Faculty Profiles - FUJII Keisuke

Presentations -

Division display 61 - 80 of about 93 ／ All the affair displays >>

Interpersonal competition dynamics in a ballgame: Modeling of a 1-on-1 game and two opposing cognitive systems International conference

Keisuke Fujii, Yuji Yamamoto

International Society of Posture and Gait Research

The role of the kinetic preparatory state in defending against a dribbler in a basketball 1-on-1 subphase

Keisuke Fujii, Shinsuke Yoshioka, Tadao Isaka, Motoki Kouzaki

The Asian-South Pacific Association of Sport Psychology (ASPASP)

選手らしい動きと部分的な観測に基づく選手軌道予測モデル

藤井慶輔, 武石直也, 河原吉伸, 武田一哉

日本バスケットボール学会第 7 回学会大会 2020.12.19

部分観測過程におけるデータ駆動的エージェントモデリング Invited

藤井慶輔

日本認知科学会第37回大会 OS2 認知的インタラクションフレームワークの構築 2020.9.16

集団スポーツにおけるデータ駆動的モデルを用いた理解 Invited

藤井慶輔

第19回認知的コミュニケーションワークショップ 2020.11.3

Data-driven Analysis for Multi-agent Trajectories in Team Sports

Keisuke Fujii

17th AIP Open Seminar, Talks by Structured Learning Team in RIKEN Advanced Intelligence Project 2021.3.17

Automatic classification of offensive and defensive tactical plays in team sports

Keisuke Fujii

The 2020 Yokohama Sport Conference 2020.9.9

サッカーにおけるボール奪取・被有効攻撃予測に基づくチームの守備評価

戸田康介, 寺西真聖, 久代恵介, 藤井慶輔

第10回日本統計学会スポーツ統計分科会スポーツデータ解析コンペティション 2020.12.27

集団運動におけるデータ駆動科学（企画セッション：データ駆動科学と機械学習） Invited

藤井慶輔

第22回情報論的学習理論ワークショップ 2019.11.22

集団スポーツの戦術に関するデータ解析手法 Invited

藤井慶輔

第6回愛媛大学DS研究セミナー 2021.3.18

Extraction of swing motion contributing to prediction of shuttle drop position in badminton International conference

Tatsuya Yoshikawa, Kazushi Tsutsui, Kazuya Takeda and Keisuke Fujii

AI for Sports Analytics (AISA) Workshop IJCAI 2021 2021.8.17

Multi-agent deep-learning based comparative analysis in basketball

ZHANG Ziyi, BUNKER Rory, TAKEDA Kazuya, FUJII Keisuke

Proceedings of the Annual Conference of JSAI 2023 The Japanese Society for Artificial Intelligence

Language：English Presentation type：Oral presentation (general)

<p>Analysis of multi-agent trajectories is one of the fundamental issues for understanding real-world biological movements. For trajectory analysis, combining with labels (e.g. scored or not in ballgames) can obtain insights rather than only from trajectories. However, the previous deep-learning based method used only single agent trajectory in animals and cannot be directly applied to multi-agent ballgame trajectories. In this paper, we propose a comparative analysis method to analyze multi-agent trajectories in basketball. We adopt a neural network approach using multi-agent motion characteristics (e.g., distances between agents and objects) as the input and based on an attention mechanism to automatically detect segments in trajectories that are characteristic of one group. It enables us to understand the difference between groups by highlighting segmented trajectories and which variables correlate with the labels. We verified our approach by comparing various baselines and demonstrated the effectiveness of our method through use cases that analyze the attacking plays in the NBA league data.</p>

DOI： 10.11517/pjsai.jsai2023.0_3u1is304

CiNii Research

Force-based modeling of heterogeneous roles in coordinated behavior of a triad

ICHIKAWA Jun, FUJII Keisuke

Proceedings of the Annual Conference of JSAI 2023 The Japanese Society for Artificial Intelligence

Language：English Presentation type：Oral presentation (general)

<p>Humans often interact with others to achieve a group goal. Many studies on cognitive science, neuroscience, and sports science have investigated the coordination mechanisms and suggested the importance of role-sharing and adjustment using others' motor information. However, the adjustment process in the nonverbal behavior of a triad is not fully understood due to complex and dynamic interactions. We previously introduced a coordinated drawing task and conducted the behavioral experiment. The triads operated reels to change thread tensions, shared three heterogeneous roles (pulling, relaxing, and adjusting), and moved a pen connected to the three threads to draw an equilateral triangle. The results indicated that the adjusting role was related to high task performance, who helped resiliently without disturbing the pen's smooth movement while avoiding great pen deviation. To supplement these findings, this study formulated the three roles using equations of motion. The multi-agent simulation results showed that the adjusting role might use the degree of pen deviation reflected by others' motor information, such as the operating procedures and forces, and change the tension to draw at least three sides. The contribution of this study is to enhance the fundamental understanding of resilient adjustment required in team sports and haul seines.</p>

DOI： 10.11517/pjsai.jsai2023.0_2u5is503

CiNii Research

集団スポーツの動きを機械学習で評価する Invited

藤井慶輔

神戸大学シンポジウム：運動・スポーツスキルの先端研究 2024.1.20

集団スポーツにおける機械学習を用いたデータ科学 Invited

藤井慶輔

人工知能学会知識ベースシステム研究会 2023.8.25

言語モデリングによる行動選択・状態推移確率の推定に基づく選手定量評価指標

染谷大河, 川口康平, 藤井慶輔

2023年度スポーツデータサイエンスコンペティションサッカー部門 2024.1

複数スポーツの多物体追跡データセットの構築と競技間における汎用性の検証

スコットアトム, 内田郁真, 丁寧, 梅基陸平, バンカーローリー, 小林蓮, 小山孟志, 大西正輝, 亀田能成, 藤井慶輔

2023年度人工知能学会全国大会（第37回） 2023.6

生体集団運動における科学的知識と機械学習の融合による理解 Invited

藤井慶輔

液体・ガラスへのデータ駆動アプローチ - グラフニューラルネットワークとその周辺 - 2023.11.29

生体集団運動における機械学習を用いたインタラクションの計測と理解 Invited

藤井慶輔

ヒューマンコミュニケーション基礎研究会（HCS 2024） 2024.3.3

深層強化学習に基づく連続状態空間におけるサッカーの複数選手の行動評価

中原啓, 筒井和詩, 武田一哉, 藤井慶輔

2023年度人工知能学会全国大会（第37回） 2023.6

　 PREV - NEXT 　

<FUJII Keisuke>

Presentations -