The Experts below are selected from a list of 315 Experts worldwide ranked by ideXlab platform
Wei Chai - One of the best experts on this subject based on the ideXlab platform.
-
Semantic Segmentation and Summarization of Music
2020Co-Authors: Wei ChaiAbstract:Automatic segmentation and summarization of music is a key issue in music browsing, searching and recommendation. This article presents methods for segmenting music based on its tonality and Recurrent Structure, and summarizing music based on its Structure. Experimental results are evaluated quantitatively to demonstrate the promise of the proposed methods.
-
semantic segmentation and summarization of music methods based on tonality and Recurrent Structure
IEEE Signal Processing Magazine, 2006Co-Authors: Wei ChaiAbstract:This paper describes a study on automatic music segmentation and summarization from audio signals. The paper inquires scientifically into the nature of human perception of music and offers a practical solution to difficult problems of machine intelligence for automated multimedia content analysis and information retrieval. Specifically, three problems are addressed: segmentation based on tonality analysis, segmentation based on Recurrent structural analysis, and summarization. Experimental results are evaluated quantitatively, demonstrating the promise of the proposed methods
Dongmei Fu - One of the best experts on this subject based on the ideXlab platform.
-
learning Recurrent Structure guided attention network for multi person pose estimation
International Conference on Multimedia and Expo, 2019Co-Authors: Jianlong Fu, Dongmei FuAbstract:Multi-person pose estimation aims to localize tens of human joints (e.g., elbow, wrist, etc.) from multiple human bodies in an image. Existing approaches mainly adopt a two stage pipeline, which usually consists of a human detector (i.e., generating a bounding box for each person) and a single person pose estimator (i.e., generating human joints from each bounding box). However, these approaches neglect the challenges of large pose variations and heavy occlusions in each bounding box, which often results in imprecise human joint localization. In this paper, we propose a Structure-guided attention network (SGAN) for multi-person pose estimation. Specifically, a Structured pose representation is encoded by learning a joint confidence map and a joint association map, which can be further refined by a Structure-guided attention network (SGAN) in a Recurrent way. Note that SGAN enables a deep neural network to take initial pose estimation as references, and to discover multi-scale pose features as completion, and thus the learning of pose Structures can be reinforced. Extensive experiments show the best single-model results against the state-of-the-art approaches, with a relative 3.5% mAP gain in the challenging COCO Keypoint dataset.
-
ICME - Learning Recurrent Structure-Guided Attention Network for Multi-person Pose Estimation
2019 IEEE International Conference on Multimedia and Expo (ICME), 2019Co-Authors: Jianlong Fu, Dongmei FuAbstract:Multi-person pose estimation aims to localize tens of human joints (e.g., elbow, wrist, etc.) from multiple human bodies in an image. Existing approaches mainly adopt a two stage pipeline, which usually consists of a human detector (i.e., generating a bounding box for each person) and a single person pose estimator (i.e., generating human joints from each bounding box). However, these approaches neglect the challenges of large pose variations and heavy occlusions in each bounding box, which often results in imprecise human joint localization. In this paper, we propose a Structure-guided attention network (SGAN) for multi-person pose estimation. Specifically, a Structured pose representation is encoded by learning a joint confidence map and a joint association map, which can be further refined by a Structure-guided attention network (SGAN) in a Recurrent way. Note that SGAN enables a deep neural network to take initial pose estimation as references, and to discover multi-scale pose features as completion, and thus the learning of pose Structures can be reinforced. Extensive experiments show the best single-model results against the state-of-the-art approaches, with a relative 3.5% mAP gain in the challenging COCO Keypoint dataset.
Mostafa Sedighizadeh - One of the best experts on this subject based on the ideXlab platform.
-
Adaptive PID control of wind energy conversion systems using wavenets
2020Co-Authors: Mostafa Sedighizadeh, Mohsen KalantarAbstract:In this paper a PID control strategy using neural network adaptive RASP1 wavelet for WECS control is proposed. It is based on single layer feedforward neural networks with hidden nodes of adaptive RASP1 wavelet function controller and an infinite impulse response (IIR) Recurrent Structure. The IIR is combined by cascading to the network to provide a double local Structure resulting in improving the speed of learning. This particular neuro PID controller assumes a certain model Structure to approximately identify the system dynamics of the unknown plant (WECS) and generate the control signal. The results are applied to a typical turbine/generator pair, showing the feasibility of the proposed solution.
-
Self tuning control of wind turbine using neural network identifier
Electrical Engineering, 2008Co-Authors: Mostafa Sedighizadeh, A. RezazadehAbstract:The nonlinear characteristics of the wind turbines and electric generators necessitate that grid connected wind energy conversion systems (WECS) use nonlinear controls. The present paper proposes an adaptive self tuning control strategy with neural network Morlet wavelet for WECS control. The proposed strategy is based on single layer feedforward neural networks with hidden nodes of adaptive Morlet wavelet functions controller and an infinite impulse response Recurrent Structure. The neuro controller is based on a certain model Structure to approximately identify the system dynamics of WECS, and control its response. The proposed controller is studied in three situations: without noise, with measurement input noise and with disturbance output noise. Finally, the results of the performance of the new controller were compared with a multilayer perceptron network proving a more precise modeling and control of WECS.
-
A Neuro Adaptive Control Strategy for Movable Power Source of Poroton Exchange Membrane Fuel Cell Using Wavelets
Proceedings of the 41st International Universities Power Engineering Conference, 2006Co-Authors: D. Arzaghi-harris, Mostafa SedighizadehAbstract:Movable power sources of proton exchange membrane fuel cells (PEMFC) are the important research done in the current fuel cells (FC) field. The PEMFC system control influences the cell performance greatly and it is a control system for industrial complex problems, due to the imprecision, uncertainty and partial truth and intrinsic nonlinear characteristics of PEMFCs. In this paper an adaptive PI control strategy using neural network adaptive Morlet wavelet for control is proposed. It is based on a single layer feed forward neural networks with hidden nodes of adaptive Morlet wavelet functions controller and an infinite impulse response (IIR) Recurrent Structure. The IIR is combined by cascading to the network to provide double local Structure resulting in improving speed of learning. The proposed method is applied to a typical 1 KW PEMFC system and the results show the proposed method has more accuracy against to MLP (multi layer perceptron) method.
-
Adaptive-Neural Pid Control of Wind Energy Conversion Systems Using Wavenets
Proceedings of the 2005 IEEE International Symposium on Mediterrean Conference on Control and Automation Intelligent Control 2005., 2005Co-Authors: Mohsen Kalantar, Mostafa SedighizadehAbstract:In this paper a PID control strategy using neural network adaptive RASP1 wavelet for WECS's control is proposed. It is based on single layer feedforward neural networks with hidden nodes of adaptive RASP1 wavelet functions controller and an infinite impulse response (IIR) Recurrent Structure. The IIR is combined by cascading to the network to provide double local Structure resulting in improving speed of learning. This particular neuro PID controller assumes a certain model Structure to approximately identify the system dynamics of the unknown plant (WECS's) and generate the control signal. The results are applied to a typical turbine/generator pair, showing the feasibility of the proposed solution
-
Adaptive PID control of wind energy conversion systems using RASP1 mother wavelet basis function networks
2004 IEEE Region 10 Conference TENCON 2004., 2004Co-Authors: Mostafa Sedighizadeh, D. Arzaghi-harris, Mohsen KalantarAbstract:In this paper a PID control strategy using neural network adaptive RASP1 wavelet for WECS's control is proposed. It is based on single layer feedforward neural networks with hidden nodes of adaptive RASP1 wavelet functions controller and an infinite impulse response (IIR) Recurrent Structure. The IIR is combined by cascading to the network to provide double local Structure resulting in improving speed of learning. This particular neuro PID controller assumes a certain model Structure to approximately identify the system dynamics of the unknown plant (WECS's) and generate the control signal. The results are applied to a typical turbine/generator pair, showing the feasibility of the proposed solutions.
Zengfu Wang - One of the best experts on this subject based on the ideXlab platform.
-
Video Super-Resolution Using Non-Simultaneous Fully Recurrent Convolutional Network
IEEE Transactions on Image Processing, 2019Co-Authors: Dingyi Li, Zengfu WangAbstract:Video super-resolution (SR) aims at restoring fine details and enhancing visual experience for low-resolution videos. In this paper, we propose a very deep non-simultaneous fully Recurrent convolutional network for video SR. To make full use of temporal information, we employ motion compensation, very deep fully Recurrent convolutional layers, and late fusion in our system. Residual connection is also employed in our Recurrent Structure for more accurate SR. Finally, a new model ensemble strategy is used to combine our method with a single-image SR method. Experimental results demonstrate that the proposed method is better than that of the state-of-the-art SR methods on quantitative visual quality assessment.
Jun Zhao - One of the best experts on this subject based on the ideXlab platform.
-
Recurrent Convolutional Neural Networks for Text Classification
Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015Co-Authors: Siwei Lai, Liheng Xu, Kang Liu, Jun ZhaoAbstract:Text classification is a foundational task in many NLP applications. Traditional text classifiers often rely on many human-designed features, such as dictionaries, knowledge bases and special tree kernels. In contrast to traditional methods, we introduce a Recurrent con-volutional neural network for text classification with-out human-designed features. In our model, we apply a Recurrent Structure to capture contextual information as far as possible when learning word representations, which may introduce considerably less noise compared to traditional window-based neural networks. We also employ a max-pooling layer that automatically judges which words play key roles in text classification to cap-ture the key components in texts. We conduct experi-ments on four commonly used datasets. The experimen-tal results show that the proposed method outperforms the state-of-the-art methods on several datasets, partic-ularly on document-level datasets.