Biyun Sheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Biyun Sheng has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Changyin Sun
Southeast University, Nanjing, China
2 shared publications - Chunhua Shen
Zhejiang University
2 shared publications - Guosheng Lin
Nanyang technological university, Singapore, Singapore
2 shared publications - Jun Li
School of Automation, Southeast University, Nanjing 210096, China
2 shared publications Wankou Yang
Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, China
2 shared publicationsChangyin Sun
Southeast University
1 shared publication
Latest Publications
- 8 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (8) , 1788-1797
Crowd Counting via Weighted VLAD on a Dense Attribute Feature Map
Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power of image representation is still an open problem. Conventional holistic features used in crowd counting often fail to capture semantic attributes and spatial cues of the image. In this paper, we propose integrating semantic information into learning locality-aware feature (LAF) sets for accurate crowd counting. First, with the help of a convolutional neural network, the original pixel space is mapped onto a dense attribute feature map, where each dimension of the pixelwise feature indicates the probabilistic strength of a certain semantic class. Then, LAF built on the idea of spatial pyramids on neighboring patches is proposed to explore more spatial context and local information. Finally, the traditional vector of locally aggregated descriptor (VLAD) encoding method is extended to a more generalized form weighted-VLAD (W-VLAD) in which diverse coefficient weights are taken into consideration. Experimental results validate the effectiveness of our presented method.
- 8 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (8) , 1788-1797
Crowd Counting via Weighted VLAD on a Dense Attribute Feature Map
Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power of image representation is still an open problem. Conventional holistic features used in crowd counting often fail to capture semantic attributes and spatial cues of the image. In this paper, we propose integrating semantic information into learning locality-aware feature (LAF) sets for accurate crowd counting. First, with the help of a convolutional neural network, the original pixel space is mapped onto a dense attribute feature map, where each dimension of the pixelwise feature indicates the probabilistic strength of a certain semantic class. Then, LAF built on the idea of spatial pyramids on neighboring patches is proposed to explore more spatial context and local information. Finally, the traditional vector of locally aggregated descriptor (VLAD) encoding method is extended to a more generalized form weighted-VLAD (W-VLAD) in which diverse coefficient weights are taken into consideration. Experimental results validate the effectiveness of our presented method.
- Open Access
Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps
Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power of image representation is still an open problem. Conventional holistic features used in crowd counting often fail to capture semantic attributes and spatial cues of the image. In this paper, we propose integrating semantic information into learning locality-aware feature sets for accurate crowd counting. First, with the help of convolutional neural network (CNN), the original pixel space is mapped onto a dense attribute feature map, where each dimension of the pixel-wise feature indicates the probabilistic strength of a certain semantic class. Then, locality-aware features (LAF) built on the idea of spatial pyramids on neighboring patches are proposed to explore more spatial context and local information. Finally, the traditional VLAD encoding method is extended to a more generalized form in which diverse coefficient weights are taken into consideration. Experimental results validate the effectiveness of our presented method.
Open AccessCrowd Counting via Weighted VLAD on Dense Attribute Feature Maps
Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power of image representation is still an open problem. Conventional holistic features used in crowd counting often fail to capture semantic attributes and spatial cues of the image. In this paper, we propose integrating semantic information into learning locality-aware feature sets for accurate crowd counting. First, with the help of convolutional neural network (CNN), the original pixel space is mapped onto a dense attribute feature map, where each dimension of the pixel-wise feature indicates the probabilistic strength of a certain semantic class. Then, locality-aware features (LAF) built on the idea of spatial pyramids on neighboring patches are proposed to explore more spatial context and local information. Finally, the traditional VLAD encoding method is extended to a more generalized form in which diverse coefficient weights are taken into consideration. Experimental results validate the effectiveness of our presented method.
- 22 October 2015
- Published by Springer Nature
- p. 145-153
Assigning PLS Based Descriptors by SVM in Action Recognition
- 22 October 2015
- Published by Springer Nature
- p. 145-153
Assigning PLS Based Descriptors by SVM in Action Recognition