Search Results for author: Keisuke Fujii

Found 37 papers, 19 papers with code

Action valuation of on- and off-ball soccer players based on multi-agent deep reinforcement learning

no code implementations29 May 2023 Hiroshi Nakahara, Kazushi Tsutsui, Kazuya Takeda, Keisuke Fujii

In this paper, we propose a method of valuing possible actions for on- and off-ball soccer players in a single holistic framework based on multi-agent deep reinforcement learning.


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

no code implementations22 May 2023 Keisuke Fujii, Kazushi Tsutsui, Atom Scott, Hiroshi Nakahara, Naoya Takeishi, Yoshinobu Kawahara

In the experiments, using chase-and-escape and football tasks with the different dynamics between the unknown source and target environments, we show that our approach achieved a balance between the reproducibility and the generalization ability compared with the baselines.

Dynamic Time Warping reinforcement-learning +1

Estimation of control area in badminton doubles with pose information from top and back view drone videos

no code implementations7 May 2023 Ning Ding, Kazuya Takeda, Wenhui Jin, Yingjiu Bei, Keisuke Fujii

In this work, we present the first annotated drone dataset from top and back views in badminton doubles and propose a framework to estimate the control area probability map, which can be used to evaluate teamwork performance.

Visual Tracking

Transformer-Based Neural Marked Spatio Temporal Point Process Model for Football Match Events Analysis

1 code implementation18 Feb 2023 Calvin C. K. Yeung, Tony Sit, Keisuke Fujii

However, most sports sequential events modeling methods and performance metrics approaches could be incomprehensive in dealing with such large-scale spatiotemporal data (in particular, temporal process), thereby necessitating a more comprehensive spatiotemporal model and a holistic performance metric.

Point Processes

Predictive World Models from Real-World Partial Observations

1 code implementation12 Jan 2023 Robin Karlsson, Alexander Carballo, Keisuke Fujii, Kento Ohtani, Kazuya Takeda

By extending HVAEs to cases where complete ground truth states do not exist, we facilitate continual learning of spatial prediction as a step towards realizing explainable and comprehensive predictive world models for real-world mobile robotics applications.

Continual Learning Reinforcement Learning (RL)

Location analysis of players in UEFA EURO 2020 and 2022 using generalized valuation of defense by estimating probabilities

1 code implementation30 Nov 2022 Rikuhei Umemoto, Kazushi Tsutsui, Keisuke Fujii

Using the open-source location data of all players in broadcast video frames in football games of men's Euro 2020 and women's Euro 2022, we investigated the effect of the number of players on the prediction and validated our approach by analyzing the games.

Estimating the Effect of Team Hitting Strategies Using Counterfactual Virtual Simulation in Baseball

no code implementations4 Jun 2022 Hiroshi Nakahara, Kazuya Takeda, Keisuke Fujii

The weighted on base average (wOBA) is well known as a measure of an batter's hitting contribution.

Evaluation of creating scoring opportunities for teammates in soccer via trajectory prediction

1 code implementation4 Jun 2022 Masakiyo Teranishi, Kazushi Tsutsui, Kazuya Takeda, Keisuke Fujii

However, it has remained difficult to evaluate an attacking player without receiving the ball, and to reveal how movement contributes to the creation of scoring opportunities for teammates.

Trajectory Prediction

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

no code implementations4 Jun 2022 Keisuke Fujii, Koh Takeuchi, Atsushi Kuribayashi, Naoya Takeishi, Yoshinobu Kawahara, Kazuya Takeda

Evaluation of intervention in a multi-agent system, e. g., when humans should intervene in autonomous driving systems and when a player should pass to teammates for a good shot, is challenging in various engineering and scientific fields.

Autonomous Driving

Parametric t-Stochastic Neighbor Embedding With Quantum Neural Network

no code implementations9 Feb 2022 Yoshiaki Kawase, Kosuke Mitarai, Keisuke Fujii

In this paper, we propose to use quantum neural networks for parametric t-SNE to reflect the characteristics of high-dimensional quantum data on low-dimensional data.

BIG-bench Machine Learning Data Visualization +1

ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignment

1 code implementation24 Nov 2021 Robin Karlsson, Tomoki Hayashi, Keisuke Fujii, Alexander Carballo, Kento Ohtani, Kazuya Takeda

Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data.

Contrastive Learning Domain Generalization +4

How does AI play football? An analysis of RL and real-world football strategies

no code implementations24 Nov 2021 Atom Scott, Keisuke Fujii, Masaki Onishi

Recent advances in reinforcement learning (RL) have made it possible to develop sophisticated agents that excel in a wide range of applications.

Reinforcement Learning (RL)

Quantum tangent kernel

no code implementations4 Nov 2021 Norihito Shirai, Kenji Kubo, Kosuke Mitarai, Keisuke Fujii

In this work, we explore a quantum machine learning model with a deep parameterized quantum circuit and aim to go beyond the conventional quantum kernel method.

BIG-bench Machine Learning Quantum Machine Learning

Evaluation of soccer team defense based on prediction models of ball recovery and being attacked: A pilot study

no code implementations17 Mar 2021 Kosuke Toda, Masakiyo Teranishi, Keisuke Kushiro, Keisuke Fujii

Results show that the proposed classifiers predicted the true events (mean F1 score $>$ 0. 483) better than the existing classifiers which were based on rare events or goals (mean F1 score $<$ 0. 201).

Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections

no code implementations19 Feb 2021 Naoya Takeishi, Keisuke Fujii, Koh Takeuchi, Yoshinobu Kawahara

Extracting coherent patterns is one of the standard approaches towards understanding spatio-temporal data.

Data-driven Analysis for Understanding Team Sports Behaviors

no code implementations15 Feb 2021 Keisuke Fujii

This survey focuses on data-driven analysis for quantitative understanding of invasion team sports behaviors 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.

Variational Quantum Algorithms

1 code implementation16 Dec 2020 M. Cerezo, Andrew Arrasmith, Ryan Babbush, Simon C. Benjamin, Suguru Endo, Keisuke Fujii, Jarrod R. McClean, Kosuke Mitarai, Xiao Yuan, Lukasz Cincio, Patrick J. Coles

Applications such as simulating complicated quantum systems or solving large-scale linear algebra problems are very challenging for classical computers due to the extremely high computational cost.

Supervised sequential pattern mining of event sequences in sport to identify important patterns of play: an application to rugby union

1 code implementation29 Oct 2020 Rory Bunker, Keisuke Fujii, Hiroyuki Hanada, Ichiro Takeuchi

Given a set of sequences comprised of time-ordered events, sequential pattern mining is useful to identify frequent subsequences from different sequences or within the same sequence.

Sequential Pattern Mining

Quantum error mitigation as a universal error-minimization technique: applications from NISQ to FTQC eras

no code implementations8 Oct 2020 Yasunari Suzuki, Suguru Endo, Keisuke Fujii, Yuuki Tokunaga

In the early years of fault-tolerant quantum computing (FTQC), it is expected that the available code distance and the number of magic states will be restricted due to the limited scalability of quantum devices and the insufficient computational power of classical decoding units.

Quantum Physics

Policy learning with partial observation and mechanical constraints for multi-person modeling

2 code implementations7 Jul 2020 Keisuke Fujii, Naoya Takeishi, Yoshinobu Kawahara, Kazuya Takeda

Extracting the rules of real-world biological multi-agent behaviors is a current challenge in various scientific and engineering fields.

Imitation Learning

Quantum self-learning Monte Carlo with quantum Fourier transform sampler

1 code implementation28 May 2020 Katsuhiro Endo, Taichi Nakamura, Keisuke Fujii, Naoki Yamamoto

The self-learning Metropolis-Hastings algorithm is a powerful Monte Carlo method that, with the help of machine learning, adaptively generates an easy-to-sample probability distribution for approximating a given hard-to-sample distribution.

Quantum Physics

Power-law intensity distribution in $γ$-decay cascades

1 code implementation24 May 2020 Keisuke Fujii, Julian C. Berengut

We show that the distribution of $\gamma$-decay intensities from heavy nuclei follows a power law.

Nuclear Theory

Succinct Trit-array Trie for Scalable Trajectory Similarity Search

1 code implementation21 May 2020 Shunsuke Kanda, Koh Takeuchi, Keisuke Fujii, Yasuo Tabei

To address this problem, we present the trajectory-indexing succinct trit-array trie (tSTAT), which is a scalable method leveraging LSH for trajectory similarity searches.

Physically-interpretable classification of biological network dynamics for complex collective motions

1 code implementation13 May 2019 Keisuke Fujii, Naoya Takeishi, Motokazu Hojo, Yuki Inaba, Yoshinobu Kawahara

A fundamental question addressed here pertains to the classification of collective motion network based on physically-interpretable dynamical properties.

Classification General Classification

The International Linear Collider: A Global Project

no code implementations5 Mar 2019 Philip Bambade, Tim Barklow, Ties Behnke, Mikael Berggren, James Brau, Philip Burrows, Dmitri Denisov, Angeles Faus-Golfe, Brian Foster, Keisuke Fujii, Juan Fuster, Frank Gaede, Paul Grannis, Christophe Grojean, Andrew Hutton, Benno List, Jenny List, Shinichiro Michizono, Akiya Miyamoto, Olivier Napoly, Michael Peskin, Roman Poeschl, Frank Simon, Jan Strube, Junping Tian, Maksym Titov, Marcel Vos, Andrew White, Graham Wilson, Akira Yamamoto, Hitoshi Yamamoto, Kaoru Yokoya

In this report, we review of all aspects of the ILC program: the physics motivation, the accelerator design, the run plan, the proposed detectors, the experimental measurements on the Higgs boson, the top quark, the couplings of the W and Z bosons, and searches for new particles.

High Energy Physics - Experiment High Energy Physics - Phenomenology Accelerator Physics

Methodology for replacing indirect measurements with direct measurements

no code implementations31 Dec 2018 Kosuke Mitarai, Keisuke Fujii

However, in certain cases, the indirect measurement can be reduced to the direct measurement, where a quantum state is destructively measured.

Quantum Physics

Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables

1 code implementation30 Aug 2018 Keisuke Fujii, Yoshinobu Kawahara

In this paper, we formulate Koopman spectral analysis for NLDSs with structures among observables and propose an estimation algorithm for this problem.

Robust Regression for Automatic Fusion Plasma Analysis based on Generative Modeling

no code implementations3 Aug 2018 Keisuke Fujii, Chihiro Suzuki, Masahiro Hasuo

The first step to realize automatic experimental data analysis for fusion plasma experiments is fitting noisy data of temperature and density spatial profiles, which are obtained routinely.


Quantum Circuit Learning

5 code implementations2 Mar 2018 Kosuke Mitarai, Makoto Negoro, Masahiro Kitagawa, Keisuke Fujii

Hybridizing a low-depth quantum circuit and a classical computer for machine learning, the proposed framework paves the way toward applications of near-term quantum devices for quantum machine learning.

Quantum Physics

High-threshold fault-tolerant quantum computation with analog quantum error correction

no code implementations1 Dec 2017 Kosuke Fukui, Akihisa Tomita, Atsushi Okamoto, Keisuke Fujii

To reduce this requirement, we propose a high-threshold fault-tolerant quantum computation with GKP qubits using topologically protected measurement-based quantum computation with the surface code.

Quantum Physics

Cannot find the paper you are looking for? You can Submit a new open access paper.