Visual tracking is one of the key research fields in computer vision. Based on the combination of correlation filter tracking (CFT) model and deep convolutional neural networks (DCNNs), deep correlation filter tracking (DCFT) has recently become a critical issue in visual tracking because of CFT’s rapidity and DCNN’s better feature representation. However, DCNNs are often complex in structure, which most possibly results in the conflict between the rapidity and accuracy of DCFT. To reduce such conflict, this paper proposes a model mainly including: (1) Based on the pre-pruning network obtained by feature channel importance, an optimal global tracking pruning rate (GTPR) is determined in terms of the contribution of filter channels to tracking response. (2) Based on (GTPR), an alternative convolutional kernel is defined to replace non-important channel kernels, which leads to the further pruning of the feature network. (3) An online updating pruned feature network with a structural similarity index is employed to adapt the model to tracking scene changes. (4) The proposed model was performed on OTB2013; experimental results demonstrate the model can effectively enhance speed with a 45% increment while guaranteeing tracking accuracy, and improve tracking accuracy with a 4% increment when tracking scene changes take place.
KLFCM is a clustering algorithm proposed by introducing K-L divergence into FCM, which has been widely used in the field of fuzzy clustering. Although many studies have focused on improving its accuracy and efficiency, little attention has been paid to its convergence properties and parameter selection. Like other fuzzy clustering algorithms, the output of the KLFCM algorithm is also affected by fuzzy parameters. Furthermore, some researchers have noted that the KLFCM algorithm is equivalent to the EM algorithm for Gaussian mixture models when the fuzzifier λ is equal to 2. In practical applications, the KLFCM algorithm may also exhibit self-annealing properties similar to the EM algorithm. To address these issues, this paper uses Jacobian matrix analysis to investigate the KLFCM algorithm’s parameter selection and convergence properties. We first derive a formula for calculating the Jacobian matrix of the KLFCM with respect to the membership function. Then, we demonstrate the self-annealing behavior of this algorithm through theoretical analysis based on the Jacobian matrix. We also provide a reference strategy for determining the appropriate values of fuzzy parameters in the KLFCM algorithm. Finally, we use Jacobian matrix analysis to investigate the relationships between the convergence rate and different parameter values of the KLFCM algorithm. Our experimental results validate our theoretical findings, demonstrating that when selecting appropriate lambda parameter values, the KLFCM clustering algorithm exhibits self-annealing properties that reduce the impact of initial clustering centers on clustering results. Moreover, using our proposed strategy for selecting the fuzzy parameter lambda of the KLFCM algorithm effectively prevents coincident clustering results from being produced by the algorithm.
The detection of key events and identification of the events’ context have been widely studied to detect key events from large volumes of online news and identify trends in such events. In this paper, we propose a Key News Event Detection and Context Method based on graphic convolving, clustering, and summarizing methods. Our method has three main contributions: (1) We propose the use of position vectors as time-embedding feature representations and concatenate semantic and time-embedding features as node features of the graph to distinguish different nodes of the graph. Additionally, a temporal nonlinear function was constructed using time embedding to objectively describe the effect of time on the degree of association between nodes. (2) We update the graph nodes using a graph convolutional neural network to extract deep semantic information about individual nodes of a high-quality phrase graph, thereby improving the clustering capability of graph-based key event detection. (3) We apply a summary generation algorithm to a subset of news data for each key event. Lastly, we validated the effectiveness of our proposed method by applying it to the 2014 Ebola dataset. The experimental results indicate that our proposed method can effectively detect key events from news documents with high precision and completeness while naturally generating the event context of key events, as compared to EvMine and other existing methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.