This paper proposes to use a convolution kernel over parse tree to model syntactic structure information for pronoun resolution. Our study reveals that the syntactic structure features embedded in a parse tree are ver...
详细信息
This paper proposes to use a convolution kernel over parse tree to model syntactic structure information for pronoun resolution. Our study reveals that the syntactic structure features embedded in a parse tree are very effective for pronoun resolution and these features can be well captured by the context-sensitive convolution tree kernel. Evaluation on the ACE 2003 corpus shows that among all structured syntactic feature space, shortest path tree achieves the best performance. Then we incorporate more features into SPT, result shows that SPT can use successfully with normal features. Finally, we compare our system with other pronoun resolution systems, our results are outstanding in success rate than normal features and tree kernel-based method of Yang.
To solve the problem of sequence to sequence super resolution, a video sequence super resolution algorithm based on a frame of reference high resolution image is proposed in this paper. The algorithm is based on the f...
详细信息
To solve the problem of sequence to sequence super resolution, a video sequence super resolution algorithm based on a frame of reference high resolution image is proposed in this paper. The algorithm is based on the fact that in most cases, the vidicon device has dual mode: HR (High Resolution) still and LR (Low Resolution) video. In the algorithm, a HR still image acquired from the same scene is used as an example, the high frequency details of it are extracted and then motion compensated and reliability weighted for super resolution of the corresponding low resolution frames. The estimated HR frames are then constraint optimized under the Maximum A Posteriori (MAP) framework to improve its fidelity. Evaluated by several sequences, the proposed algorithm shows obvious performance improvements compared with the traditional bilinear interpolation and the MAP based static batch method. The average PSNR (Peak signal-to-Noise Ratio) of the reconstructed frames are improved by more than 2.4 dB.
Registration of the consecutive frames is quite essential in dynamic video super resolution. In this paper, a multi-scale least square affine-based block-match method is proposed. An index Dmv is defined to evaluate g...
详细信息
Registration of the consecutive frames is quite essential in dynamic video super resolution. In this paper, a multi-scale least square affine-based block-match method is proposed. An index Dmv is defined to evaluate global and local matching performances of the images. Then a multi-scale scheme is designed to adjust the block size automatically according to the motions between frames, which guaranteed well performances in both planar and un-planar regions. Different from the traditional block-match method, the affine-based least square estimation algorithm is introduced for registration of each pair of blocks. Convergence of the estimating process for different size of blocks is resolved by unification of the update step, which results in improvements in both estimating precision and speed. Finally, the proposed algorithm is evaluated in both the registration performance and its affects to the performance of the super resolution algorithm. Experimental results show that the proposed algorithm not only can provide more accurate motion estimation, when be applied to the Maximum A Posterior (MAP) based super resolution method, it shows obvious enhancement in both reconstruction performances and efficiencies.
Scheduling is one of the most well-known problems in both modern service science and service operational management. On the basis of quantum swarm evolutionary method, a new technique, immune quantum swarm optimizatio...
详细信息
Scheduling is one of the most well-known problems in both modern service science and service operational management. On the basis of quantum swarm evolutionary method, a new technique, immune quantum swarm optimization (IQSO) approach is proposed by redefining the immune operators, vaccinating operator and immune selecting operator, which has a powerful global exploration capability and its applications with permutation flowshop scheduling. The experimental results obtained from the proposed method on some benchmark instances show that it is very promising, compared to genetic algorithms and swarm intelligence methods.
The presented research addressed a novel visual attention model and watershed segmentation based approach of Regions of Interest (ROIs) extraction, which automatically extracts ROIs and copes with the watershed over-s...
详细信息
The image color recorded in a computer vision system depends on three factors: the physical content of the scene, the illumination on the scene, and the characteristics of the camera. The goal of computational color c...
详细信息
In this paper a new method for automatic word clustering is presented. We used this method for building n-gram language models for Persian continuous speech recognition (CSR) systems. In this method, each word is spec...
详细信息
In this paper, we formulate a speech enhancement problem under multiple hypotheses, assuming an indicator for the lens motor noise presence is availab.e in the time domain. This approach is largely based on an existin...
详细信息
In this paper, by using the cyclostationary properties of speech signal, a voice activity detection (VAD) algorithm based on cyclic cumulant is proposed. The proposed scheme employs the thirdorder cyclic cumulant of t...
详细信息
暂无评论