In this paper, we present a pose based approach for locating and recognizing human actions in videos. In our method, human poses are detected and represented based on deformable part model. To our knowledge, this is t...
详细信息
Considering the shortage of edge preservation and low direction-resolution for SAR image segmentation based on the conventional wavelet transform domain, a new segmentation method is proposed based on Gray-Level Coocc...
详细信息
Considering the shortage of edge preservation and low direction-resolution for SAR image segmentation based on the conventional wavelet transform domain, a new segmentation method is proposed based on Gray-Level Cooccurrence Probability (GLCP) features in the overcomplete Brushlet domain. This method compresses the redundant GLCP features extracted by the adaptive window Gabor filtering in different direction coefficient blocks using compressed sensing, then the Fuzzy C-Mean (FCM) clustering method is utilized to complete the clustering and obtain the segmentation result. The experiment results show that the new method has advantages in the edge preservation and direction extraction, and obtains better segmentation results with respect to other methods.
General object recognition and image understanding is recognized as a dramatic goal for computer vision and multimedia retrieval. In spite of the great efforts devoted in the last two decades, it still remains an open...
详细信息
General object recognition and image understanding is recognized as a dramatic goal for computer vision and multimedia retrieval. In spite of the great efforts devoted in the last two decades, it still remains an open problem. In this paper, we propose a selective attention-driven model for general image understanding, named GORIUM (general object recognition and image understanding model). The key idea of our model is to discover recurring visual objects by selective attention modeling and pairwise local invariant features matching on a large image set in an unsupervised manner. Towards this end, it can be formulated as a four-layer bottom-up model, i.e., salient region detection, object segmentation, automatic object discovering and visual dictionary construction. By exploiting multi-task learning methods to model visual saliency simultaneously with the bottom-up and top-down factors, the lowest layer can effectively detect salient objects in an image. The second layer exploits a simple yet effective learning approach to generate two complementary maps from several raw saliency maps, which then can be utilized to segment the salient objects precisely from a complex scene. For the third layer, we have also implemented an unsupervised approach to automatically discover general objects from large image set by pairwise matching with local invariant features. Afterwards, visual dictionary construction can be implemented by using many state-of-the-art algorithms and tools available nowadays.
Nonnegative matrix factorization (NMF) is an increasingly popular technique for data processing and analysis. For an incomplete data matrix, the weighted nonnegative matrix factorization (WNMF) is employed to decompos...
详细信息
Nonnegative matrix factorization (NMF) is an increasingly popular technique for data processing and analysis. For an incomplete data matrix, the weighted nonnegative matrix factorization (WNMF) is employed to decompose it. But the searching step size in WNMF is not optimal along the given searching direction. This paper studies the incomplete nonnegative matrix factorization (INMF) and proposes an accelerated algorithm. First, INMF is transformed into solving alternatively two nonnegative least squares (NNLS) problems. For each NNLS problem, the exact step size is chosen along the searching direction. Then, the complexity of NNLS problems is analyzed. Finally, experimental results show that the proposed method outperforms WNMF.
For least squares support vector machine (LSSVM) the lack of sparse, while the standard sparse algorithm exist a problem that it need to mark all of training data. We propose an active learning algorithm based on LSSV...
详细信息
Cloud computing focuses on supporting high scalable and high available parallel and distributed computing, based on the infrastructure built on top of large scale clusters which contain a large number of cheap PC serv...
详细信息
Decoding is a core process of the statistical machine translation, and determines the final results of it. In this paper, a decoding optimization for Chinese-English SMT with a dependent syntax language model was prop...
详细信息
We introduce synchronous tree adjoining grammars (TAG) into tree-to-string translation, which converts a source tree to a target string. Without reconstructing TAG derivations explicitly, our rule extraction algorithm...
详细信息
As one of the important artistic styles of portrait, sketch portrait has wide applications for both digital entertainment and law enforcement. In this paper, an automatic face sketch generation approach is presented b...
详细信息
暂无评论