Xiangsheng Huang

Dr. Xiangsheng Huang


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 August 2012 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
XHXiangsheng Huang
Xiangsheng Huang
ZLZhen Lei
Zhen Lei
MFMingyu Fan
Mingyu Fan
XWXiao Wang
Xiao Wang
SLStan Z. Li
Stan Z. Li
Face recognition is confronted with situations in which face images are captured in various modalities, such as the visual modality, the near infrared modality, and the sketch modality. This is known as heterogeneous face recognition. To solve this problem, we propose a new method called discriminative spectral regression (DSR). The DSR maps heterogeneous face images into a common discriminative subspace in which robust classification can be achieved. In the proposed method, the subspace learning problem is transformed into a least squares problem. Different mappings should map heterogeneous images from the same class close to each other, while images from different classes should be separated as far as possible. To realize this, we introduce two novel regularization terms, which reflect the category relationships among data, into the least squares approach. Experiments conducted on two heterogeneous face databases validate the superiority of the proposed method over the previous methods.

2 June 2020 in International Journal of Machine Learning and Cybernetics
Verified
Journal Article
Open access
PDF file
WDWeili Ding
Weili Ding
BHBo Hu
Bo Hu
HLHan Liu
Han Liu
XWXinming Wang
Xinming Wang
XHXiangsheng Huang
Xiangsheng Huang
The use of skeleton data for human posture recognition is a key research topic in the human-computer interaction field. To improve the accuracy of human posture recognition, a new algorithm based on multiple features and rule learning is proposed in this paper. Firstly, a 219-dimensional vector that includes angle features and distance features is defined. Specifically, the angle and distance features are defined in terms of the local relationship between joints and the global spatial location of joints. Then, during human posture classification, the rule learning method is used together with the Bagging and random subspace methods to create different samples and features for improved classification performance of sub-classifiers for different samples. Finally, the performance of our proposed algorithm is evaluated on four human posture datasets. The experimental results show that our algorithm can recognize many kinds of human postures effectively, and the results obtained by the rule-based learning method are of higher interpretability than those by traditional machine learning methods and CNNs.

28 March 2013 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
XHXiangsheng Huang
Xiangsheng Huang
XCXinghao Chen
Xinghao Chen
TTTao Tang
Tao Tang
ZHZiling Huang
Ziling Huang
We present a 3D reconstruction system to realize fast 3D modeling using a vision sensor. The system can automatically detect the face region and obtain the depth data as well as color image data once a person appears in front of the sensor. When the user rotates his head around, the system will track the pose and integrate the new data incrementally to obtain a complete model of the personal head quickly. In the system, iterative closest point (ICP) algorithm is first used to track the pose of the head, and then a volumetric integration method is used to fuse all the data obtained. Third, ray casting algorithm extracts the final vertices of the model, and finally marching cubes algorithm generates the polygonal mesh of the reconstructed face model for displaying. During the process, we also make improvements to speed up the system for human face reconstruction. The system is very convenient for real-world applications, since it can run very quickly and be easily operated.

11 November 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
XYXiao Yang
Xiao Yang
XHXiangsheng Huang
Xiangsheng Huang
HLHaihao Lin
Haihao Lin
WZWeibang Zhou
Weibang Zhou
SZSimin Zeng
Simin Zeng
Automatic corrections offer direct policy supervision during assisted robotic reinforcement learning. We evaluate whether regressing on these actions improves learning beyond their use in replay. Uniform corrective distillation (UCD) adds actor regression on initial demonstrations and online corrections to an AutoSERL-derived soft actor–critic system. We compare four objectives on simulated spatula hanging and drawer opening with fixed and randomized starts and extend the randomized UCD–baseline comparison to five training seeds per method. Training stops when the shared process-success criterion is met or the budget is exhausted; each returned model receives 100 fresh test episodes with task assistance disabled. Across five seeds, UCD averaged 100.0% success on spatula and 91.2% on drawer, versus baseline means of 71.6% and 79.8%, with all five spatula UCD models achieving 100/100 successes. A separate comparison matched auxiliary batch size and update frequency; correction-inclusive supervision exceeded demonstration-only supervision in all six task–seed pairs. These results support direct actor regression for reusing automatic corrections under the evaluated stopping protocol.