 2022 133
Autor:
Han, Zhitao, Li, Xiaodi, Wang, Xinxin, Gao, Yu, Yang, Shaolong, Song, Liguo, Dong, Jingming, Pan, Xinxiang
Publikováno v:
In Journal of Colloid And Interface Science 15 February 2022 608 Part 3:2718-2729
Autor:
Han, Zhihua1,2 (AUTHOR), Dong, Jingming3 (AUTHOR), Wu, Jianhong1 (AUTHOR), Bi, Chun1 (AUTHOR), Wang, Qiugeng1 (AUTHOR), Lin, Haodong1 (AUTHOR), Zhang, Lei4 (AUTHOR) lei.zhang2@shgh.cn, Wu, Xiaoming1 (AUTHOR) drwxm@263.net
Publikováno v:
Orthopaedic Surgery. Aug2023, Vol. 15 Issue 8, p2025-2032. 8p.
Publikováno v:
Jinming Dong, Iuri Frosio, Jan Kautz, Learning Adaptive Parameter Tuning for Image Processing, Proc. EI 2018, Image Processing: Algorithms and Systems XVI, Burlingame, USA, 28 Jan - 2 Feb 2018
The non-stationary nature of image characteristics calls for adaptive processing, based on the local image content. We propose a simple and flexible method to learn local tuning of parameters in adaptive image processing: we extract simple local feat
Externí odkaz:
http://arxiv.org/abs/1610.09414
We describe a system to detect objects in three-dimensional space using video and inertial sensors (accelerometer and gyrometer), ubiquitous in modern mobile platforms from phones to drones. Inertials afford the ability to impose class-specific scale
Externí odkaz:
http://arxiv.org/abs/1606.03968
Autor:
Du, Huan, Han, Zhitao, Wu, Xitian, Wang, Qimeng, Li, Chenglong, Gao, Yu, Yang, Shaolong, Song, Liguo, Dong, Jingming, Pan, Xinxiang
Publikováno v:
In Journal of Environmental Chemical Engineering August 2021 9(4)
Autor:
Zhai, Guangpeng, Han, Zhitao, Wu, Xitian, Du, Huan, Gao, Yu, Yang, Shaolong, Song, Liguo, Dong, Jingming, Pan, Xinxiang
Publikováno v:
In Journal of the Taiwan Institute of Chemical Engineers August 2021 125:132-140
We conduct an empirical study to test the ability of Convolutional Neural Networks (CNNs) to reduce the effects of nuisance transformations of the input data, such as location, scale and aspect ratio. We isolate factors by adopting a common convoluti
Externí odkaz:
http://arxiv.org/abs/1505.06795
Autor:
Dong, Jingming, Soatto, Stefano
We introduce a simple modification of local image descriptors, such as SIFT, based on pooling gradient orientations across different domain sizes, in addition to spatial locations. The resulting descriptor, which we call DSP-SIFT, outperforms other m
Externí odkaz:
http://arxiv.org/abs/1412.8556
We study the structure of representations, defined as approximations of minimal sufficient statistics that are maximal invariants to nuisance factors, for visual data subject to scaling and occlusion of line-of-sight. We derive analytical expressions
Externí odkaz:
http://arxiv.org/abs/1412.6607