研究者詳細 - 藤井　慶輔

論文 - 藤井　慶輔

分割表示 105 件中 1 - 20 件目／全件表示 >>

Estimating counterfactual treatment outcomes over time in complex multi-agent scenarios 査読有り

Keisuke Fujii, Koh Takeuchi, Atsushi Kuribayashi, Naoya Takeishi, Yoshinobu Kawahara, Kazuya Takeda

IEEE Transactions on Neural Networks and Learning Systems 36 巻 ( 2 ) 頁： 2103 - 2117 2025年2月

Attempting to incorporate elements of open skills into closed-skill learning : A case study using a golf putting task 査読有り

HASEGAWA Yumiko, YAMAMOTO Kota, OKADA Ayako, FUJII Keisuke

114 巻頁： 101 - 119 2024年6月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Faculty of Humanities and Social Sciences, Iwate University

In motor learning, how a target skill is learned is important, and performance results vary depending on practice-related factors. Motor skills, which are classified as closed skills, are typically practiced through self-paced repetition. However, learning a target-following task performed alone may be facilitated by intervention from another person. Therefore, we considered an environment with disturbances such as open skills, even for a closed-skill learning activity such as a golf putting task, and expected that learning would be promoted in an environment with high uncertainty. In this study, we developed an idea based on several previous studies, and examined the effects of the practice of "catching and hitting a ball launched from ball launchers." The participants were four golf novices, two of whom practiced a conventional putting style as the control group. The participants practiced 10 times over a month, during which they took a pretest, midterm test, and posttest. Subsequently, the participants were challenged with two tasks. The participants practiced with approximately 1,000 balls during the study. To evaluate their performance, we used a motion capture device to measure the orientation of their body, kinematics of the putter head, and final ball positions. To measure participants’ sight lines, we proposed a method that utilizes a local coordinate system to efficiently represent and estimate the movement of points. From the results of the sight line analysis using this method, we understood the problems of novices’ alignment (aligning the putter head and body for the target). In addition, we were able to determine how long it takes for golf novices to acquire their approximate movement patterns and the number of days that the absolute error of the final ball position can be kept within 0.2 m ~ 0.4 m. We discuss the impact and future possibilities of incorporating elements of open skills to improve golf-putting skills.

DOI： 10.15113/0002000356

CiNii Research

Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling 査読有り

Keisuke Fujii, Naoya Takeishi, Yoshinobu Kawahara, Kazuya Takeda

Neural Networks 171 巻頁： 40 - 52 2024年3月

Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations 査読有り

Keisuke Fujii, Kazushi Tsutsui, Atom Sco, Hiroshi Nakahara, Naoya Takeishi, Yoshinobu Kawahara

International Conference on Agents and Artificial Intelligence (ICAART 2024) 2 巻頁： 27 - 39 2024年2月

Estimating counterfactual treatment outcomes over time in complex multi-vehicle simulation 査読有り

2022年11月

Learning interaction rules from multi-animal trajectories via augmented behavioral model 査読有り

Keisuke Fujii, Naoya Takeishi, Kazushi Tsutsui, Emyo Fujioka, Nozomi Nishiumi, Ryoya Tanaka, Mika Fukushiro, Kaoru Ide, Hiroyoshi Kohno, Ken Yoda, Susumu Takahashi, Shizuko Hiryu, Yoshinobu Kawahara

Advances in Neural Information Processing Systems (NeurIPS'21) 34 巻 2021年12月

Data-Driven Analysis for Understanding Team Sports Behaviors

Keisuke Fujii

Journal of Robotics and Mechatronics 33 巻 ( 3 ) 頁： 505 - 514 2021年6月

担当区分：筆頭著者,　最終著者,　責任著者記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：富士技術出版株式会社

<p>Understanding the principles of real-world biological multi-agent behaviors is a current challenge in various scientific and engineering fields. The rules regarding the real-world biological multi-agent behaviors such as those in team sports are often largely unknown due to their inherently higher-order interactions, cognition, and body dynamics. Estimation of the rules from data, i.e., via data-driven approaches such as machine learning, provides an effective way to analyze such behaviors. Although most data-driven models have non-linear structures and high predictive performances, it is sometimes hard to interpret them. This survey focuses on data-driven analysis for quantitative understanding of behaviors in invasion team sports such as basketball and football, and introduces two main approaches for understanding such multi-agent behaviors: (1) extracting easily interpretable features or rules from data and (2) generating and controlling behaviors in visually-understandable ways. The first approach involves the visualization of learned representations and the extraction of mathematical structures behind the behaviors. The second approach can be used to test hypotheses by simulating and controlling future and counterfactual behaviors. Lastly, the potential practical applications of extracted rules, features, and generated behaviors are discussed. These approaches can contribute to a better understanding of multi-agent behaviors in the real world.</p>

DOI： 10.20965/jrm.2021.p0505

CiNii Research

Physically-interpretable classification of biological network dynamics for complex collective motions 査読有り国際誌

Fujii Keisuke, Takeishi Naoya, Hojo Motokazu, Inaba Yuki, Kawahara Yoshinobu

SCIENTIFIC REPORTS 10 巻 ( 1 ) 頁： 3005 - 3005 2020年2月

Data-driven spectral analysis for coordinative structures in periodic human locomotion 査読有り国際誌

Fujii Keisuke, Takeishi Naoya, Kibushi Benio, Kouzaki Motoki, Kawahara Yoshinobu

SCIENTIFIC REPORTS 9 巻 ( 1 ) 頁： 16755 - 16755 2019年11月

Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables 査読有り国際誌

Keisuke Fujii, Yoshinobu Kawahara

Neural Networks 117 巻頁： 94 - 103 2019年9月

Transformer-based neural marked spatio temporal point process model for analyzing football match events. 査読有り

Calvin Yeung, Tony Sit, Keisuke Fujii

Applied Intelligence 55 巻 ( 5 ) 頁： 335 - 335 2025年4月

Two clusterings to capture basketball players’ shooting tendencies using tracking data: clustering of shooting styles and the shots themselves 査読有り

Kazuhiro Yamada, Keisuke Fujii

International Journal of Computer Science in Sport 24 巻 ( 1 ) 頁： 35 - 55 2025年2月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Walter de Gruyter GmbH

Abstract

Studies to understand the shooting preferences of basketball players relied exclusively on data on shot location, which did not lead to concrete understandings because they contained no information on how they moved to that location. Therefore, this study tried to cluster the players’ shooting tendencies using the tracking data of the players’ movements during the game. To do this, we first created hand-crafted shot features that included information on the pre-shot movement. Using those features, the dissimilarity of shooting tendencies between players was computed by considering the shot set of each player as a probability distribution and calculating the Wasserstein distance between them. The clustering based on their dissimilarity resulted in more clusters than in previous studies and allowed for specific shooting styles to be defined. Clustering using Gower distance as a dissimilarity measure for shot features, including a categorical feature, extracted clusters of shots that are useful for understanding players’ more detailed shooting tendencies. These results prove that it is not only the shot location but also how the player moved before the shot that is important to capture the player’s shooting preferences.

DOI： 10.2478/ijcss-2025-0003

researchmap

特集「スポーツ×情報学×インタラクション」にあたって

市川淳, 藤井慶輔, 山田雅敏, 一ノ瀬元喜

人工知能 40 巻 ( 1 ) 頁： 1002 - 1003 2025年1月

Putting performance bias to the front-lower side of the hole on steep slopes: Differences in strategies and movements between professional and amateur golfers 査読有り

Yumiko Hasegawa, Ayako Okada, Keisuke Fujii

PLOS ONE 19 巻 ( 12 ) 頁： e0314820 - e0314820 2024年12月

担当区分：最終著者記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Public Library of Science (PLoS)

When playing on an sloped golf course, the ball often misses the hole to the front-lower side, which is also referred to as the “amateur side.” This can be attributed to the difficulty in perceiving the green slope and choosing the appropriate launch direction and ball speed, especially for amateurs. The study had three main objectives. The first was to examine whether a front-down bias toward the hole could be experimentally observed in golfers’ putting. Second, to measure golfers’ aims and movements to determine why golfers, especially amateurs, putt poorly on steep slopes. Third, to investigate using a miniature platform how golfers recognized the steepness of the slopes and the relationship between their aim and their slope recognition. Twelve professionals and twelve intermediate amateurs were asked to perform in the 1- and 3-degree conditions (left-to-right line) at a distance of 3 m from the hole. Participants wore shutter goggles to inhibit visual feedback of outcomes. The aim, address, ball launch direction (analyzed as angles), and kinematics of the putter head and ball were measured. The results of this study experimentally confirmed the amateur side and indicated that the aim, address, and launch directions of the amateurs were smaller than those of the professionals. As for reproducing the slope task, we found that the amateurs underestimated the steepness on both conditions when compared to professionals. Additionally, golfers’ aim and slope recognition were weakly correlated. These suggest that amateurs, compared to professionals, were unable to choose the optimal speed of the putter head and the launch direction of the ball in relation to the slope. Furthermore, amateurs’ recognition was worse than that of professionals, which may affect their aim.

DOI： 10.1371/journal.pone.0314820

researchmap

ButterFlySet: A 2D video dataset for pose estimation of the flying butterflies in the wild 査読有り

Kai Amino, Keisuke Fujii

Visual observation and analysis of Vertebrate And Insect Behavior (VAIB) at International Conference on Pattern Recognition (ICPR 2024) 2024年12月

Runner re-identification from single-view running video in the open-world setting 査読有り

Tomohiro Suzuki, Kazushi Tsutsui, Kazuya Takeda, Keisuke Fujii

Multimedia Tools and Applications 83 巻 ( 36 ) 頁： 83729 - 83745 2024年11月

Estimation of Overlapped Tactical Actions from Soccer Match Video. 査読有り

Kento Kuroda, Ikuma Uchida, Keisuke Fujii, Yoshinari Kameda

icSPORTS 頁： 257 - 264 2024年11月

Basketball-SORT: an association method for complex multi-object occlusion problems in basketball multi-object tracking. 査読有り

Qingrui Hu, Atom Sco, Calvin Yeung, Keisuke Fujii

Multimedia Tools and Applications 83 巻 ( 38 ) 頁： 86281 - 86297 2024年11月

MulCPred: Learning Multi-Modal Concepts for Explainable Pedestrian Action Prediction. 査読有り国際誌

Yan Feng, Alexander Carballo, Keisuke Fujii, Robin Karlsson, Ming Ding, Kazuya Takeda

Sensors (Basel, Switzerland) 24 巻 ( 20 ) 頁： 6742 2024年10月

記述言語：英語掲載種別：研究論文（学術雑誌）

Pedestrian action prediction is crucial for many applications such as autonomous driving. However, state-of-the-art methods lack the explainability needed for trustworthy predictions. In this paper, a novel framework called MulCPred is proposed that explains its predictions based on multi-modal concepts represented by training samples. Previous concept-based methods have limitations, including the following: (1) they cannot be directly applied to multi-modal cases; (2) they lack the locality needed to attend to details in the inputs; (3) they are susceptible to mode collapse. These limitations are tackled accordingly through the following approaches: (1) a linear aggregator to integrate the activation results of the concepts into predictions, which associates concepts of different modalities and provides ante hoc explanations of the relevance between the concepts and the predictions; (2) a channel-wise recalibration module that attends to local spatiotemporal regions, which enables the concepts with locality; (3) a feature regularization loss that encourages the concepts to learn diverse patterns. MulCPred is evaluated on multiple datasets and tasks. Both qualitative and quantitative results demonstrate that MulCPred is promising in improving the explainability of pedestrian action prediction without obvious performance degradation. Moreover, by removing unrecognizable concepts, MulCPred shows improved cross-dataset prediction performance, suggesting its potential for further generalization.

DOI： 10.3390/s24206742

PubMed

researchmap

Evaluating soccer match prediction models: a deep learning approach and feature optimization for gradient-boosted trees. 査読有り

Calvin Yeung, Rory P. Bunker, Rikuhei Umemoto, Keisuke Fujii

Machine Learning 113 巻 ( 10 ) 頁： 7541 - 7564 2024年10月

　前のページ - 次のページ　

<藤井 慶輔>

論文 - 藤井 慶輔

<藤井　慶輔>

論文 - 藤井　慶輔