Results 1-20 of 90
 | 
会议论文
Wei, Yingli; Wang, Wenmin; Wang, Ronggang
2015 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2015
2015
[ABSTRACT] A key development in the design of visual object recognition systems is the combination of multiple features. In recent years, various popular opti...
[KEYWORDS] 
会议论文
Huang, Ying; Wang, Wenmin; Wang, Ronggang
40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
2015
[ABSTRACT] Many successful systems for scene recognition transform low-level descriptors into complex representations. This process consists of the two steps:...
[KEYWORDS] 
会议论文
Zhang, Jianlong; Wang, Wenmin; Wang, Ronggang; Chen, Qinshui
2014
[ABSTRACT] Web technology provides a relatively easy way to generate contents for us to recognize the world, and with the development of stereoscopic display ...
[KEYWORDS] web; stereoscopic; browser; render; matrix
会议论文
Yang, Jun; Li, Ge; Wang, Wenmin; Wang, Ronggang
23rd International Conference on Pattern Recognition (ICPR)
2016
[ABSTRACT] The performance of an object detection system relies heavily on two components: an object model to capture the compositional relationship among the...
[KEYWORDS] OBJECT DETECTION
会议论文
Yao, Kaili; Wang, Ronggang; Wang, Zhenyu; Wang, Wenmin; Gao, Wen
2nd IEEE International Conference on Multimedia Big Data (BigMM)
2016
[ABSTRACT] The emerging ultra-HD video content and the latest generation video coding standards such as HEVC and AVS2 involve significant computational comple...
[KEYWORDS] Inverse Transform; Inverse Discrete Cosine Transform; Video Compression; AVS2; ALGORITHM
会议论文
Zheng, Zi'Ou; Wang, Wenmin; Wang, Ronggang
Visual Communications and Image Processing, VCIP 2015
2015
[ABSTRACT] Object retrieval in the large-scale image corpus is an appealing, yet challenging task. Most of existing frameworks are based on bag-of-visual-word...
[KEYWORDS] 
会议论文
Zhen, Mingmin; Wang, Wenmin; Wang, Ronggang
Visual Communications and Image Processing, VCIP 2015
2015
[ABSTRACT] In recent yeas, VLAD has been used to represent an image effectively and efficiently by just a few bytes in large-scale image retrieval. In spite o...
[KEYWORDS] 
会议论文
Wang, Jinzhuo; Wang, Wenmin; Wang, Ronggang; Gao, Wen
IEEE International Conference on Image Processing, ICIP 2015
2015
[ABSTRACT] This paper proposes to employ deep learning model to encode local descriptors for image classification. Previous works using deep architectures to ...
[KEYWORDS] 
会议论文
Zhang, Xinxin; Wang, Ronggang; Tian, Yonghong; Wang, Wenmin; Gao, Wen
2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
2015
[ABSTRACT] In this paper, we propose a robust method to remove motion blur from a single photograph. We find that an inaccurate kernel and an unreliable final...
[KEYWORDS] Motion blur; deblurring; kernel estimation; image reconstruction
会议论文
Zhen, Mingmin; Wang, Wenmin; Wang, Ronggang
2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
2015
[ABSTRACT] The feature coding algorithm, "Vector of Locally Aggregated Descriptors (VLAD)", can be used effectively for large scale object instance ...
[KEYWORDS] Image classification; Feature coding; Image retrieval; Image representation
会议论文
Li, Chenxia; Wang, Ronggang; Wang, Wenmin; Duan, Lingyu; Gao, Wen
2013
[ABSTRACT] View synthesis technique is important for multi-viewpoint 3D video applications. In our technical investigation, we find that some of the current v...
[KEYWORDS] 
会议论文
Tang, Chuanxin; Wang, Ronggang; Wang, Wenmin; Gao, Wen
2015
[ABSTRACT] In this paper, a new frame interpolation method with pixel-level motion vector field (MVF) is proposed. Given that existing methods cannot handle o...
[KEYWORDS] 
会议论文
Liu, Zhongxin; Wang, Wenmin; Wang, Ronggang
2014
[ABSTRACT] A lot of manifold learning algorithms have been developed, which are used to learn a low dimensional model on a manifold representing large numbers...
[KEYWORDS] 
会议论文
Chen, Qinshui; Wang, Wenmin; Wang, Ronggang; Zhang, Jianlong; Liu, Zhongxin
2014
[ABSTRACT] With the stereoscopic technology gradually maturing, realistic 3D devices are more and more popular. However, how to adapt current Web technologies...
[KEYWORDS] 
会议论文
Zhu, Chunbiao; Li, Ge; Wang, Wenmin; Wang, Ronggang
IEEE 3rd International Conference on Multimedia Big Data (BigMM)
2017
[ABSTRACT] Detecting salient objects with complex backgrounds is still a challenging problem. Under the background having similar colors with complex patterns...
[KEYWORDS] Salient object detection; Depth information; Center-bias; Luminance map; VISUAL-ATTENTION; REGION DETECTION; MODEL
会议论文
Song, Hongmeng; Wang, Wenmin; Wang, Jinzhuo; Wang, Ronggang
IEEE 3rd International Conference on Multimedia Big Data (BigMM)
2017
[ABSTRACT] Conventional pedestrian detection methods construct models based on hand-crafted features or deep learning. They are powerful but limited due to fi...
[KEYWORDS] Pedestrian Detection; Collaborative Deep Networks; Fully-Connected Network; Resampling Process; Collaborative Learning
会议论文
Han, Liang; Wang, Wenmin; Fan, Mengdi; Wang, Ronggang
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
2017
[ABSTRACT] Cross-modal retrieval, which aims to solve the problem that the query and the retrieved results are from different modality, becomes more and more ...
[KEYWORDS] Cross-modal retrieval; Fisher Vector; deep CNN image features; cross-modality matchin
会议论文
Huang, Jingjia; Li, Ge; Li, Nannan; Wang, Ronggang; Wang, Wenmin
17th International Conference on Computer Analysis of Images and Patterns, CAIP 2017
2017
[ABSTRACT] In the field of activity recognition, violence detection is one of the most challenging tasks due to the variety of action patterns and the lack of...
[KEYWORDS] 
会议论文
Li, Hao; Fan, Kui; Wang, Ronggang; Li, Ge; Wang, Wenmin
2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
2018
[ABSTRACT] Merge prediction is a practical inter-technique in HEVC, which can significantly improve the coding efficiency, especially for homogeneous regions ...
[KEYWORDS] 
会议论文
Zhang, Yiwei; Li, Ge; Guo, Xiaoqiang; Wang, Wenmin; Wang, Ronggang
18th Pacific-Rim Conference on Multimedia, PCM 2017
2018
[ABSTRACT] In this paper, we propose an effective and robust method SPOS (Sparsity Prior and Outlier Suppression) for blurry image restoration. First, we comb...
[KEYWORDS] 
Results 1-20 of 90