Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Xiaohui Shen"'
Publikováno v:
The International Journal of Advanced Manufacturing Technology. 120:5673-5685
Autor:
Huiting Wang, Xiaohui Shen
Publikováno v:
The International Journal of Advanced Manufacturing Technology. 114:829-839
A novel method named hydrodynamic deep drawing process utilizing a combined floating and static die cavity (HDDC) was proposed in this research, in order to depress wrinkling during hydrodynamic deep drawing process to form a conical cup with higher
Autor:
Radomir Mech, Jianming Zhang, Minh Hoai, Zijun Wei, Boyu Wang, Xiaohui Shen, Dimitris Samaras, Zhe Lin
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 43:1009-1021
Detecting segments of interest from videos is a common problem for many applications. And yet it is a challenging problem as it often requires not only knowledge of individual target segments, but also contextual understanding of the entire video and
Publikováno v:
IEEE Transactions on Systems, Man, and Cybernetics: Systems. 50:707-716
Power demand side management (DSM) regulations stipulate that electric power grid enterprises of cities and provinces must complete their target of power saving through efficient power plant (EPP) programs. This investigation studies power DSM and es
Publikováno v:
International Journal of Computer Vision. 126:1084-1102
We aim to model the top-down attention of a convolutional neural network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation Bac
Autor:
Xiaohui Shen, Mehrnoosh Sameki, Radomir Mech, Stan Sclaroff, Zhe Lin, Brian Price, Shugao Ma, Jianming Zhang, Margrit Betke
Publikováno v:
CVPR
We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items
Autor:
Jianchao Yang, Shuicheng Yan, Chunyan Xu, Jinhui Tang, Xiaodan Liang, Liang Lin, Xiaohui Shen
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 39:115-127
In this work, we address the human parsing task with a novel Contextualized Convolutional Neural Network (Co-CNN) architecture, which well integrates the cross-layer context, global image-level context, semantic edge context, within-super-pixel conte
Autor:
Ding Liu, Yu Cheng, Xiaohui Shen, Chen Fang, Pan Zhou, Yifan Jiang, Jianchao Yang, Zhangyang Wang, Xinyu Gong
Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1c517bcc236be77e3d9e8c67b9e169e
http://arxiv.org/abs/1906.06972
http://arxiv.org/abs/1906.06972
Publikováno v:
IEEE Transactions on Image Processing. 24:3321-3331
In this paper, we propose a novel adaptive metric learning algorithm (AML) for visual saliency detection. A key observation is that the saliency of a superpixel can be estimated by the distance from the most certain foreground and background seeds. I
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 40(12)
Instance-level object segmentation is an important yet under-explored task. The few existing studies are almost all based on region proposal methods to extract candidate segments and then utilize object classification to produce final results. Noneth