Entity

Time filter

Source Type


Gu K.,Shanghai JiaoTong University | Gu K.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | Zhai G.,Shanghai JiaoTong University | Zhai G.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | And 5 more authors.
Proceedings - IEEE International Conference on Multimedia and Expo | Year: 2013

In the research of image quality assessment (IQA), no-reference approaches are usually thought of as a big challenge since none of original image information is available. To tackle this problem, we propose a new no-reference image quality metric through combining two recently proposed reduced-reference IQA models, namely the free energy based distortion metric (FEDM) and the structural degradation model (SDM). In this work, it will be shown that there exists an approximate linear relationship between the original image information of the free energy feature and the structural degradation information. Based on this observation and the application of support vector machine (SVM) that is widely used in the current study of IQA, our newly developed No-reference Free energy and Structural degradation based Distortion Metric (NFSDM) is found to alleviate the dependance of original images, and has achieved remarkably well prediction accuracy, outperforming the most two full-reference IQA approaches PSNR/SSIM and several mainstream no-reference image quality metrics. © 2013 IEEE. Source


Wang J.,Shanghai JiaoTong University | Wang J.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | Wu X.,McMaster University | Sun J.,Shanghai JiaoTong University | And 3 more authors.
IEEE Transactions on Information Theory | Year: 2014

We study the problem of two-stage sequential coding (TSSC), which is an extension of sequential coding of correlated sources. Let X and Y be dependent random variables. The network contains two encoders and two decoders: 1) a Y encoder with input Y ; 2) an X encoder with inputs X and Y ; 3) a Y decoder that reconstructs Y ; and 4) an X decoder that reconstructs X. The first stage is traditional sequential coding, where the Y encoder describes Y to both the X decoder and Y decoder, and the X encoder describes X and Y to the X decoder. At the second stage, the Y encoder refines the description of Y , and the X encoder refines the description of X. The TSSC model is a theoretical abstraction of scalable video coding; here, Y and X represent successive frames of a video sequence, and the two stages together give an embedded description that allows the video to be decoded at two distinct rates. We give an inner bound on the rate distortion region for this TSSC model. The tight bound on the rate distortion region is derived when Y must be reconstructed losslessly (in the usual Shannon sense) in the second stage. We also study the minimum total rate of the TSSC model and show that the minimum total rate of one-stage sequential coding cannot be achieved at both stages for jointly Gaussian sources. This theoretical result can shed light on the rate-distortion performance behavior of scalable video coding widely noted by practitioners. © 2014 IEEE. Source


Li N.,Shanghai JiaoTong University | Li N.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | Xu Y.,Shanghai JiaoTong University | Xu Y.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | And 2 more authors.
2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010 | Year: 2010

Gait recognition has already achieved satisfactory performance on small databases under ideal conditions. Most of the existing approaches represent gait pattern using a locomotion model or statistic model of human silhouette. However, it is still a challenging task to conduct human gait identification under variations of clothing and carrying condition in real scenes. In this paper, an adaptive part-based feature selection method is proposed to filter out interference feature blocks and a matching procedure is performed to identify the correct subject. Compared with the state-of-the-art methods on a large standard dataset, the proposed method shows an encouraging computational complexity reduction and performance improvement in identification rates. © 2010 IEEE. Source


Gu K.,Shanghai JiaoTong University | Gu K.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | Zhai G.,Shanghai JiaoTong University | Zhai G.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | And 4 more authors.
Proceedings - IEEE International Symposium on Circuits and Systems | Year: 2013

Image quality assessment (IQA) is an important research area in image processing. Reduced-reference (RR) IQA methods contained therein mainly aim to estimate image quality degradations with partial information about the reference image. Following the remarkable achievement of SSIM, structural information has been recognized as one key factor, and has aroused many image quality metrics so far. In this paper, we design a structural degradation model (SDM). Then, the quality score of an image is defined as a nonlinear combination, or SVM based integration, of distance between the structural degradation information of the original and distorted images. Accordingly, a new RR IQA approach using the SDM model is exploited. Experimental results on LIVE database are provided to justify the superior prediction accuracy performance of the proposed method as compared to three significant image quality metrics, PSNR, SSIM and FEDM. © 2013 IEEE. Source


Gong M.,Institute of Image Communication and Information Processing | Gong M.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | Xu Y.,Institute of Image Communication and Information Processing | Xu Y.,Shanghai Key Laboratory of Digital Media Processing and Transmissions | And 4 more authors.
Proceedings - 2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011 | Year: 2011

Gait recognition under variations of clothing and carrying condition is still a challenging task. In this paper, we present a gait identification method via sparse representation. We formulate the recognition problem as finding the coefficients of linear combination of the training samples plus an error term and discuss sparse signal representation theory that offers the solution to this problem. Based on the sparse representation computed by l1-minimization, we define a new distance metric to choose non-polluted area and propose a method for gait identification. Compared with the state-of-the-art methods on a large dataset, the proposed method achieves significant performance improvement in identification rates and it shows robustness to variations. © 2011 IEEE. Source

Discover hidden collaborations