Search

For the rate control of H. 264/AVC, one of the most important things is to get the statistics of the current frame accurately. To achieve this, a novel adaptive coding characteristics prediction scheme is presented to improve the accuracy of R-D modeling, by exploiting spatio-temporal correlations. With the proposed prediction scheme, we present a novel rate function and a linear distortion model, and then deduce a simple close-form solution to the problem of optimum bit allocation, just in a TMN-8-alike way. Extensive experiments show that improvements with gains up to 0.92 dB per frame over JVT-G012, the current standardized rate control scheme, are achieved by the proposed scheme for a variety of test sequences with less demanding bandwidth. Index Terms--H.264/AVC, optimum bit allocation, rate control, rate-distortion optimization.

Invariant features extraction is important for object detection. Affine-SIFT (ASIFT) [J.M. Morel and G. Yu, ASIFT: A new framework for fully affine invariant image comparison, SIAM J. Imaging Sci. 2(2) (2009)] has been proved to be fully affine-invariant. However, the high cost of memory and query time hampers its application in large-scale object detection tasks. In this paper, we present a novel algorithm for mining concise and distinctive invariant features called affine-stable characteristics (ASC). Two new notions, global stability and local stability, are introduced to calculate the robustness of each feature from two mutually complementary aspects. Furthermore, to make these stable characteristics more distinctive, spatial information taken from several representative scales is encoded in a concise method. Experiments show that the robustness of our ASC is comparable with ASIFT, while the cost of memory can be reduced significantly to only 5%. Moreover, compared with the traditional SIFT method [D. Lowe, Distinctive image features from scale invariant keypoints, Int. J. Comput. Vis. 60(2) (2004), pp. 91–110], the accuracy of object detection can be improved 38.6% by our ASC using similar amount of features. [ABSTRACT FROM AUTHOR]

Realistic human action recognition in videos has been a useful yet challenging task. Video shots of same actions may present huge intra-class variations in terms of visual appearance, kinetic patterns, video shooting, and editing styles. Heterogeneous feature representations of videos pose another challenge on how to effectively handle the redundancy, complementariness and disagreement in these features. This paper proposes a localized multiple kernel learning (L-MKL) algorithm to tackle the issues above. L-MKL integrates the localized classifier ensemble learning and multiple kernel learning in a unified framework to leverage the strengths of both. The basis of L-MKL is to build multiple kernel classifiers on diverse features at subspace localities of heterogeneous representations. L-MKL integrates the discriminability of complementary features locally and enables localized MKL classifiers to deliver better performance in its own region of expertise. Specifically, L-MKL develops a locality gating model to partition the input space of heterogeneous representations to a set of localities of simpler data structure. Each locality then learns its localized optimal combination of Mercer kernels of heterogeneous features. Finally, the gating model coordinates the localized multiple kernel classifiers globally to perform action recognition. Experiments on two datasets show that the proposed approach delivers promising performance. [ABSTRACT FROM AUTHOR]

Abstract: Mobile visual search is a new class of applications that use images taken by camera phone to initiate search queries. It is a very challenging task mainly because of image affine transformations caused by viewpoints changes, and motion blur due to hand tremble. These problems are unavoidable in mobile visual search and often result in low recall. Query expansion is an effective strategy for recall improvement, but existing methods are highly memory and time consuming, and often involve lots of redundant features. Integrating robust local patch mining and geometric parameter coding, this paper proposes an accurate offline query expansion method for large-scale mobile visual search. Concretely, a novel criterion is presented for robust patch evaluation and mining. Then multiple representative features are extracted from these selected local patches to deal with viewpoint changes. Moreover, the geometric parameter of each representative viewpoint is also recorded, to support fast and accurate feature matching. Experimental results on several well-known datasets and a large image set (1M) have demonstrated the effectiveness and efficiency of our method, especially its high robustness to viewpoint changes. The proposed approach can also be well generalized to other multimedia content analysis tasks. [Copyright &y& Elsevier]

Abstract: Total variation (TV) minimization algorithms are often used to recover sparse signals or images in the compressive sensing (CS). But the use of TV solvers often suffers from undesirable staircase effect. To reduce this effect, this paper presents an improved TV minimization method for block-based CS by intra-prediction. The new method conducts intra-prediction block by block in the CS reconstruction process and generates a residual for the image block being decoded in the CS measurement domain. The gradient of the residual is sparser than that of the image itself, which can lead to better reconstruction quality in CS by TV regularization. The staircase effect can also be eliminated due to effective reconstruction of the residual. Furthermore, to suppress blocking artifacts caused by intra-prediction, an efficient adaptive in-loop deblocking filter was designed for post-processing during the CS reconstruction process. Experiments show competitive performances of the proposed hybrid method in comparison with state-of-the-art TV models for CS with respect to peak signal-to-noise ratio and the subjective visual quality. [Copyright &y& Elsevier]