检索结果-内蒙古大学图书馆

DanceFix: An Exploration in Group Dance Neatness Assessment Through Fixing Abnormal Challenges of Human Pose 39

学校读者我要写书评

暂无评论

DanceFix: An Exploration in Group Dance Neatness Assessment ...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Huangbiao Ke, Xiao Wu, Huanqi Xu, Rui Li, Yuezhou Xu, Peirong Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

ISBN: (纸本)157735897X

The fair and objective assessment of performances and competitions is a common pursuit and challenge in human society. The application of computer vision technology offers hope for this purpose, but it still faces obstacles such as occlusion and motion blur. To address these hindrances, our DanceFix proposes a bidirectional spatial-temporal context optical flow correction (BOFC) method. This approach leverages the consistency and complementarity of motion information between two modalities: optical flow, which excels at pixel capture, and lightweight skeleton data. It enables the extraction of pixel-level motion changes and the correction of abnormal skeleton data. Furthermore, we propose a part-level dance dataset (Dancer Parts) and part-level motion feature extraction based on task decoupling (PETD). This aims to decouple complex whole-body parts tracking into fine-grained limb-level motion extraction, enhancing the confidence of temporal information and the accuracy of correction for abnormal data. Finally, we present the DNV dataset, which simulates fully neat group dance scenes and provides reliable labels and validation methods for the newly introduced group dance neatness assessment (GDNA). To the best of our knowledge, this is the first work to develop quantitative criteria for assessing limb and joint neatness in group dance. We conduct experiments on DNV and video-based public JHMDB datasets. Our method effectively corrects abnormal skeleton points, flexibly embeds, and improves the accuracy of existing pose estimation algorithms. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

Research on solving time-dependent Schrodinger equation for higher-order FDTD based on spatial filtering

学校读者我要写书评

暂无评论

Research on solving time-dependent Schrodinger equation for ...

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Wenjie Ding Guoda Xie Zhixiang Huang Education of Anhui Province. Anhui Province Key Laboratory of Target Recognition and Feature Extraction (Luan Anhui 237000 China) Ministry of Education. the Key Laboratory of Intelligent Computing and Signal Processing Hefei China Key Laboratory of Electromagnetic Environmental Sensing (Hefei 230601 China) Anhui Province Anhui University Anhui university Hefei China

Combining the spatial filtering (SF) technique with FDTD(2, q) method (2 and q denote the temporal differential order and spatial differential order, respectively), a novel SF-FDTD(2, q) method with more relaxed Courant-Friedrichs-Lewy (CFL) condition is proposed and used for solving 3D time-dependent Schrödinger equation. Then, the correctness of the SF-FDTD(2, $q$ ) method is validated by calculating eigenfrequencies of the 3D quantum well model.

关键词：

Efficient CDI-FDTD Method for Modelling Graphene-Based Structures

学校读者我要写书评

暂无评论

Efficient CDI-FDTD Method for Modelling Graphene-Based Struc...

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Jiale Liu Guoda Xie Zhixiang Huang Education of Anhui Province. Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan Anhui China Ministry of Education. the Key Laboratory of Intelligent Computing and Signal Processing Hefei China Anhui Province Anhui University. Key Laboratory of Electromagnetic Environmental Sensing Hefei China Anhui university Hefei China

This paper presents a novel approach for calculating graphene-based structures in the complying divergence implicit finite-difference time-domain (CDI-FDTD) method. To begin, the differential iteration formula of graphene structure in the CDI-FDTD method is derived utilizing the auxiliary-differential-equation (ADE) method. Next, the transmission characteristics of an infinite graphene sheet in an open space are investigated by conducting simulation analyses within the CDI-FDTD framework, considering various magnetostatic or electrostatic biases. Finally, the simulation results were compared with analytical solutions and the results obtained from traditional FDTD methods, confirming the unconditional stability and reliability of the proposed method.

关键词：

Edge-Preserving Multi-Exposure Fusion with Guided Filtering for Structural Patch Decomposition

学校读者我要写书评

暂无评论

Edge-Preserving Multi-Exposure Fusion with Guided Filtering ...

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Yang Zhen Junwei Qi Yingsong Li College of Information and Communication Engineering Harbin Engineering University Harbin China College of Computer Science and Technology Harbin Engineering University Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

Multi-exposure image fusion (MEF) is one of the effective ways to obtain high dynamic range (HDR) images. Multi-scale structural patch decomposition based MEF(MSPD) and edge-preserving structural patch decomposition (MESPD) have achieved state-of-the-art fusion quality. MESPD incorporates edge-preserving factors into MSPD to preserve details in a single-scale setting. However, we find that the edge-preserving factors put too much emphasis on the edge, resulting in artifacts on some edges and loss of details. To tackle this issue, guided filter is introduced into MSPD, which is directly used as an edge-preserving filter instead of mean filter to implicitly decompose images. In addition, we have designed a flexible adaptive weight, which can further maintain details of the light and dark areas. Likewise, we inherit MESPD and MSPD to extend our method to multi-scale framework. Extensive experimental results demonstrate our method can produce satisfactory results in both static and dynamic scenes with fewer artifacts and low computational cost.

关键词：

Multi-Granularity Prosodic Speech Synthesis with Grammar Information

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zhou, Jian Liu, Jiahui Fan, Cunhang Zheng, Wenming Lv, Zhao Tao, Liang Kwan, Hon Keung The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China Ministry of Education School of Biological Science and Medical Engineering Southeast University Nanjing210096 China The Department of Electrical and Computer Engineering University of Windsor WindsorN9B 3P4 Canada

Personalized speech synthesis involves learning an individual's unique speaking patterns from a reference audio to generate speech that mimics the speaker's habitual rhythm. However, the one-to-many mapping between text and speech, combined with the dynamic nature of personalized speech style characteristics in the reference audio, poses significant challenges for accurate personalized speech synthesis. In this paper, we propose a Grammar Infused Multi-granularity Prosody Network (GMG ProsodyNet) for personalized speech synthesis. Specifically, 1) We model prosodic features hierarchically at the levels of utterance, content syntax, word, and phoneme. We utilize the utterance-level prosodic feature to guide the prediction of fine-grained prosodic features according to the hierarchical property of prosodic features. We introduce a context syntax encoder to improve the prediction accuracy of duration, pitch, and energy characteristics in the synthesized audio. The proposed word-level prosodic encoder can efficiently extract valuable pitch dynamic and speech continuity features from the word spectrum. For controlling subtle prosodic nuances, we employ phoneme-level prosodic modeling. 2) We extract syntax level prosodic features from the syntax graph constructed by Graph Neural Network (GNN) with word as node, exploiting grammatical dependencies between distant words. Experimental results demonstrate that the proposed GMG ProsodyNet can effectively encode delicate and personalized prosodic features, leading to improved speech synthesis quality, fluency, and naturalness. © 2024, The Authors. All rights reserved.

关键词： Speech synthesis

Low-rank generalized alternating direction implicit iteration method for solving matrix equations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Juan Xun, Wenlu Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan China School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan China

This paper presents an effective low-rank generalized alternating direction implicit iteration (R-GADI) method for solving large-scale sparse and stable Lyapunov matrix equations and continuous-time algebraic Riccati matrix equations. The method is based on generalized alternating direction implicit iteration (GADI), which exploits the low-rank property of matrices and utilizes the Cholesky factorization approach for solving. The advantage of the new algorithm lies in its direct and efficient low-rank formulation, which is a variant of the Cholesky decomposition in the Lyapunov GADI method, saving storage space and making it computationally effective. When solving the continuous-time algebraic Riccati matrix equation, the Riccati equation is first simplified to a Lyapunov equation using the Newton method, and then the R-GADI method is employed for computation. Additionally, we analyze the convergence of the R-GADI method and prove its consistency with the convergence of the GADI method. Finally, the effectiveness of the new algorithm is demonstrated through corresponding numerical experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Riccati equations

Optimization methods for solving matrix equations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Juan Luo, Xiao Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan China School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan China

In this paper, we focus on using optimization methods to solve matrix equations by transforming the problem of solving the Sylvester matrix equation or continuous algebraic Riccati equation into an optimization problem. Initially, we use a constrained convex optimization method (CCOM) to solve the Sylvester matrix equation with 2,1-norm, where we provide a convergence analysis and numerical examples of CCOM;however, the results show that the algorithm is not efficient. To address this issue, we employ classical quasi-Newton methods such as DFP and BFGS algorithms to solve the Sylvester matrix equation and present the convergence and numerical results of the algorithm. Additionally, we compare these algorithms with the CG algorithm and AR algorithm, and our results demonstrate that the presented algorithms are effective. Furthermore, we propose a unified framework of the alternating direction multiplier method (ADMM) for directly solving the continuous algebraic Riccati equation (CARE), and we provide the convergence and numerical results of ADMM. Our experimental results indicate that ADMM is an effective optimization algorithm for solving CARE. Finally, to improve the effectiveness of the optimization method for solving Riccati equation, we propose the Newton-ADMM algorithm framework, where the outer iteration of this method is the classical Newton method, and the inner iteration involves using ADMM to solve Lyapunov matrix equations inexactly. We also provide the convergence and numerical results of this algorithm, which our results demonstrate are more efficient than ADMM for solving CARE. Copyright © 2024, The Authors. All rights reserved.

关键词： Newton-Raphson method

A general alternating direction implicit iteration method for solving complex symmetric linear systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Juan Xun, Wenlu Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan China School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan China

We have introduced the generalized alternating direction implicit iteration (GADI) method for solving large sparse complex symmetric linear systems and proved its convergence properties. Additionally, some numerical results have demonstrated the effectiveness of this algorithm. Furthermore, as an application of the GADI method in solving complex symmetric linear systems, we utilized the flattening operator and Kronecker product properties to solve Lyapunov and Riccati equations with complex coefficients using the GADI method. In solving the Riccati equation, we combined inner and outer iterations, first simplifying the Riccati equation into a Lyapunov equation using the Newton method, and then applying the GADI method for solution. Finally, we provided convergence analysis of the method and corresponding numerical results. Copyright © 2024, The Authors. All rights reserved.

关键词： Riccati equations

Low-rank alternating direction doubling algorithm for solving large-scale continuous time algebraic Riccati equations

学校读者我要写书评

暂无评论

arXiv 2024年

This paper proposes an effective low-rank alternating direction doubling algorithm (R-ADDA) for computing numerical low-rank solutions to large-scale sparse continuous-time algebraic Riccati matrix equations. The method is based on the alternating direction doubling algorithm (ADDA), utilizing the low-rank property of matrices and employing Cholesky factorization for solving. The advantage of the new algorithm lies in computing only the 2k-th approximation during the iterative process, instead of every approximation. Its efficient low-rank formula saves storage space and is highly effective from a computational perspective. Finally, the effectiveness of the new algorithm is demonstrated through theoretical analysis and numerical experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Matrix algebra