Sentence alignment, as one of the most active and fundamental tasks in the field of natural language processing (NLP), is usually realized in two categories of methods. One is traditional methods which are firstly pro...
详细信息
ISBN:
(纸本)9781450377607
Sentence alignment, as one of the most active and fundamental tasks in the field of natural language processing (NLP), is usually realized in two categories of methods. One is traditional methods which are firstly proposed, the other, which are adopted later, is based on the Neural Network method. Presently, under the limitation that the existing mainstream data corpora are mostly in the form of 1-to-1, the alignment models with relatively good performance mainly apply to the cases of 1-to-1 sentence alignment. However, under the circumstance that a sentence contains too much information, 1-to-N sentence alignment can actually have a better effect on sentence translation tasks, compared with the 1-to-1 form, since it is more flexible and can reduce the complexity of the original sentence. As a result, we attempt to exploit neural networks with relatively good performance in the cases of 1-to-1 to fit in the cases of 1-to-N. In this paper, a novel 1-N Bilingual word Embedding with Sentence Combination CNN Improved Framework (1-NBESCC) is proposed in order to align 1-to-N sentences more precisely. Experiments show that our proposed model performs as good as the traditional methods such as BLEUALIGN in 1-to-1 situation, but much better in 1-to-N situation.
Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on Image and Video Deblurring. In this challenge, we present the evaluation results...
详细信息
This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HS...
详细信息
The aim of this paper is to assess the impact of devices on Quality of Experience (QoE) of the user. As the types of video content viewed over handheld devices increases e.g. streaming video, it is important to evalua...
详细信息
The aim of this paper is to assess the impact of devices on Quality of Experience (QoE) of the user. As the types of video content viewed over handheld devices increases e.g. streaming video, it is important to evaluate the impact of the end device on video quality assessment. In this paper subjective tests were conducted with QCIF (176×144) videos over two devices - Personal Computer (PC) and mobile handset with 90 test conditions. The dataset was generated with a combination of parameters associated with the access network (block error rates and mean burst lengths), H.264 codec related parameter (sender bitrates) and content types. Subjects favoured PC test over handset test in almost all test scenarios. These studies should help in context-aware services in deciding the appropriate encoding parameters based on type of device being used to receive content.
The popular formulas of evaluating the similarity of digital watermarks have serious drawbacks: when the similarity degree is 1, the watermarks are not unique. This paper firstly analyzes the drawbacks in the popular ...
详细信息
Efficient linear separation algorithms are important for pattern classification applications. In this paper, an algorithm is developed to solve linear separation problems in n-dimensional space. Its convergence featur...
详细信息
Efficient linear separation algorithms are important for pattern classification applications. In this paper, an algorithm is developed to solve linear separation problems in n-dimensional space. Its convergence feature is proved. The proposed algorithm is proved to converge to a correct solution whenever the two sets are separable. The complexity of the proposed algorithm is analyzed, and experiments on both randomly generated examples and real application problems were carried out. While analysis shows that its time complexity is lower than SVM that needs computations for quadratic programming optimization, experiment results show that the developed algorithm is more efficient than the least-mean-square (LMS), and the Perceptron.
In Universal Mobile Telecommunication System (UMTS) Radio Link Control (RLC) losses severely affect the Quality of Service (QoS) due to high error probability. Therefore, for any video quality prediction model, it is ...
详细信息
In Universal Mobile Telecommunication System (UMTS) Radio Link Control (RLC) losses severely affect the Quality of Service (QoS) due to high error probability. Therefore, for any video quality prediction model, it is important to model the radio-link loss behaviour. In this paper we evaluate the impact of the radio access network on the end-to-end QoS for H.264 encoded video. In order to characterize the QoS level, a learning model based on Adaptive Neural Fuzzy Inference System (ANFIS) is proposed that takes into account the RLC loss models to predict the video quality in terms of the Mean Opinion Score (MOS). The RLC loss models considered are 2-state Markov models with variable mean burst lengths. The aim of the paper is two-fold. First, to find the impact of QoS parameters in both the physical and application layer on end-to-end video quality. Second, to propose a prediction model based on ANFIS to predict video quality over UMTS networks. ANFIS is well suited for video quality prediction over error prone and bandwidth restricted UMTS as it combines the advantages of neural networks and fuzzy systems. The ANFIS model is trained with a combination of application and physical layer parameters. The performance of the proposed model is validated with unseen dataset. These studies should help in the understanding of the impact of both the application and physical layer parameters on end-to-end video quality and in QoS control methods and adaptation.
The Quality of Service (QoS) of Universal Mobile Telecommunication System (UMTS) is severely affected by the losses occurring in Radio Link Control (RLC) due to high error probability. Therefore, for any video quality...
The Quality of Service (QoS) of Universal Mobile Telecommunication System (UMTS) is severely affected by the losses occurring in Radio Link Control (RLC) due to high error probability. Therefore, for any video quality prediction model, it is important to model the radio-link loss behaviour appropriately. In addition, video content has an impact on video quality under same network conditions. The aim of this paper is to present video quality prediction models for objective, non-intrusive prediction of H.264 encoded video for all content types combining parameters both in the physical and application layer over UMTS networks. In order to characterize the QoS level, a learning model based on Adaptive Neural Fuzzy Inference System (ANFIS) is proposed to predict the video quality in terms of the Mean Opinion Score (MOS). ANFIS is well suited for video quality prediction over error prone and bandwidth restricted UMTS as it combines the advantages of neural networks and fuzzy systems. The loss models considered are 2-state Markov models with variable Mean Burst Lengths (MBLs) depicting the various UMTS scenarios. The proposed model is trained with a combination of physical and application layer parameters and validated with unseen dataset. Preliminary results show that good prediction accuracy was obtained from the model. The work should help in the development of a reference-free video prediction model and Quality of Service (QoS) control methods for video over UMTS networks.
This paper presents a public mesh watermarking algorithm whereby the resultant watermarked image minus the original image is the watermark information. According to the addition property of the Fourier transform, a ch...
详细信息
Image classification is a challenging problem in organizing a large image database. However, an effective method for such an objective is still under investigation. This paper presents a method based on wavelet and in...
详细信息
Image classification is a challenging problem in organizing a large image database. However, an effective method for such an objective is still under investigation. This paper presents a method based on wavelet and independent analysis component (ICA) for image classification with adaptive processing of data structures. With wavelet, an image is decomposed into low frequency bands and high frequency bands. An image can be characterized by wavelet coefficients in the form of tree representation. While the histograms of low frequency wavelet bands are effective in characterizing images, the histograms of high frequency wavelet bands are similar for different images and therefore they cannot be directly used as features. We make use of ICA for feature extraction from high frequency bands to improve image classification. Two sets of features are used together to classify images using a structured neural network. In total, 2940 images generated from seven categories are used in experiments. Half of the images are used for training the neural network and the other images used for testing. The classification rate of the training set is 92%, and the classification rate of the test set reaches 89%. The experimental results show the effectiveness of the proposed method based on combining wavelet and ICA for image classification.
暂无评论