Publications

Refereed Journal Papers

Xiaotong Ji, Daiki Suehiro, Seiichi Uchida, “Paired Contrastive Feature for Highly Reliable Signature Verification”, Pattern Recognition, accepted．

Heon Song, Nariaki Mitsuo, Seiichi Uchida, Daiki Suehiro, "No Regret Sample Selection with Noisy Labels", Machine Learning, accepted (code implemented by Heon Song).

Yan Zheng, Yuchen Zheng, Daiki Suehiro, Seiichi Uchida, "Top-Rank Convolutional Neural Network and its Application to Medical Image-based Diagnosis", Pattern Recognition, vol.120, 2021.12. (preprint version) (Publisher site)

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, Shuji Yamamoto, Kenichi Bannai, Akiko Takeda, "Theory and Algorithms for Shapelet-based Multiple-Instance Learning", Neural Computation, Volume 32, Issue 8, pp.1580-1613, 2020.8. (preprint version, code)

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, "Efficient Reformulation of 1-norm Ranking SVM", IEICE Transactions on Information and Systems, Vol.E101-D, No.3, pp.719--729, 2018. (paper)

末廣大貴，畑埜晃平，坂内英夫，瀧本英二，竹田正幸，“SVM による 2 部ランキング学習を用いたコンピュータ将棋における評価関数の学習”，電子情報通信学会論文誌 D, 情報・システム J97-D(3), pp.593--600, 2014.3.

Refereed Conference Papers

Shinnnosuke Matsuo, Ryoma Bise, Seiichi Uchida, Daiki Suehiro, "Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization", Proceedings of the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), to appear.

Daiki Suehiro, Eiji Takimoto, "Simplified and Unified Analysis of Various Learning Problems by Reduction to Multiple-Instance Learning", Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022), 2022.8, PMLR 180:1896-1906. (paper)

Xiaotong Ji, Yan Zheng, Daiki Suehiro and Seiichi Uchida, "Revealing Reliable Signatures by Learning Top-Rank Pairs", Proceedings of the 15th IAPR International Workshop on Document Analysis Systems (DAS2022), pp.323--337, 2022.5, accepted as an oral presentation, Best Student Paper Award. (paper)

Yan Zheng, Daiki Suehiro, Seiichi Uchida, "Top-Rank Learning Robust to Outliers", Proceedings of the 28th International Conference on Neural Information Processing (ICONIP 2021), pp.608--619, accepted as an oral presentation.

Kazuma Fujii, Daiki Suehiro, Kazuya Nishimura, and Ryoma Bise, "Cell Detection from Imperfect Annotation by Pseudo Label Selection Using P-classification", Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI2021), pp. 425--434.

Heon Song, Daiki Suehiro, Seiichi Uchida, "Adaptive Aggregation of Arbitrary Online Trackers with a Regret Bound", Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp.681--689, 2020.3. (paper, code implemented by Heon Song)

Xiaotong Ji, Yuchen Zheng, Daiki Suehiro, Seiichi Uchida, "Optimal Rejection Function Meets Character Recognition Tasks", Proceedings of the 5th Asian Conference on Pattern Recognition, pp.169--183, 2019.11.

Yan Zheng, Yuchen Zheng, Wataru Ohyama, Daiki Suehiro, Seiichi Uchida, "RankSVM for Offline Signature Verification", Proceedings of the 15th International Conference on Document Analysis and Recognition, pp.928--933, 2019.9.

Takuro Karamatsu, Daiki Suehiro, Seiichi Uchida, "Logo Design Analysis by Ranking", Proceedings of the 15th International Conference on Document Analysis and Recognition, pp.1482--1487, 2019.9.

Daiki Suehiro, Yuta Taniguchi, Atsushi Shimada, Hiroaki Ogata, “Face-to-Face Teaching Analytics: Extracting Teaching Activities from E-book Logs via Time-Series Analysis”, Proceedings of the 17th IEEE International Conference on Advanced Learning Technologies, pp.267--268, 2017.7.

Yuta Taniguchi, Daiki Suehiro, Atsushi Shimada and Hiroaki Ogata, “Revealing Hidden Impression Topics in Students’ Journals Based on Nonnegative Matrix Factorization”. Proceedings of the 17th IEEE International Conference on Advanced Learning Technologies, pp.298--300, 2017.7.

Hiroaki Ogata, Yuta Taniguchi, Daiki Suehiro, Atsushi Shimada, Misato Oi, Fumiya Okubo, Masanori Yamada, Kentaro Kojima, “M2B System: A Digital Learning Platform for Traditional Classrooms in University”, Practitioner Track Proceedings of the 7th International Conference on Learning Analytics & Knowledge, pp.155--162, 2017.3.

Xinyu Fu, Atsushi Shimada, Hiroaki Ogata, Yuta Taniguchi, Daiki Suehiro, “Real-time learning analytics for C programming language courses”,  Proceedings of the 7th International Conference on Learning Analytics & Knowledge, pp.280--288, 2017.3.

Daiki Suehiro, Kohei Hatano, Shuji Kijima, Eiji Takimoto, Kiyohito Nagano, “Online Prediction under Submodular Constraints”, Proceedings of the 23rd International Conference on Algorithmic Learning Theory 2012, pp.260--274, 2012.10. (paper)

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, “Approximate Reduction from AUC Maximization to 1-norm Soft Margin Optimization”, Proceedings of the 22nd International Conference on Algorithmic Learning Theory 2011, pp.324--337, 2011.10.

Refereed Workshop Papers

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, Shuji Yamamoto, Kenichi Bannai, Akiko Takeda, "Learning theory and algorithms for shapelets and other local features", NIPS Time Series Workshop 2017, 2017.12. (accepted as an oral presentation, rate=6/53)

Daiki Suehiro, Kengo Kuwahara, Kohei Hatano, Eiji Takimoto, “Time Series Classification Based on Random Shapelets”, NIPS Time Series Workshop 2016, 2016.12. (paper)

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, Shuji Kijima, Kiyohito Nagano, “Online Prediction over Base Polyhedra”, NIPS 2012 Workshop on Discrete Optimization in Machine Learning (DISCML), 2012.12.

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, Approximate Reduction from AUC Maximization to 1-norm Soft Margin Optimization, NIPS 2011 Workshop on Computational Trade-offs in Statistical Learning (COST), 2011.12.

Preprints

Heon Song, Nariaki Mitsuo, Seiichi Uchida, Daiki Suehiro, "No Regret Sample Selection with Noisy Labels", arXiv preprint 2003.03179, 2020. (paper, code implemented by Heon Song)

Domestic conference and others

斉藤優也, 内田誠一, 末廣大貴, 適応的データバランス調整～オンライン予測の理論に基づくアプローチ～, 電気・情報関係学会九州支部連合大会講演論文集, 04-1P-06, 2022年9月16日. （電子情報通信学会九州支部連合大会講演奨励賞受賞論文）

本田康祐, 内田誠一，末廣大貴，識別器の斟酌学習，電子情報通信学会技術研究報告, PRMU2021-11, 2021.8.

Heon Song, Daiki Suehiro, Seiichi Uchida，任意のオンライントラッカの統合法，画像の認識・理解シンポジウム（MIRU2020）, 2020.8.

Shee Chean Fei, Daiki Suehiro, Seiichi Uchida, GANを用いた局所パターン生成, 画像の認識・理解シンポジウム（MIRU2020）, 2020. 8. (Short oral presentation)

末廣大貴，マルチインスタンス学習への再定式化に基づく理論的汎化誤差導出，情報論的学習理論ワークショップ（IBIS2019），2019.11.

満尾成亮, 末廣大貴, 内田誠一，"オンラインエキスパート選択問題としての適応的学習率調整"，画像の認識・理解シンポジウム（MIRU2019），2019.7. (Short oral presentation)

ソンホン, 末廣大貴, 内田誠一，"オンライントラッカの統合について"，画像の認識・理解シンポジウム（MIRU2019)，2019.7 (Poster Presentation)

八尋俊希，末廣大貴，本館利佳，鈴木利治，内田誠一，"弱教師学習問題における最適局所特徴抽出および樹状突起スパイン検出への応用"，医用画像研究会，2019.1.

角淳之介，末廣大貴，加藤貴昭，内田誠一，"投手の打ちづらさとは何か～機械学習に基づく投球印象解析～"，スポーツ情報処理時限研究会，2018.12.

八尋俊希, 末廣大貴, 内田誠一, "Shapeletに基づいた文字認識",

電気・情報関係学会九州支部連合大会講演論文集（琉球大学，沖縄県中頭郡）, 13-2P-04, 2017.9. (H29年度電子情報通信学会九州支部講演奨励賞受賞論文)

Huiyong Li, Tomoyuki Tsuchiya, Daiki Suehiro, Yuta Taniguchi, Atsushi Shimada, Yubun Suzuki, Hiroshi Ohashi, Hiroaki Ogata, “Behavioral Analysis and Visualization on Learning Logs from CALL Courses”, 第 31 回人工知能学会全国大会, 2017.5.

末廣大貴，毛利孝佑，谷口雄太，大久保文哉，島田敬士，緒方広明，“教育データのオープン化に向けて”，信学技報, vol.116, no.259, PRMU2016-105, pp.79--84, 2016.10.

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, “Efficient AUC Maximization by Approximate Reduction of Ranking SVMs”，The 4th Asian Conference on Machine Learning (ACML 2012), 2012.11. (only poster presentation)

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, “Efficient AUC Maximization by Approximate Reduction of Ranking SVMs”, IEICE technical report. IBISML, Information-based induction sciences and machine learning 112(279), pp.243--249, 2012.10.

Daiki Suehiro, Kohei Hatano, Eiji Takimoto, “Approximate Reduction from AUC Maximization to 1-norm Soft Margin Optimization”, IEICE technical report. IBISML, Information-based induction sciences and machine learning 111(275), pp.39--46, 2011.11. (Award: Honorable Mention)

末廣大貴，畑埜晃平，坂内英夫，瀧本英二，竹田正幸，“カーネル法を用いたコンピュータ将棋の評価関数の学習”，ゲームプログラミングワークショップ 2010 論文集 2010(12)，pp 23--27, 2010.11.（査読あり）

Patent

末廣大貴，大串俊明，"時系列データ波形分析装置、方法、及びプログラム"，Patent number: P2017-138929A, Application number: P2016-21313.

Daiki Suehiro, Toshiaki Ohgushi, "TIME-SERIES DATA WAVEFORM ANALYSIS DEVICE, METHOD THEREFOR AND NON-TRANSITORY COMPUTER READABLE MEDIUM", Patent number: 20170227584, Application number: 15261165.