Achievements
Our research achievements and publications.
2026
Journal Articles
6DoF Pose Estimation of Deformed AR Markers and Implementation on Embedded Boards
**Notice:**Notice for the use of this material.The copyright of this material is retained by the Information Processing Society of Japan (IPSJ). This material is published here with the permission of IPSJ. Please comply with the Copyright Act of Japan and the IPSJ Code of Ethics in the use of this material.
変形ARマーカの3次元位置・姿勢推定と組み込みボードへの実装
**注意:**ここに掲載した著作物の利用に関する注意 本著作物の著作権は情報処理学会に帰属します。本著作物は著作権者である情報処理学会の許可のもとに掲載するものです。ご利用に当たっては「著作権法」ならびに「情報処理学会倫理綱領」に従うことをお願いいたします。
Domestic Conferences
Basic Study on Generated Image Detection Focusing on Geometric Inconsistencies Revealed by Monocular Depth Estimation
Published in IEICE General Conference.
単眼深度推定により顕在化する幾何学的不整合に着目した生成画像検出の基礎検討
単眼深度推定により顕在化する幾何学的不整合に着目した生成画像検出の基礎検討
2025
Journal Articles
Incorporating Image Prediction Model in Value Function for Deep Reinforcement Learning
Incorporating Image Prediction Model in Value Function for Deep Reinforcement Learning
End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models
Published in IEEE Access, vol. 13, pp. 73355 - 73361.
Improving Deepfake Detection with Wavelet Vision Transformer using Self-Supervised Learning
Improving Deepfake Detection with Wavelet Vision Transformer using Self-Supervised Learning
画像予測モデルを導入した価値関数に基づく深層強化学習
画像予測モデルを導入した価値関数に基づく深層強化学習
End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models
End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models
自己教師あり学習を導入したWavelet Vision TransformerによるDeepfake検出の高精度化
自己教師あり学習を導入したWavelet Vision TransformerによるDeepfake検出の高精度化
International Conferences
Enhancing Anomaly Detection Accuracy with Conditional CutPaste
Enhancing Anomaly Detection Accuracy with Conditional CutPaste
Aesthetic Quality Assessment of Images Using Text Tags with CLIP
Aesthetic Quality Assessment of Images Using Text Tags with CLIP
Enhancing Anomaly Detection Accuracy with Conditional CutPaste
Enhancing Anomaly Detection Accuracy with Conditional CutPaste
Aesthetic Quality Assessment of Images Using Text Tags with CLIP
Aesthetic Quality Assessment of Images Using Text Tags with CLIP
Domestic Conferences
Acceleration of Position and Pose Estimation for Deformed AR Markers
Acceleration of Position and Pose Estimation for Deformed AR Markers
High-Speed and High-Accuracy 3D Position and Pose Estimation of Deformed AR Markers and Implementation on Embedded Boards
High-Speed and High-Accuracy 3D Position and Pose Estimation of Deformed AR Markers and Implementation on Embedded Boards
Enhancing Anomaly Detection Accuracy via Local Expansion-Based Anomaly Generation with Self-Supervised Learning
Enhancing Anomaly Detection Accuracy via Local Expansion-Based Anomaly Generation with Self-Supervised Learning
Integrating Image Prediction Model into Saliency-guided Q-Networks for Reinforcement Learning
Integrating Image Prediction Model into Saliency-guided Q-Networks for Reinforcement Learning
Acceleration of Machine Unlearning Based on Selective Destructive Forgetting
Acceleration of Machine Unlearning Based on Selective Destructive Forgetting
Improving Anomaly Detection with Conditional CutPaste
Improving Anomaly Detection with Conditional CutPaste
An experimental study to compare the performance of machine unlearning methods with multiple datasets
An experimental study to compare the performance of machine unlearning methods with multiple datasets
Lightweight and Fast Framework for Image Compression, Restoration, and Recognition
Lightweight and Fast Framework for Image Compression, Restoration, and Recognition
Aesthetic Quality Assessment of Images Using Text Tags with CLIP
Aesthetic Quality Assessment of Images Using Text Tags with CLIP
変形ARマーカの高速，高精度な3次元位置・姿勢推定と組み込みボードへの実装
変形ARマーカの高速，高精度な3次元位置・姿勢推定と組み込みボードへの実装
自己教師あり学習を導入した局所拡張型異常生成による異常検知の高精度化
自己教師あり学習を導入した局所拡張型異常生成による異常検知の高精度化
視覚強化学習における画像予測モデルを導入した顕著性誘導Qネットワーク
視覚強化学習における画像予測モデルを導入した顕著性誘導Qネットワーク
複数データセットを用いたマシンアンラーニング手法の性能比較に関する実験的検討
複数データセットを用いたマシンアンラーニング手法の性能比較に関する実験的検討
2024
Domestic Conferences
High-Speed and High-Accuracy Pose Estimation of Deformed AR Markers
High-Speed and High-Accuracy Pose Estimation of Deformed AR Markers
End-to-End Learning of Image Compression/Restoration and Recognition Models
End-to-End Learning of Image Compression/Restoration and Recognition Models
2023
Domestic Conferences
Future Image Prediction Model and Reinforcement Learning with Time-Weighted Value Functions
Future Image Prediction Model and Reinforcement Learning with Time-Weighted Value Functions
Prediction of C-Space for Motion Planning in Dynamic Environments
Prediction of C-Space for Motion Planning in Dynamic Environments
Reinforcement Learning Based on Value Functions with Time Series Prediction Models
Reinforcement Learning Based on Value Functions with Time Series Prediction Models
Motion Planning for Collaborative Robots Based on Human Pose Prediction
Motion Planning for Collaborative Robots Based on Human Pose Prediction
Improving Deepfake Detection with Wavelet Vision Transformer using Self-Supervised Learning
Improving Deepfake Detection with Wavelet Vision Transformer using Self-Supervised Learning
動的環境における動作計画のための C-space の予測
動的環境における動作計画のための C-space の予測
未来画像予測モデルと時間重み付けを導入した価値関数に基づく強化学習
未来画像予測モデルと時間重み付けを導入した価値関数に基づく強化学習
自己教師あり学習を導入したWavelet Vision TransformerによるDeepfake検出の高精度化
自己教師あり学習を導入したWavelet Vision TransformerによるDeepfake検出の高精度化
2022
Domestic Conferences
3D Position and Pose Estimation of Deformed AR Markers Using Machine Learning
3D Position and Pose Estimation of Deformed AR Markers Using Machine Learning
Vox2C-Space: Machine Learning-Based C-Space Generation for Motion Planning
Vox2C-Space: Machine Learning-Based C-Space Generation for Motion Planning
Path Planning Based on Machine Learning
Path Planning Based on Machine Learning
Image Recognition for Edge Computing
Image Recognition for Edge Computing
Vox2C-space:動作計画のための機械学習に基づくC-spaceの生成
Vox2C-space:動作計画のための機械学習に基づくC-spaceの生成
2021
Domestic Conferences
Position and Pose Estimation of Deformed AR Markers Using Machine Learning
Position and Pose Estimation of Deformed AR Markers Using Machine Learning
Motion Planning Based on Configuration Spatio-Temporal for Dynamic Environments
Motion Planning Based on Configuration Spatio-Temporal for Dynamic Environments
Anomaly Detection Based on 3D Pose Estimation Information
Anomaly Detection Based on 3D Pose Estimation Information
Improving Future Image Generation with PredNet Using Motion Information
Improving Future Image Generation with PredNet Using Motion Information
2020
Domestic Conferences
Distance Image Inpainting Based on VAE and Application to Object Recognition
Distance Image Inpainting Based on VAE and Application to Object Recognition
Distance Image Inpainting Using Variational Autoencoders
Distance Image Inpainting Using Variational Autoencoders
2019
Domestic Conferences
Path Planning for Mobile Robots Considering Dynamic Environments
Path Planning for Mobile Robots Considering Dynamic Environments