Shoichiro Takeda
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shoichiro Takeda has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Hayaru Shouno
Graduate School of Informatics and Engineering, The University of Electro-Communications, Chofu, Tokyo 182-8585, Japan
3 shared publications - Satoshi Suzuki
NTT Computer and Data Science Laboratories, NTT Corporation, Yokosuka, Japan
3 shared publications Akinori Fujino
NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan
1 shared publication- Arinobu Niijima
NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Kanagawa, Japan
1 shared publication - Atsushi Ando
NTT Corporation, NTT Media Intelligence Laboratories,Japan
1 shared publication - Guoqiang Zhang
University of Exeter
1 shared publication
Latest Publications
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Improving Putting Accuracy with Electrical Muscle Stimulation Feedback Guided by Muscle Synergy Analysis
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessImproving Putting Accuracy with Electrical Muscle Stimulation Feedback Guided by Muscle Synergy Analysis
- Open Access
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 92062-92072
MMW-AQA: Multimodal In-the-Wild Dataset for Action Quality Assessment
Action quality assessment (AQA) is a task for assessing a specific action quality in videos. Since existing AQA datasets provide only two-dimensional (2D) video data captured from fewer viewpoints, existing AQA methods based on deep neural networks (DNNs) struggle to assess complex three-dimensional (3D) actions accurately, and their robustness against diversified viewpoints remains unknown. We created a dataset called multimodal in-the-wild (MMW)-AQA in freestyle windsurfing that addresses these concerns. In addition to video data, MMW-AQA provides inertial measurement unit (IMU) and global positioning system (GPS) data. The 3D information of IMU data helps DNNs accurately assess complex 3D actions. Moreover, MMW-AQA provides wild video data captured by an unmanned aerial vehicle (UAV). These wild video data enable us to evaluate whether AQA methods can work well on diversified viewpoints. Furthermore, we also present the baseline multimodalization framework with a transformer-based fusion module. These frameworks multimodalize existing unimodal DNN models easily to assess action quality using multimodal data. Our experimental results demonstrate that multimodal data improves the AQA accuracy compared with unimodal video data.
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 92062-92072
Open AccessMMW-AQA: Multimodal In-the-Wild Dataset for Action Quality Assessment
Action quality assessment (AQA) is a task for assessing a specific action quality in videos. Since existing AQA datasets provide only two-dimensional (2D) video data captured from fewer viewpoints, existing AQA methods based on deep neural networks (DNNs) struggle to assess complex three-dimensional (3D) actions accurately, and their robustness against diversified viewpoints remains unknown. We created a dataset called multimodal in-the-wild (MMW)-AQA in freestyle windsurfing that addresses these concerns. In addition to video data, MMW-AQA provides inertial measurement unit (IMU) and global positioning system (GPS) data. The 3D information of IMU data helps DNNs accurately assess complex 3D actions. Moreover, MMW-AQA provides wild video data captured by an unmanned aerial vehicle (UAV). These wild video data enable us to evaluate whether AQA methods can work well on diversified viewpoints. Furthermore, we also present the baseline multimodalization framework with a transformer-based fusion module. These frameworks multimodalize existing unimodal DNN models easily to assess action quality using multimodal data. Our experimental results demonstrate that multimodal data improves the AQA accuracy compared with unimodal video data.
- Open Access
- 8 August 2023
- Published by Elsevier in Neural Networks
- Vol. 167, 50-64
Distorted image classification using neural activation pattern matching loss
- 8 August 2023
- Published by Elsevier in Neural Networks
- Vol. 167, 50-64
Open AccessDistorted image classification using neural activation pattern matching loss
- 24 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 9, 242-257
CoordiNet: Constrained Dynamics Learning for State Coordination Over Graph
A neural architecture to efficiently coordinate the transitions of state variables (states) over a graph is proposed. We consider the coordination of the time evolution of the state variables associated with the nodes on a graph. The states are associated with physical attributes of agents, e.g., the speed and/or location of vehicles. Efficient coordination then corresponds to the optimization of dynamics (how fast do vehicles travel) that may be subject to constraints (travel must be collision-free). The aim of this paper is (i) the formulation of learnable constrained dynamics which governs the transition of states under constraints over a graph and (ii) to show its industrial application. Firstly, we formulate continuous ordinary differential equations (ODEs), namely forward propagation of state transitions over a graph and backward propagation to optimize model parameters for the learnable constrained dynamics. Discretization of these continuous ODEs results in the neural architecture CoordiNet . Secondly, as an application of CoordiNet, we address a traffic coordination problem by learning constrained dynamics such that vehicles can travel as fast as possible without collisions. Simulation experiments of traffic coordination confirm that our method maximizes the vehicles' speed states while avoiding collisions.
- 24 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 9, 242-257
CoordiNet: Constrained Dynamics Learning for State Coordination Over Graph
A neural architecture to efficiently coordinate the transitions of state variables (states) over a graph is proposed. We consider the coordination of the time evolution of the state variables associated with the nodes on a graph. The states are associated with physical attributes of agents, e.g., the speed and/or location of vehicles. Efficient coordination then corresponds to the optimization of dynamics (how fast do vehicles travel) that may be subject to constraints (travel must be collision-free). The aim of this paper is (i) the formulation of learnable constrained dynamics which governs the transition of states under constraints over a graph and (ii) to show its industrial application. Firstly, we formulate continuous ordinary differential equations (ODEs), namely forward propagation of state transitions over a graph and backward propagation to optimize model parameters for the learnable constrained dynamics. Discretization of these continuous ODEs results in the neural architecture CoordiNet . Secondly, as an application of CoordiNet, we address a traffic coordination problem by learning constrained dynamics such that vehicles can travel as fast as possible without collisions. Simulation experiments of traffic coordination confirm that our method maximizes the vehicles' speed states while avoiding collisions.
- Open Access
- 24 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 68384-68396
Knowledge Transferred Fine-Tuning: Convolutional Neural Network Is Born Again With Anti-Aliasing Even in Data-Limited Situations
Anti-aliased convolutional neural networks (CNNs) are models that introduce blur filters to intermediate representations of CNNs to achieve high accuracy in image recognition tasks. A promising way to prepare a new anti-aliased CNN is to introduce blur filters to the intermediate representations of pre-trained (non anti-aliased) CNNs, since many researchers have released them online. Although this scheme can build the new anti-aliased CNN easily, the blur filters drastically degrade the pre-trained representations. Therefore, to take full advantage of the benefits of introducing blur filters, fine-tuning using massive amounts of training data is often required. This can be problematic because the training data is often limited. In such a “data-limited” situation, the fine-tuning does not bring about a high performance because it induces overfitting to the limited training data. To tackle this problem, we propose “knowledge transferred fine-tuning.” Knowledge transfer is a technique that utilizes the representations of a pre-trained model to help ensure generalization in data-limited situations. Inspired by this concept, we transfer knowledge from intermediate representations in a pre-trained CNN to an anti-aliased CNN while fine-tuning. The key idea of our method is to transfer only the essential knowledge for image recognition in the pre-trained CNN using two types of loss: pixel-level loss and global-level loss. The former loss transfers the detailed knowledge from the pre-trained CNN, but this knowledge may contain “aliased” non-essential knowledge. The latter loss, on the other hand, is designed to increase when the pixel-level loss transfers non-essential knowledge while ignoring the essential knowledge, i.e., it penalizes the pixel-level loss. Experimental results demonstrate that the proposed method using just 25 training images per class on ImageNet 2012 can achieve higher accuracy than a conventional pre-trained CNN.
- 24 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 68384-68396
Open AccessKnowledge Transferred Fine-Tuning: Convolutional Neural Network Is Born Again With Anti-Aliasing Even in Data-Limited Situations
Anti-aliased convolutional neural networks (CNNs) are models that introduce blur filters to intermediate representations of CNNs to achieve high accuracy in image recognition tasks. A promising way to prepare a new anti-aliased CNN is to introduce blur filters to the intermediate representations of pre-trained (non anti-aliased) CNNs, since many researchers have released them online. Although this scheme can build the new anti-aliased CNN easily, the blur filters drastically degrade the pre-trained representations. Therefore, to take full advantage of the benefits of introducing blur filters, fine-tuning using massive amounts of training data is often required. This can be problematic because the training data is often limited. In such a “data-limited” situation, the fine-tuning does not bring about a high performance because it induces overfitting to the limited training data. To tackle this problem, we propose “knowledge transferred fine-tuning.” Knowledge transfer is a technique that utilizes the representations of a pre-trained model to help ensure generalization in data-limited situations. Inspired by this concept, we transfer knowledge from intermediate representations in a pre-trained CNN to an anti-aliased CNN while fine-tuning. The key idea of our method is to transfer only the essential knowledge for image recognition in the pre-trained CNN using two types of loss: pixel-level loss and global-level loss. The former loss transfers the detailed knowledge from the pre-trained CNN, but this knowledge may contain “aliased” non-essential knowledge. The latter loss, on the other hand, is designed to increase when the pixel-level loss transfers non-essential knowledge while ignoring the essential knowledge, i.e., it penalizes the pixel-level loss. Experimental results demonstrate that the proposed method using just 25 training images per class on ImageNet 2012 can achieve higher accuracy than a conventional pre-trained CNN.
- 24 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (6) , 3934-3946
Deep Feature Compression Using Spatio-Temporal Arrangement Toward Collaborative Intelligent World
Collaborative Intelligence is a new paradigm that splits a deep neural network (DNN) into an edge and cloud for deploying a DNN-based image recognition application. In this paradigm, deep features, which are the outputs of the edge DNN, are compressed and transmitted to the cloud DNN. Because the deep features have a number of responses that are similar to each other, for efficient compression, previous methods spatially arrange and compress the deep features as an image to utilize the similarity as a spatial correlation. However, if the deep features are arranged in not only spatial but also temporal directions like those in a video, it may be possible to compress them more efficiently by increasing a temporal correlation. To explore this possibility, we propose a “spatio-temporal arrangement”. This method spatially arranges the deep features as images and temporally arranges them as a video with a novel ordering search algorithm. Our method effectively increases the spatial and temporal correlations hidden in the deep features and achieves high compression efficiency compared with the previous methods. Experimental results demonstrate the compression efficiency of our method is better than that of the previous methods (1.50% to 4.98% on BD-Rate evaluation in a lossy setting). Our analysis shows that our method effectively increases the correlation when the input is an image with rich edges and textures.
- 24 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (6) , 3934-3946
Deep Feature Compression Using Spatio-Temporal Arrangement Toward Collaborative Intelligent World
Collaborative Intelligence is a new paradigm that splits a deep neural network (DNN) into an edge and cloud for deploying a DNN-based image recognition application. In this paradigm, deep features, which are the outputs of the edge DNN, are compressed and transmitted to the cloud DNN. Because the deep features have a number of responses that are similar to each other, for efficient compression, previous methods spatially arrange and compress the deep features as an image to utilize the similarity as a spatial correlation. However, if the deep features are arranged in not only spatial but also temporal directions like those in a video, it may be possible to compress them more efficiently by increasing a temporal correlation. To explore this possibility, we propose a “spatio-temporal arrangement”. This method spatially arranges the deep features as images and temporally arranges them as a video with a novel ordering search algorithm. Our method effectively increases the spatial and temporal correlations hidden in the deep features and achieves high compression efficiency compared with the previous methods. Experimental results demonstrate the compression efficiency of our method is better than that of the previous methods (1.50% to 4.98% on BD-Rate evaluation in a lossy setting). Our analysis shows that our method effectively increases the correlation when the input is an image with rich edges and textures.