Key frame extraction based on sparsecoding can reduce the redundancy of continuous frames and concisely express the entire ***,how to develop a key frame extraction algorithm that can automatically extract a few fram...
详细信息
Key frame extraction based on sparsecoding can reduce the redundancy of continuous frames and concisely express the entire ***,how to develop a key frame extraction algorithm that can automatically extract a few frames with a low reconstruction error remains a *** this paper,we propose a novel model of structuredsparse-codingbased key frame extraction,wherein a nonconvex group log-regularizer is used with strong sparsity and a low reconstruction *** automatically extract key frames,a decomposition scheme is designed to separate the sparse coefficient matrix by *** rows enforced by the nonconvex group log-regularizer become zero or nonzero,leading to the learning of the structuredsparse coefficient *** solve the nonconvex problems due to the log-regularizer,the difference of convex algorithm(DCA)is employed to decompose the log-regularizer into the difference of two convex functions related to the l1 norm,which can be directly obtained through the proximal ***,an efficient structured sparse coding algorithm with the group log-regularizer for key frame extraction is developed,which can automatically extract a few frames directly from the video to represent the entire video with a low reconstruction *** results demonstrate that the proposed algorithm can extract more accurate key frames from most Sum Me videos compared to the stateof-the-art ***,the proposed algorithm can obtain a higher compression with a nearly 18% increase compared to sparse modeling representation selection(SMRS)and an 8% increase compared to SC-det on the VSUMM dataset.
sparsecoding can exploit the intrinsic sparsity of hyperspectral images (HSIs) by representing it as a group of sparse codes. This strategy has been shown to be effective for HSI denoising. However, how to effectivel...
详细信息
sparsecoding can exploit the intrinsic sparsity of hyperspectral images (HSIs) by representing it as a group of sparse codes. This strategy has been shown to be effective for HSI denoising. However, how to effectively exploit the structural information within the sparse codes (structured sparsity) has not been widely studied. In this paper, we propose a new method for HSI denoising, which uses structured sparse coding and intracluster filtering. First, due to the high spectral correlation, the HSI is represented as a group of sparse codes by projecting each spectral signature onto a given dictionary. Then, we cast the structured sparse coding into a covariance matrix estimation problem. A latent variable-based Bayesian framework is adopted to learn the covariance matrix, the sparse codes, and the noise level simultaneously from noisy observations. Although the considered strategy is able to perform denoising through accurately reconstructing spectral signatures, an inconsistent recovery of sparse codes may corrupt the spectral similarity in each spatial homogeneous cluster within the scene. To address this issue, an intracluster filtering scheme is further employed to restore the spectral similarity in each spatial cluster, which results in better denoising results. Our experimental results, conducted using both simulated and real HSIs, demonstrate that the proposed method outperforms several state-of-the-art denoising methods.
sparsecoding provides an excellent image prior for hyper-spectral images (HSIs) denoising. However, on one hand, it is challenging to capture the structure within each sparse code for improving the reconstruction acc...
详细信息
ISBN:
(纸本)9781509033324
sparsecoding provides an excellent image prior for hyper-spectral images (HSIs) denoising. However, on one hand, it is challenging to capture the structure within each sparse code for improving the reconstruction accuracy, on the other hand, the inconsistent recovery of the sparse codes corrupts the spectrum similarity in each homogeneous cluster of the HSI. To address these problems, we first propose a novel covariance matrix estimation based structured sparse coding method, where the sparse code matrix is modeled by a matrix normal distribution with a full covariance matrix. By estimating the covariance matrix with a latent variable based Bayesian framework, the data-dependent and noise-robust structure for each sparse code is learned from the noisy observation, with which the sparse codes are reconstructed accurately. Then, an intra-cluster filtering is employed to restore the spectrum similarity in each cluster. Experimental results demonstrate that the proposed method outperforms several state-of-the-art methods in HSIs denoising.
Robust exemplar extraction from the noisy sample set is one of the most important problems in pattern recognition. In this brief, we propose a novel approach for exemplar extraction through structuredsparse learning....
详细信息
Robust exemplar extraction from the noisy sample set is one of the most important problems in pattern recognition. In this brief, we propose a novel approach for exemplar extraction through structuredsparse learning. The new model accounts for not only the reconstruction capability and the sparsity, but also the diversity and robustness. To solve the optimization problem, we adopt the alternating directional method of multiplier technology to design an iterative algorithm. Finally, the effectiveness of the approach is demonstrated by experiments of various examples including traffic sign sequences.
We extend the scope of Wikification to novel words by relaxing two premises of Wikification: (i) we wikify without using the surface form of the word (ii) to a mixture ofWikipedia senses instead of a single sense. We ...
详细信息
ISBN:
(纸本)9783319126104;9783319126098
We extend the scope of Wikification to novel words by relaxing two premises of Wikification: (i) we wikify without using the surface form of the word (ii) to a mixture ofWikipedia senses instead of a single sense. We identify two types of "novel" words: words where the connection between their surface form and their meaning is broken (e. g., a misspelled word), and words where there is no meaning to connect to-the meaning itself is also novel. We propose a method capable of wikifying both types of novel words while also dealing with the inherently large-scale disambiguation problem. We show that the method can disambiguate between up to 1,000 Wikipedia senses, and it can explain words with novel meaning as a mixture of other, possibly related senses. This mixture representation compares favorably to the widely used bag of words representation.
In this paper, we aim to achieve robust and cost-effective room-level localization for the indoor mobile robot. It is unrealistic to obtain precise localization information from the sonar sensors because of the sparse...
详细信息
In this paper, we aim to achieve robust and cost-effective room-level localization for the indoor mobile robot. It is unrealistic to obtain precise localization information from the sonar sensors because of the sparseness and uncertainty. Our attempts show that the room-level localization can be achieved using sonar sensors by accumulating the sonar data to overcome the limitations of sensor performance. To this end, we formulate the room-level localization as a joint sparsecoding problem, which encourages the coding vectors to share the common room sparsity, but different locations. We systematically evaluate the performance of the different coding strategies on the collected sonar measurement data set.
A central goal in automatic music transcription is to detect individual note events in music recordings. An important variant is instrument-dependent music transcription where methods can use calibration data for the ...
详细信息
ISBN:
(纸本)9781538616321
A central goal in automatic music transcription is to detect individual note events in music recordings. An important variant is instrument-dependent music transcription where methods can use calibration data for the instruments in use. However, despite the additional information, results rarely exceed an f-measure of 80%. As a potential explanation, the transcription problem can be shown to be badly conditioned and thus relies on appropriate regularization. A recently proposed method employs a mixture of simple, convex regularizers (to stabilize the parameter estimation process) and more complex terms (to encourage more meaningful structure). In this paper, we present two extensions to this method. First, we integrate a computational loudness model to better differentiate real from spurious note detections. Second, we employ (Bidirectional) Long Short Term Memory networks to re-weight the likelihood of detected note constellations. Despite their simplicity, our two extensions lead to a drop of about 35% in note error rate compared to the state-of-the-art.
Learning adaptive dictionaries for sparsecoding has been the focus of latest research as it provides a promising way to maximize the efficiency of sparse representation. In particular, learning discriminative diction...
详细信息
Learning adaptive dictionaries for sparsecoding has been the focus of latest research as it provides a promising way to maximize the efficiency of sparse representation. In particular, learning discriminative dictionaries rather than reconstructive ones has demonstrated significantly improved performance in pattern recognition. In this paper, a powerful method is proposed for discriminative dictionary learning. During the dictionary learning process, we enhance the discriminability of sparse codes by promoting hierarchical group sparsity and reducing linear prediction error on sparse codes. With the employment of joint within-class collaborative hierarchical sparsity, our method is able to learn adaptive dictionaries from labeled data for classification, which encourage coefficients to be sparse at both group level and singleton level and thus enforce the separability of sparse codes. Benefiting from joint dictionary and classifier learning, the discriminability of sparse codes is further strengthened. An efficient alternating iterative scheme is presented to solve the proposed model. We applied our method to face recognition, object recognition and scene classification. Experimental results have demonstrated the excellent performance of our method in comparison with existing discriminative dictionary learning approaches. (C) 2015 Elsevier Inc. All rights reserved.
Small target detection in infrared video sequence is a challenging problem. In this paper, a collaborative structured sparse coding (SSC) model which incorporates the L-1,L-2 and L-2,L-1 regularization terms is propos...
详细信息
Small target detection in infrared video sequence is a challenging problem. In this paper, a collaborative structured sparse coding (SSC) model which incorporates the L-1,L-2 and L-2,L-1 regularization terms is proposed. The Alternating Direction Method of Multiplier (ADMM) is developed to solve this model. Further, online dictionary learning is embedded into the model and temporal information is incorporated to eliminate the clutters and noises. Extensive synthetic and real data experiments show that our method obtains better detection performance than baseline methods and state-of-art infrared-patch-image (IPI) model. (C) 2014 Elsevier B.V. All rights reserved.
Learning adaptive dictionaries for sparsecoding has been the focus of latest research as it provides a promising way to maximize the efficiency of sparse *** particular, learning discriminative dictionaries rather th...
详细信息
Learning adaptive dictionaries for sparsecoding has been the focus of latest research as it provides a promising way to maximize the efficiency of sparse *** particular, learning discriminative dictionaries rather than reconstructive ones has demonstrated significantly improved performance in pattern *** this paper, a powerful method is proposed for discriminative dictionary *** the dictionary learning process, we enhance the discriminability of sparse codes by promoting hierarchical group sparsity and reducing linear prediction error on sparse *** the employment of joint within-class collaborative hierarchical sparsity, our method is able to learn adaptive dictionaries from labeled data for classification, which encourage coefficients to be sparse at both group level and singleton level and thus enforce the separability of sparse *** from joint dictionary and classifier learning, the discriminability of sparse codes is further *** efficient alternating iterative scheme is presented to solve the proposed *** applied our method to face recognition, object recognition and scene *** results have demonstrated the excellent performance of our method in comparison with existing discriminative dictionary learning approaches.
暂无评论