With the development of Internet big data, how people obtain a large amount of news text information and automatically obtain the information they want from the text information is an urgent task. In order to structure and analyze a large amount of Chinese text information on the Internet, this paper proposes an entity extraction method based on the BERT pre-training model and BiLSTM with the Attention Mechanism. Aiming at the problem that the BiLSTM model can only obtain feature information at the sentence context level, but cannot obtain local feature information. In this paper, based on the BiLSTM model, a BERT feature extraction model is added to obtain word vectors containing contextual semantic information, thereby capturing global and local information. At the same time, an Attention Mechanism is added to improve the effect of the model. The model was trained on the 2018 Football World Cup dataset corpus, and it was verified that the precision, F1 value and recall rate of the model have significantly improved performance on the dataset.
KEYWORDS: Image compression, Volume rendering, Video compression, Video coding, Video, Motion measurement, Computer programming, Quantization, Optical flow, Radio over Fiber
Criticality is a measure of the difficulty of video compression. Image sequences with high criticality are required for the
evaluation of video compression algorithms. The selected test sequences are usually determined by experts from large
amounts of material,which is labor-intensive and subjective. In order to solve this problem, a test sequence selection
algorithm for video criticality evaluation is proposed in this paper. Based on basic principles of video coding, four types of
metrics including texture map variance, AC energy, motion vector difference and motion angle entropy are selected in this
paper. The least squares method is applied to fit the parameters of these four types of metrics to their corresponding
criticality values for multiple resolution image sequences, and the fitting results are verified by experiments to effectively
select the test sequences.
This paper presents a Belief Propagation (BP) stereo matching algorithm using ground control points. The proposed
algorithm combines local and global stereo methods, which first utilizes local stereo method to obtain an initial disparity
map, then the ground control points are selected from the initial disparity and used on belief propagation algorithm for
global stereo matching. Since using ground control points, the proposed algorithm improves BP algorithm in
convergence speed. Moreover, this paper proposes a color constraint voting method to optimize the disparity in postprocessing. Experimental results show that the proposed algorithm shares low computational complexity but high
matching accuracy.
In this paper, we propose a stereo matching approach using belief propagation for video disparity estimation by establishing a novel spatiotemporal belief propagation model. The proposed model extends 2D belief propagation algorithm to 3D mode by propagating the belief of preceding frame to the following frame. Additionally, the propagating messages of the preceding frame are translated through referring to motion vector and then used as the initial values of message for the current frame. Meanwhile, the consistency of the motion vector is incorporated to the smoothness constraint for the current frame. The proposed spatiotemporal model of belief propagation has more systematic and comprehensive combination of temporal correlation compared to previous works. The experimental results show that it outperforms the algorithms based on 2D belief propagation especially for non-deformation motion in middle-low speed.
KEYWORDS: Particle filters, Particles, Detection and tracking algorithms, RGB color model, Communication engineering, Digital filtering, Visual process modeling, Performance modeling, Statistical modeling, Lanthanum
In the object tracking area, both particle filter and mean shift algorithm have proven successful approaches. However, both of them have notable weakness. In this paper, we present a new algorithm which combined the two algorithms to track the target. First, the mean shift algorithm is employed to search an object candidate near the target state. Then, if the candidate is good enough, it will be used to adapt the particle filter parameters, including the number of particle filter, and etc. Finally, the particle filter will estimate the target state based on these new parameters. Further, the paper introduces the color-texture combined feature instead of color feature.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.