Filter Results:
- Full text PDF available (4)
Publication Year
2010
2017
- This year (1)
- Last 5 years (17)
- Last 10 years (21)
Publication Type
Co-author
Journals and Conferences
Data Set Used
Learn More
- Ziheng Wang, Shangfei Wang, Qiang Ji
- 2013 IEEE Conference on Computer Vision and…
- 2013
Spatial-temporal relations among facial muscles carry crucial information about facial expressions yet have not been thoroughly exploited. One contributing factor for this is the limited ability of… (More)
- Ziheng Wang, Yongqiang Li, Shangfei Wang, Qiang Ji
- 2013 IEEE International Conference on Computer…
- 2013
In this paper we tackle the problem of facial action unit (AU) recognition by exploiting the complex semantic relationships among AUs, which carry crucial top-down information yet have not been… (More)
- Ziheng Wang, Qiang Ji
- 2015 IEEE Conference on Computer Vision and…
- 2015
Traditional data-driven classifier learning approaches become limited when the training data is inadequate either in quantity or quality. To address this issue, in this paper we propose to combine… (More)
- Yongmian Zhang, Yifan Zhang, Eran Swears, Natalia Larios, Ziheng Wang, Qiang Ji
- IEEE Transactions on Pattern Analysis and Machine…
- 2013
Complex activities typically consist of multiple primitive events happening in parallel or sequentially over a period of time. Understanding such activities requires recognizing not only each… (More)
- Siqi Nie, Ziheng Wang, Qiang Ji
- Computer Vision and Image Understanding
- 2015
Many computer vision applications involve modeling complex spatiotemporal patterns in high-dimensional motion data. Recently, restricted Boltzmann machines (RBMs) have been widely used to capture and… (More)
- Ziheng Wang, Tian Gao, Qiang Ji
- 2014 22nd International Conference on Pattern…
- 2014
Classifier learning is challenging when the training data is inadequate in either quantity or quality. Prior knowledge hence is important in such cases to improve the performance of classification.… (More)
- Ziheng Wang, Ryan M. Hope, Zuoguan Wang, Qiang Ji, Wayne D. Gray
- NeuroImage
- 2012
Most of the current EEG-based workload classifiers are subject-specific; that is, a new classifier is built and trained for each human subject. In this paper we introduce a cross-subject workload… (More)
- Ziheng Wang, Xiaoyang Wang, Qiang Ji
- 2014 22nd International Conference on Pattern…
- 2014
In many classification problems, there exists additional information which is available during training but not available during testing. In this paper we denote such information as hidden… (More)
- Yue Wu, Ziheng Wang, Qiang Ji
- 2014 IEEE Conference on Computer Vision and…
- 2014
Facial feature detection from facial images has attracted great attention in the field of computer vision. It is a nontrivial task since the appearance and shape of the face tend to change under… (More)
- Ziheng Wang, Xudong Xie
- ICIMCS
- 2010
In this paper, an efficient face recognition algorithm is proposed, which is robust to illumination, expression and occlusion. In our method, a human face image is considered as a multiplication of a… (More)