2025
P. Cervantes, Y. Sekikawa, I. Sato and K. Shinoda, “Integrating Generative and Contrastive Approaches for Human Action Recognition,” IEEE Access, 2025.
Masahiro Kada, Ryota Yoshihashi, Satoshi Ikehata, Rei Kawakami, and Ikuro Sato, “Robustifying Routers Against Input Perturbations for Sparse Mixture-of-Experts Vision Transformers”, IEEE Open Journal of Signal Processingm 2025.
Qiaoyi Deng, Satoshi Ikehata, Yusuke Sekikawa, and Ikuro Sato, “Regularizing Image Encoders to Generate Bird’s-Eye View Representations for Autonomous Driving Tasks”, PRMU研究会, Jan., 2025. [paper]
2024
Ryo Isobe, Rei Kawakami, Satoshi Ikehata, and Ikuro Sato, “Generative Inference for Object Poses by Regressive-Feature Reconstruction”, IBISML研究会, Dec., 2024. [paper]
Mao Tomita, Ikuro Sato, Rei Kawakami, Nakamasa, Inoue, Satoshi Ikehata, and Masayuki Tanaka, “A Simple Finetuning Strategy Based on Bias-Variance Ratios of Layer-Wise Gradients”, ACCV 2024 (oral). [project]
Tamotsu Kurioka, Teppei Suzuki, Rei Kawakami, and Ikuro Sato, “Transferring Teacher’s Invariance to Student Through Data Augmentation Optimization”, ICONIP 2024. [paper]
内田輝, 吉田悠一, 池畑諭, 佐藤育郎，”不良品検出のためのデワーピング拡散モデル,” MIRU 2024. [paper]
寺内怜央, 佐藤育郎, 川上玲，“汎化改善のためのモデル診断,” MIRU 2024. [paper]
冨田真央, 佐藤育郎, 川上玲, 井上中順, 池畑諭, 田中正行，“深層ネットワークのランダム層選択による転移学習,” MIRU 2024. [paper]
玉山敦也, 池畑諭, 佐藤育郎，“運転負荷予測のための走行画像データセット構築,” MIRU 2024. [paper]
森合遼, 井上中順, 田中正行, 川上玲, 池畑諭, 佐藤育郎，“分布外データの棄却機能を持つモダンホップフィールドネットワーク,” MIRU 2024. [paper]
加太将弘, 吉橋亮太, 池畑 諭, 川上玲, 佐藤育郎，“摂動に対するスパース混合エキスパートモデルの頑健化,” MIRU 2024. [paper]
佐藤 育郎, “自動運転のためのビジョン技術,” チュートリアル講演、MIRU 2024. [slides]
Ryo Moriai, Nakamasa Inoue, Masayuki Tanaka, Rei Kawakami, Satoshi Ikehata, and Ikuro Sato, “Distribution-Aware State Update Rule for Modern Hopfield Networks”, Symbolic-Neural Learning (SNL) 2024.
Yanhao Bao, Tatsukichi Shibuya, Ikuro Sato, Rei Kawakami, Nakamasa Inoue, “Efficient Target Propagation by Deriving Analytical Solution,” AAAI, 2024. [paper]
2023
Yuzhe Hao, Asako Kanezaki, Ikuro Sato, Rei Kawakami and Koichi Shinoda, “Egocentric Human Activities Recognition with Multimodal Interaction Sensing”, IEEE Sensors, vol. 24, no. 5, 7085-7096, 2023.
Tomoya Takahashi, Shingo Yashima, Kohta Ishikawa, Ikuro Sato, Rio Yokota, “Pixel-level Contrastive Learning of Driving Videos with Optical Flow,” CVPR workshop 2023. [paper]
加太 将弘, 吉橋 亮太, 川上 玲, 池畑諭, 佐藤 育郎, “対照学習に基づくMixture of Experts の経路表現学習,” MIRU, 2023. [paper]
J.R. Liang, S. Gongyo, M. Ambai, R. Kawakami, I. Sato, “Learning Non-Uniform Step-Sizes for Neural Network Quantization,” MIRU, 2023. [paper]
磯部凌, 川上 玲, 佐藤 育郎, “回帰器と生成器の協調による視線角度推論,” MIRU, 2023. [paper]
栗岡 保, 鈴木 哲平, 川上 玲, 佐藤 育郎, “Teach the way to deform: 教師モデルが持つ不変性の転移,” MIRU, 2023.[paper]
澁谷辰吉, 井上中順, 川上玲, 佐藤育郎, “二値重み空間でのBinary Neural Networksの学習,” MIRU, 2023. [paper]
J.R. Liang, S. Gongyo, M. Ambai, R. Kawakami, I. Sato, “Learning Non-Uniform Step-Sizes for Neural Network Quantization,” SNL, 2023. [paper]
Masahiro Kada, Ryota Yoshihashi, Rei Kawakami, Satoshi Ikehata, Ikuro Sato, “Path Representation Learning of Mixture of Experts BasedonContrastive Learning”, SNL,2023. [paper]
Ota, Toshihiro; Sato, Ikuro; Kawakami, Rei; Tanaka, Masayuki; Inoue, Nakamasa, “Learning with Partial Forgetting in Modern Hopfield Networks”, AISTATS, 2023. [paper]
Tatsukichi Shibuya, Nakamasa Inoue, Rei Kawakami, and Ikuro Sato, “Fixed-Weight Difference Target Propagation”, AAAI, 2023. [paper]
2022
Hao, Yuzhe; Uto, Kuniaki; Kanezaki, Asako; Sato, Ikuro; Kawakami, Rei; Shinoda, Koichi, “EvIs-Kitchen: Egocentric Human Activities Recognition with Video and Inertial Sensor data”, Multimedia Modeling (MMM) 2023.
Aoyu Li (Tokyo Institute of Technology)*; Ikuro Sato (Tokyo Institute of Technology / Denso IT Laboratory); Kohta Ishikawa (Denso IT Laboratory, Inc.); Rei Kawakami (Tokyo Institute of Technology); Rio Yokota (Tokyo Institute of Technology), “Informative Sample-Aware Proxy for Deep Metric Learning”, ACM MM Asia 2023. (BEST PAPER AWARD) [paper]
Hiroki Naganuma, Kartik Ahuja, Ioannis Mitliagkas, Shiro Takagi, Tetsuya Motokawa, Rio Yokota, Kohta Ishikawa, Ikuro Sato, “Empirical Study on Optimizer Selection for Out-of-Distribution Generalization”, NeurIPS 2022 Workshop on Distribution Shift, 2022. [paper]
Hiroaki Igarashi (DENSO Corporation),* Kenichi Yoneji (DENSO), Kohta Ishikawa (Denso IT Laboratory, Inc.), Rei Kawakami (Tokyo Institute of Technology), Teppei Suzuki (Denso IT Laboratory), Shingo Yashima (Denso IT Laboratory), Ikuro Sato (Tokyo Institute of Technology / Denso IT Laboratory), “Multi-task Curriculum Learning based on Gradient Similarity”, BMVC, 2022. [paper]
緒方貴紀，田中正行，佐藤育郎，“輝度特徴と色特徴の混合率の変化に対する画像分類の整合性評価”，第25回情報論的学習理論ワークショップ(IBIS)，2022. [paper]
Pablo Cervantes, Yusuke Sekikawa, Ikuro Sato, Koichi Shinoda. “Implicit Neural Representations for Variable Length Human Motion Generation,” ECCV, 2022. [paper]
北山翼, 川上玲, 佐藤育郎, 吉橋亮太, 金崎朝子, “球面畳み込みの時間軸拡張による全天球映像からの行動種別の領域分割”, MIRU, 2022.
Wenru Zheng, Rei Kawakami, Ikuro Sato, Ryota Yoshihashi, and Asako Kanezak, “Event Recognition by Audio-Visual Fusion with Omnidirectional Camera and Microphone Array”, MIRU, 2022.
高橋那弥，八嶋晋吾，石川康太，佐藤育郎，横田理央, “走行動画の大規模自己教師あり学習の検討と計画”, MIRU, 2022.
澁谷辰吉, 佐藤育郎, 川上玲, 井上中順, “ランダム行列による固定逆伝播ネットワークを用いた Target Propagation の改良”, MIRU, 2022.
Pablo Cervantes, Yusuke Sekikawa, Ikuro Sato, and Koichi Shinoda, “Implicit Neural Representation Learning for Human Motion Generation”, MIRU, 2022.
Toshihiro Ota, Ikuro Sato, Rei Kawakami, Masayuki Tanaka, and Nakamasa Inoue, “Learning with Partial Forgetting in Modern Hopfield Networks”, MIRU, 2022.
栗岡保, 鈴木哲平, 川上玲1, 佐藤育郎, “複数教師モデルを用いたデータ拡張最適化手法の検討”, MIRU, 2022.
山田陵太, 佐藤育郎, 田中正行, 井上中順, 川上玲, “深層モデルの汎化性能改善を目的とした特徴抽出器の事後学習”, MIRU, 2022.
Jinrong. R. Liang, Shinya Gongyo, Mitsuru Ambai, Rei Kawakami, and Ikuro Sato, “Learning of Non-Uniform Step-Sizes for Neural Network Quantization”, MIRU, 2022.
髙山啓太, 鈴木哲平, 佐藤育郎, 川上玲, 宇都有昭, 篠田浩一, “滑らかな転移学習による汎化性能の改善”, MIRU, 2022.
チェンマーク, 川上玲, 佐藤育郎, 苗村健, “生成的特徴量の角度依存性に着目した単画像からの視点角度推定の精度向上”, MIRU, 2022.
Li Aoyu, 佐藤育郎, 石川康太, 川上玲, 横田理央, “Informative Sample-Aware Proxy for Deep Metric Learning”, MIRU, 2022.
Shingo Yashima, Teppei Suzuki, Kohta Ishikawa, Ikuro Sato, and Rei Kawakami, “Feature Space Particle Inference for Neural Network Ensembles”, MIRU, 2022.
Ikuro Sato, Ryota Yamada, Masayuki Tanaka, Nakamasa Inoue, Rei Kawakami. PoF: Post-Training of Feature Extractor for Improving Generalization. International Conference on Machine Learning (ICML), 2022. [paper]
Shingo Yashima, Teppei Suzuki, Kohta Ishikawa, Ikuro Sato, Rei Kawakami. Feature Space Particle Inference for Neural Network Ensembles. International Conference on Machine Learning (ICML), 2022. [paper]
チェン マーク (東京大)・川上 玲・佐藤 育郎 (東工大/デンソーITラボラトリ)・苗村 健 (東京大), “生成的特徴量の角度依存性に着目した視点角度推定の精度向上, ” CVIM2022. [paper]
2021
Pablo Cervantes, Yusuke Sekikawa, Ikuro Sato, Koichi Shinoda. “Implicit Neural Representations for Variable Length Human Motion Generation,” arXiv:2203.13694, 2022. [paper]
Keita Takayama, Ikuro Sato, Teppei Suzuki, Rei Kawakami, Kuniaki Uto, Koichi Shinoda. “Smooth Transfer Learning for Source-to-Target Generalization,” NeurIPS 2021 Workshop on Distribution Shifts, 2021. [paper]
Ikuro Sato, Guoqing Liu, Kohta Ishikawa, and Masayuki Tanaka, “Does End-to-End Trained Deep Model Always Perform Better than Non-End-to-End Counterpart?”, Electronic Imaging 2021. [paper]
Nakamasa Inoue, Ryota Yamada, Rei Kawakami, Ikuro Sato, “Disentangling Latent Groups of Factors”, International Conference on Image Processing (ICIP), 2021. [paper]
Yuto Kodama, Yinang Wang, Rei Kawakami, Takeshi Naemura. “Open-set Recognition with Supervised Contrastive Learning.” 17th International Conference on Machine Vision and Applications (MVA), 2021. [paper]
Hajime Oi, Rei Kawakami, Takeshi Naemura. “Analysis of Evaluation Metrics with the Distance between Positive Pairs and Negative Pairs in Deep Metric Learning”, 17th International Conference on Machine Vision and Applications (MVA), 1-5. 2021. [paper]
Miho Kitamura, Hiroki Sato, Rei Kawakami, Natsuyo Yanagi, Takeshi Naemura, Yasufumi Sawada. “Index for Measuring Perceptual Similarity of Pharmaceutical Blister Packages on the Basis of Deep Features.” 画像の認識・理解シンポジウム(MIRU2021), I21-21, (2021.7).
川上玲, OUR Shurijoみんなの首里城デジタル復元プロジェクト―記憶の中の首里城－. O plus E 光学・画像専門誌, 2021年11・12月号.
2020
Wen Shao, Rei Kawakami, Ryota Yoshihashi, Shaodi You, Hidemichi Kawase, Takeshi Naemura. “Cattle detection and counting in UAV images based on convolutional neural networks.” International Journal of Remote Sensing 41 (1), 31-52. 2020.
Yutaro Honda, Rei Kawakami, Takeshi Naemura. “RNN-based Motion Prediction in Competitive Fencing Considering Interaction between Players”
In Proc. of British Machine Vision Conference (BMVC), September, 2020. [paper]
Teppei Suzuki and Ikuro Sato. “Adversarial Transformations for Semi-Supervised Learning.” AAAI, 2020. [paper]
鈴木理紗, 川上 玲, カラーヌワット タリン, 北本 朝展, 中澤 敏明, 苗村 健. Bi-LSTMを用いた中古日本語の文境界推定. 人文科学とコンピュータシンポジウム「じんもんこん」2020論文集, 17-22. (2020.12).
本田悠太郎, 川上玲, 苗村健. フェンシングにおける選手間相互作用を考慮したRNNによる姿勢予測. 統計関連学会連合大会（招待講演）, 1CPM1 (2020.9).
邵文, 川上玲, 苗村健. 映像生成による時間順序の並べ替えで学習した時空間コンテキストに基づく異常検知. 画像の認識・理解シンポジウム(MIRU2020), OS1-1B-2 (口頭発表). (2020.8).
本田悠太郎, 川上玲, 苗村健. フェンシングにおける選手間相互作用を考慮したRNNによる姿勢予測. 画像の認識・理解シンポジウム(MIRU2020), OS3-3B-3 (口頭発表) (2020.8).
Chanya Kukulprasong, 川上玲, 苗村健. 画像と音声の特徴マッチングによる物体およびシーンを考慮した環境音の生成. 画像の認識・理解シンポジウム(MIRU2020), IS1-1-11 (2020.8).
川上玲, OUR Shurijoみんなの首里城デジタル復元プロジェクト―記憶の収集－. 「写真測量とリモートセンシング」, 日本写真測量学会誌, 2021年3月号.
川上玲, みんなの首里城デジタル復元プロジェクト～建物にある記憶をつなぐ～. 「建築と社会」, 日本建築協会学会誌, 2020年12月号.