発表論文

査読付き論文誌・国際会議

2024

Taiga Kashima, Ikki Kishida, Ayako Amma, Hideki Nakayama,
"FedFit: Server Aggregation Through Linear Regression in Federated Learning",
IEEE Access, Vol. 12, pp. 22803-22812, 2024.

Kai Katsumata, Duc Minh Vo, Tatsuya Harada, Hideki Nakayama,
"Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data",
In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2024.

Kai Katsumata, Duc Minh Vo, Bei Liu, Hideki Nakayama,
"Revisiting Latent Space of GAN Inversion for Robust Real Image Editing",
In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2024.

Kai Katsumata, Duc Minh Vo, Hideki Nakayama,
"Label Augmentation as Inter-class Data Augmentation for Conditional Image Synthesis with Imbalanced Data",
In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2024.

2023

Jiaxuan Li, Duc Minh Vo, Hideki Nakayama,
"Partition-and-Debias: Agnostic Biases Mitigation via a Mixture of Biases-Specific Experts",
In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.

Jan Zdenek, Hideki Nakayama,
"Handwritten Text Generation with Character-specific Encoding for Style Imitation",
In Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR), pp.313-329, 2023.

Erica Kido Shimomoto, Edison Marrese-Taylor, Hiroya Takamura, Ichiro Kobayashi, Hideki Nakayama, Yusuke Miyao,
"Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding",
Findings of the Association for Computational Linguistics: ACL 2023, 2023.
pdf

KuanChao Chu, Hideki Nakayama,
"Two-Path Object Knowledge Injection For Detecting Novel Objects With Single-Stage Dense Detector",
IEICE Transactions on Information and Systems, Vol.E106-D, No.11, pp.-, 2023. (in press)

Duc Minh Vo, Quoc-An Luong, Akihiro Sugimoto, Hideki Nakayama,
"A-CAP: Anticipation Captioning with Commonsense Knowledge",
In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp.10824-10833, 2023.
pdf

Yi-Pei Chen, An-Zi Yen, Hen-Hsen Huang, Hideki Nakayama, Hsin-Hsi Chen,
"LED: A Dataset for Life Event Extraction from Dialogs",
Findings of the Association for Computational Linguistics: EACL 2023, pp.384-398, 2023.
pdf

Rui Yang, Duc Minh Vo, Hideki Nakayama,
"Indirect Adversarial Losses via an Intermediate Distribution for Training GANs",
In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp.4641-4650, 2023.
pdf

2022

Hong Chen, Rujun Han, Te-Lin Wu, Hideki Nakayama and Nanyun Peng,
“Character-Centric Story Visualization via Visual Planning and Token Alignment”,
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.8259-8272, 2022.
pdf

Hong Chen, Duc Minh Vo, Hiroya Takamura, Yusuke Miyao, Hideki Nakayama,
“StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning”,
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.1739-1753, 2022.
pdf

Yuxuan Wu, Hideki Nakayama,
“Weakly Supervised Formula Learner for Solving Mathematical Problems”,
In Proceedings of the International Conference on Computational Linguistics (COLING), pp.1743–1752, 2022.
pdf

Rui Yang, Duc Minh Vo, Hideki Nakayama,
"Stochastically Flipping Labels of Discriminator’s Outputs for Training Generative Adversarial Networks",
IEEE Access, Vol.10, pp.103644-103654, 2022. pdf

Yi-Pei Chen, Nobuyuki Shimizu, Takashi Miyazaki, Hideki Nakayama,
“How do people talk about images? A study on open-domain conversations with images”,
In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) Student Research Workshop, pp.156-162, 2022.
pdf

Jun Takeuchi, Noriki Nishida, Hideki Nakayama,
“Neural Networks in a Product of Hyperbolic Spaces”,
In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) Student Research Workshop, pp.211-221, 2022.
pdf

Rui Yang, Raphael Shu, Hideki Nakayama,
"Improving Noised Gradient Penalty with Synchronized Activation Function for Generative Adversarial Networks",
IEICE Transactions on Information and Systems, Vol.E105-D, No.9, pp.1537-1545, 2022. pdf

Ryuichiro Hataya, and Hideki Nakayama,
"DJMix: Unsupervised Task-agnostic Image Augmentation for Improving Robustness of Convolutional Neural Networks",
In Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2022.

Ikki Kishida, Hideki Nakayama,
“Pixel to Binary Embedding Towards Robustness for CNNs”,
In Proceedings of the International Conference on Pattern Recognition (ICPR), 2022.
pdf

Duc Minh Vo, Hong Chen, Akihiro Sugimoto, Hideki Nakayama,
“NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge”,
In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp.17979-17987, 2022.
pdf

Kai Katsumata, Duc Minh Vo, and Hideki Nakayama,
“OSSGAN: Open-Set Semi-Supervised Image Generation”,
In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp.11175-11183, 2022.
pdf

Hisashi Kamezawa, Noriki Nishida, Nobuyuki Shimizu, Takashi Miyazaki, Hideki Nakayama,
“RNSum: A Large-Scale Dataset for Automatic Release Note Generation via Commit Logs Summarization”,
In Proceedings of the Association for Computational Linguistics (ACL), pp.8718–8735, 2022.
pdf

Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama,
“PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression”,
In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp.2436-2444, 2022.
pdf

Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe, and Hideki Nakayama
“Meta Approach to Data Augmentation Optimization”,
In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp.2574-2583, 2022.
pdf

2021

Hong Chen, Hiroya Takamura, Hideki Nakayama
“SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation”,
Findings of the Association for Computational Linguistics: EMNLP 2021, pp.1483-1492, 2021.
pdf

Jan Zdenek and Hideki Nakayama,
“JokerGAN: Memory-Efficient Model for Handwritten Text Generation with Text Line Awareness”,
Proceedings of the 29th ACM International Conference on Multimedia (ACMMM), pp.5655-5663, 2021.
pdf

Hong Chen, Raphael Shu, Hiroya Takamura, Hideki Nakayama
“GraphPlan: Story Generation by Planning with Event Graph”,
Proceedings of the 14th International Conference on Natural Language Generation (INLG), pp.377-386, 2021.
pdf

Kai Katsumata, Ikki Kishida, Ayako Anma, and Hideki Nakayama,
"Open-Set Domain Generalization via Metric Learning",
Proceedings of the IEEE International Conference on Image Processing (ICIP), pp.459-463, 2021.

Shisheng Wang, Hideki Nakayama,
“Stochastic Observation Prediction for Efficient Reinforcement Learning in Robotics”,
Proceedings of the 4th IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR), pp.131-137, 2021.

Yuhao Xu and Hideki Nakayama,
“DCT-based Fast Spectral Convolution for Deep Convolutional Neural Networks”,
Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2021.

西原 哲郎, 田村晃裕, 二宮崇, 表悠太郎, 中山 英樹,
"教師付き視覚的注意を用いたマルチモーダルニューラル機械翻訳",
自然言語処理, Vol.28, No.2, pp.554-572, 2021.
pdf

Kai Katsumata and Hideki Nakayama,
"Semantic Image Synthesis from Inaccurate and Coarse Masks",
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.2285-2289, 2021.

Taiga Kashima, Ryuichiro Hataya, and Hideki Nakayama,
"Visualizing Association in Exemplar-based Classification",
Proceedings of the 46th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.1780-1784, 2021.

Changhee Han, Leonardo Rundo, Kohei Murao, Tomoyuki Noguchi, Yuki Shimahara, Zoltán, Ádám Milacski, Saori Koshino, Evis Sala, Hideki Nakayama, Shin'ichi Satoh
"MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstruction",
BMC Bioinformatics, Vol.22, No.31, 2021. pdf

Hong Chen, Yifei Huang, Hiroya Takamura, and Hideki Nakayama,
"Commonsense Knowledge Aware Concept Selection for Diverse and Informative Visual Storytelling",
Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), pp.999-1008, 2021.
pdf

Ikki Kishida, Hong Chen, Masaki Baba, Jiren Jin, Ayako Amma, and Hideki Nakayama,
"Object Recognition with Continual Open Set Domain Adaptation for Home Robot",
Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp.1517-1526, 2021.
pdf

2020

Tetsuro Nishihara, Akihiro Tamura, Takashi Ninomiya, Yutaro Omote, and Hideki Nakayama,
"Supervised Visual Attention for Multimodal Neural Machine Translation",
Proceedings of the International Conference on Computational Linguistics (COLING), pp.4304-4314, 2020. pdf

Yuxuan Wu and Hideki Nakayama,
"Graph-based Heuristic Search for Module Selection Procedure in Neural Module Network",
Proceedings of the Asian Conference on Computer Vision (ACCV), pp.560-575, 2020. pdf

Hisashi Kamezawa, Noriki Nishida, Nobuyuki Shimizu, Takashi Miyazaki, and Hideki Nakayama,
"A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses",
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.3299-3310, 2020. pdf

Taiga Kashima, Kento Masui, and Hideki Nakayama,
"Unsupervised Visual Relationship Inference",
Proceedings of the IEEE International Conference on Image Processing (ICIP), pp.1476-1480, 2020.

Ryuichiro Hataya, Zdenek Jan, Kazuki Yoshizoe, and Hideki Nakayama,
"Faster AutoAugment: Learning Augmentation Strategies using Backpropagation",
Proceedings of the 16th European Conference on Computer Vision (ECCV), 2020. pdf

Ryosuke Kuwabara, Jun Suzuki, Hideki Nakayama,
"Single Model Ensemble using Pseudo-Tags and Distinct Vectors",
Proceedings of the 58th annual meeting of the Association for Computational Linguistics (ACL), pp.3006-3013, 2020. pdf

Takumi Ohkuma, Hideki Nakayama,
"Efficient Base Class Selection Algorithms for Few-shot Classification",
Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR), pp.271-275, 2020. pdf

Hideki Nakayama, Akihiro Tamura, Takashi Ninomiya,
"A Visually-Grounded Parallel Corpus with Phrase-to-Region Linking",
Proceedings of the 25th International Conference on Language Resources and Evaluation (LREC), pp.4204-4210, 2020. pdf

Raphael Shu, Jason Lee, Hideki Nakayama, Kyunghyun Cho,
"Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference using a Delta Posterior",
Proceedings of the 24th AAAI Conference on Artificial Intelligence (AAAI), pp.8846-8853, 2020. pdf
(Acceptance rate 20.6%.)

Jan Zdenek and Hideki Nakayama
"Erasing Scene Text with Weak Supervision",
Proceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020. pdf

Noriki Nishida and Hideki Nakayama
"Unsupervised Discourse Constituency Parsing Using Viterbi EM",
Transactions of the Association for Computational Linguistics, Vol.8, pp.215-230, 2020. pdf

2019

Yuhao Xu and Hideki Nakayama
"Shifted Spatial-Spectral Convolution for Deep Neural Networks",
Proceedings of the 1st ACM International Conference on Multimedia in Asia (MM Asia), 2019.
(Acceptance rate 27.5%.)

Ikki Kishida and Hideki Nakayama
"Empirical Study of Easy and Hard Examples in CNN Training",
Proceedings of the 26th International Conference on Neural Information Processing (ICONIP), 2019. pdf

Changhee Han, Kohei Murao, Tomoyuki Noguchi, Yusuke Kawata, Fumiya Uchiyama, Leonardo Rundo, Hideki Nakayama, Shin'Ichi Satoh
"Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images",
Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM), 2019. pdf
(Acceptance rate 19.4%.)

Leonardo Rundo, Changhee Han, Yudai Nagano, Jin Zhang, Ryuichiro Hataya, Carmelo Militello, Andrea Tangherloni, Marco S. Nobile, Claudio Ferretti, Daniela Besozzi, Maria Carla Gilardi, Salvatore Vitabile, Giancarlo Mauri, Hideki Nakayama, Paolo Cazzaniga
"USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets",
Neurocomputing, Volume 365, Pages 31-43, 2019. pdf

Changhee Han, Leonardo Rundo, Ryosuke Araki, Yudai Nagano, Yujiro Furukawa, Giancarlo Mauri, Hideki Nakayama, Hideaki Hayashi
"Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detection",
IEEE Access, Vol.7, pp.156966-156977, 2019.
pdf

Changhee Han, Yoshiro Kitamura, Akira Kudo, Akimichi Ichinose, Leonardo Rundo, Yujiro Furukawa, Kazuki Umemoto, Yuanzhong Li, Hideki Nakayama
"Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection",
The International Conference on 3D Vision (3DV), 2019. pdf

Changhee Han, Leonardo Rundo, Kohei Murao, Zoltán Ádám Milacski, Kazuki Umemoto, Hideki Nakayama, Shin'Ichi Satoh
"GAN-based Multiple Adjacent Brain MRI Slice Reconstruction for Unsupervised Alzheimer's Disease Diagnosis",
The 16th International Conference on Computational Intelligence methods for Bioinformatics and Biostatistic (CIBB), 2019. pdf

Raphael Shu, Hideki Nakayama, Kyunghyun Cho
"Generating Diverse Translations with Sentence Codes",
The 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2019. pdf
(Acceptance rate 22.7%.)

Ryuichiro Hataya, Hideki Nakayama,
"LOL: Learning to Optimize Loss Switching Under Label Noise",
Proceedings of the 26th IEEE International Conference on Image Processing (ICIP), 2019.

Yuhao Xu, Hideki Nakayama,
"DCT Based Information-Preserving Pooling for Deep Neural Networks",
Proceedings of the 26th IEEE International Conference on Image Processing (ICIP), 2019.

Rui Yang, Hideki Nakayama,
"Bipolar GAN: Double Check the Solution Space and Lighten False Positive Errors in Generative Adversarial Nets",
Proceedings of the 26th IEEE International Conference on Image Processing (ICIP), 2019.

Ryuichiro Hataya, Hideki Nakayama,
"Unifying Semi-Supervised and Robust Learning by Mixup",
Proceedings of the 2nd Learning from Limited Labeled Data (LLD) Workshop, ICLR, 2019. pdf

Jiali Yao, Raphael Shu, Xinjian Li, Katsutoshi Ohtsuki, Hideki Nakayama,
"Enabling Real-time Neural IME with Incremental Vocabulary Selection",
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT) (industry track), 2019. pdf

Hiroki Takushima, Akihiro Tamura, Takashi Ninomiya, Hideki Nakayama,
"Multimodal Neural Machine Translation Using CNN and Transformer Encoder",
Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing), 2019. pdf

2018

Hong Chen, Yifei Huang, Hideki Nakayama,
"Semantic Aware Attention Based Deep Object Co-segmentation",
Proceedings of the 14th Asian Conference on Computer Vision (ACCV), 2018. pdf

Diep Thi Ngoc Nguyen,Hideki Nakayama,Naoaki Okazaki,Tatsuya Sakaeda,
"PoB: Toward Reasoning Patterns of Beauty in Image Data",
Proceedings of the ACM Multimedia Conference on Multimedia Conference (MM), 2018. pdf
(Acceptance rate 27.6%.)

Raphael Shu and Hideki Nakayama,
"Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation",
The 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018. pdf
(Acceptance rate 24.0%.)

Noriki Nishida and Hideki Nakayama,
"Coherence Modeling Improves Implicit Discourse Relation Recognition",
The 19th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), 2018. pdf

Masaya Abe and Hideki Nakayama,
"Deep Learning for Forecasting Stock Returns in the Cross-Section",
Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2018. pdf
(Acceptance rate 27.7%.)

Raphael Shu and Hideki Nakayama,
"Compressing Word Embeddings via Deep Compositional Code Learning",
International Conference on Learning Representations (ICLR), 2018. pdf

Changhee Han, Hideaki Hayashi, Leonardo Rundo, Ryosuke Araki, Wataru Shimoda,Shinichi Muramatsu, Yujiro Furukawa, Giancarlo Mauri, and Hideki Nakayama,
"GAN-based Synthetic Brain MR Image Generation",
IEEE International Symposium on Biomedical Imaging (ISBI), 2018. pdf

Masashi Yokota and Hideki Nakayama,
"Augmenting Image Question Answering Dataset by Exploiting Image Captions",
International Conference on Language Resources and Evaluation (LREC), 2018. pdf

Natsuda Laokulrat, Naoaki Okazaki, and Hideki Nakayama,
"Incorporating Semantic Attention in Video Description Generation",
International Conference on Language Resources and Evaluation (LREC), 2018. pdf

2017

Kento Masui, Akiyoshi Ochiai, Shintaro Yoshizawa, Hideki Nakayama,
"Recurrent Visual Relationship Recognition with Triplet Unit",
IEEE International Symposium on Multimedia (ISM), 2017. pdf

Noriki Nishida, Hideki Nakayama,
"Word Ordering as Unsupervised Learning Towards Syntactically Plausible Word Representations",
International Joint Conference on Natural Language Processing (IJCNLP), 2017.  pdf

Jan Zdenek, Hideki Nakayama
"Bag of Local Convolutional Triplets for Script Identification in Scene Text",
International Conference on Document Analysis and Recognition (ICDAR), 2017. pdf

Hideki Nakayama, Noriki Nishida
"Zero-resource machine translation by multimodal encoder-decoder network with multimedia pivot",
Machine Translation, Vol.31, No.1-2, pp.49-64, 2017. link

Raphael Shu, Hideki Nakayama
"An Empirical Study of Adequate Vision Span for Attention-Based Neural Machine Translation",
ACL Workshop on Neural Machine Translation, 2017. pdf
(Outstanding paper award)

2016

Natsuda Laokulrat(AIST-AIRC), Sang Phan(NII), Noriki Nishida, Raphael Shu, Yo Ehara(AIST-AIRC), Naoaki Okazaki(Tohoku Univ,AIST-AIRC), Yusuke Miyao(NII,AIST-AIRC), Shin'ichi Satoh(NII), Hideki Nakayama,
"Generating Video Description using Sequence-to-sequence Model with Temporal Attention",
International Conference on Computational Linguistics (COLING), 2016. pdf
(Acceptance rate 32.4%.)

Jiren Jin, Hideki Nakayama,
"Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Tagging",
International Conference on Pattern Recognition (ICPR), 2016. pdf Demo

Hideki Nakayama, Tomoya Tsuda,
"Efficient two-step middle-level part feature extraction for fine-grained visual categorization",
IEICE Transactions on Information and Systems,Vol.E99-D, pp.1626-1634, 2016. pdf

Kohei Yamamoto, Hayato Kobayashi(Yahoo!JAPAN), Yukihiro Tagami(Yahoo!JAPAN), Hideki Nakayama,
"Multimodal content-aware image thumbnaling",
ACM International Conference on World Wide Web (WWW) (Companion Volume), pp.129-130, 2016.  pdf

2015

Noriki Nishida, Hideki Nakayama,
"Multimodal gesture recognition using multi-stream recurrent neural network",
Pacific-Rim Symposium on Image and Video Technology (PSIVT), 2015.  pdf

Ruka Funaki, Hideki Nakayama,
"Image-mediated learning for zero-shot cross-lingual document retrieval",
Empirical Methods in Natural Language Processing (EMNLP), 2015.  pdf
(Short paper, acceptance rate 23.7%.)

Takanori Tamanaha, Hideki Nakayama,
"Unsupervised cosegmentation based on global graph matching",
ACM International Conference on Multimedia, 2015.  pdf
(Short paper, acceptance rate 30.3%.)

2014

Masaya Okamoto, Hideki Nakayama,
"Unsupervised visual domain adaptation using auxiliary information in target domain",
IEEE International Symposium on Multimedia (ISM), 2014. pdf

Kohei Yamamoto, Riku Togashi, Hideki Nakayama,
"Content-based viewer estimation using image features for recommendation of video clips",
ACM RecSys 2014 Workshop on RecSysTV, 2014. pdf

2013

Hideki Nakayama,
"Efficient discriminative convolution using Fisher weight map",
British Machine Vision Conference (BMVC), 2013. pdf abstract
(Acceptance rate 30%.)

Hideki Nakayama,
"Augmenting descriptors for fine-grained visual categorization using polynomial embedding",
IEEE International Conference on Multimedia & Expo (ICME), 2013. pdf
(Oral, 12.7%.) 

2012

Hideki Nakayama,
"Aggregating descriptors with local Gaussian metrics",
NIPS 2012 Workshop on Large Scale Visual Recognition and Retrieval, 2012. pdf

コンペティション

Noriki Nishida, Jan Zdenek, Hideki Nakayama,
"Object Detection from Video with Nested Recurrent Neural Networks",
ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) Video Object Detection Task, 2015. poster

Hideki Nakayama,
"NLab-UTokyo at ImageCLEF 2013 Plant Identifitication Task",
CLEF 2013 Working Notes, 2013. pdf
Got the 1st place in NaturalBackground Task

Hideki Nakayama, Masaya Okamoto, Tomoya Tsuda, Hiroki Miyatani, and Kohei Yamamoto,
Fine-grained challenge 2013 (in conjunction with ImageNet large-scale visual recognition challenge).
Classification results of testing images.

招待講演

  • 中山英樹, "ディープラーニングと画像認識", 情報処理学会連続セミナー2017 第4回:ディープラーニングの活用と基盤, 2017/10/17.
  • 中山英樹, "ディープラーニングの基礎と応用例", 日本生物環境工学会公開シンポジウム:農業の情報化と人工知能の応用に向けて-SPA, IoT, ディープラーニングの活用-, 2017/9/1.
  • 中山英樹, "クロスモーダル表現学習と自然言語処理", 情報処理学会自然言語処理研究会シンポジウム「自然言語処理の中長期研究構想を論じる会」,2017/3/5.
  • 中山英樹, "ディープラーニングの現状と今後の可能性", 日本金属学会・日本鉄鋼協会東海支部若手材料研究会・技術交流フォーラム, 2016/11/28. 
  • Hideki Nakayama, "Pivot-based multimodality integration for cross-media machine intelligence", CEMS Topical Meeting on Soft Robotics, 2016/10/27. 
  • 中山英樹, "ディープラーニングによるマルチメディア認識理解", 次世代画像入力ビジョンシステム部会定例会, 2016/10/24. 
  • 中山英樹, "深層学習の基礎と応用", 産総研AIセンター機械学習チュートリアル(生命医薬情報学連合大会前日イベント), 2016/9/28. 
  • 中山英樹, "Deep Learning の基礎と最新動向 第6講:画像認識への応用", 日本情報技術センターセミナー, 2016/9/16. 
  • 中山英樹, "ディープラーニングによるマルチメディア認識理解", Prometech Simulation Conference, 2016/9/9. 
  • 中山英樹, "ディープラーニングの現状と今後の可能性", 学振第176委員会第31回研究会, 2016/9/1. 
  • 中山英樹, "コンピュータビジョンと自然言語処理", NLP若手の会(YANS)シンポジウム, 2016/8/29.
  • 中山英樹, "ディープラーニングの発展と最新動向", 画像電子学会 Advanced Image Seminar, 2016/6/1.
  • 中山英樹, "ディープラーニングの現状と可能性", NIIコグニティブ・イノベーションセンター研究会, 2016.
  • 中山英樹, "深層学習と機械知覚", 確率場と深層学習に関する第1回CRESTシンポジウム, 2016.
  • 中山英樹, "画像認識におけるディープラーニング研究の最新動向", STARCアドバンストセミナー, 2015.
  • 中山英樹, "一般画像認識の発展とディープラーニング",  ImPACT未来開拓研究会, 2015.
  • 中山英樹, "ディープラーニングの礎技術と今後の課題・展望 ~画像認識分野を中心に~", 情報機構セミナー, 2015. slideshare
  • 西田典起, "ディープラーニングの映像認識への応用", Prometech Simulation Conference, 2015. 
  • 中山英樹, "Deep Learning の基礎と最新動向 第6講:画像認識への応用", 日本情報技術センターセミナー, 2015. 
  • 中山英樹, "深層畳み込みニューラルネットワークによる画像特徴抽出と転移学習", 電子情報通信学会音声研究会7月研究会, 2015. pdf slide
  • 中山英樹, "一般画像認識の発展と最新動向", 慶應大学電子工学科特別講義, 2015.
  • 中山英樹, "画像認識分野におけるdeep learningの発展と最新動向", 日経エレクトロニクスセミナー ディープラーニング,開発/実装最前線, 2015.
  • 中山英樹, "Deep Learningによる画像認識革命 -歴史・最新理論から実践応用まで-", 第21回 画像センシングシンポジウム (SSII) チュートリアルセッション, 2015. slideshare
  • 中山英樹, "Deep Learningの過去と未来~黒魔術からの脱却へ向けて~", ディープ・ラーニングと画像処理・画像解析セミナー, 2015. slideshare
  • 中山英樹, "画像認識分野におけるdeep learningの発展と最新動向", 日本音響学会関西支部談話会, 2014.pdf
  • 中山英樹, "タカとハヤブサはどこが違う? ~新たな認識領域「詳細画像識別」の展開と応用~", 第20回 画像センシングシンポジウム (SSII) オーガナイズドセッション「物体認識の最前線 -先端技術の実利用に向けて-」, 2014. pdf

国際発表

  • Ryosuke Kuwabara, Jun Suzuki, Hideki Nakayama, "Pseudo Ensemble Technique with a Single Model" Asian Conference on Machine Learning Workshop on Statistics & Machine Learning Researchers (ACML), 2019.
  • Changhee Han, Florian Gesser, Zoltan Adam Milacski, Leonardo Rundo, "RNN-based Unsupervised Anomaly Detection for Alzheimer's Disease Diagnosis Using Multiple MR Image Interpolation", International Summer School on Deep Learning (DeepLearn), 2018.
  • Leonardo Rundo, Changhee Han, Jin Zhang, Ryuichiro Hataya, Yudai Nagano, Carmelo Militello, Claudio Ferretti, Marco S. Nobile, Andrea Tangherloni, Maria Carla Gilardi, Salvatore Vitabile, Hideki Nakayama, Giancarlo Mauri, "CNN-based Prostate Zonal Segmentation on MR Images: A Multi-centric Study", International Summer School on Deep Learning (DeepLearn), 2018.
  • Changhee Han, Hideaki Hayashi, Leonardo Rundo, Ryosuke Araki, Yujiro Furukawa, Giancarlo Mauri, Hideki Nakayama, "Infinite Brain MR Images: PGGAN-based Data Augmentation for Tumor Detection", International Computer Vision Summer School (ICVSS), 2018.

国内発表

  • Jan Zdenek, Hideki Nakayama,"Efficient Model for Handwritten Text Generation with Text Line Awareness",第24回 画像の認識・理解シンポジウム(MIRU), 2021.
  • 幡谷龍一郎,中山英樹,”iMADAO: 画像事例に応じたデータ拡張戦略の設計手法”,第24回 画像の認識・理解シンポジウム(MIRU),2021.
  • 杉浦昇太,西田典起,朱中元,中山英樹,"相互情報量最小化による例文に基づく制御可能な言い換え生成",言語処理学会第27回年次大会,2021.
  • 陳宏,黄逸飛(東京大学),高村大也(東京工業大学,産業技術総合研究所),中山英樹,"Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling",言語処理学会第27回年次大会,2021.
  • 大熊拓海,中山英樹,"Few-shot classificationにおけるベースクラスデータ多様化の有効性",第23回 画像の認識・理解シンポジウム,2020.
  • 岸田一輝,中山英樹,"Incorporating Horizontal Connections in Convolution by Spatial Shuffling",第23回 画像の認識・理解シンポジウム,2020.
  • 幡谷龍一郎,ズデニェク・ヤン,美添一樹,中山英樹,"MADAO: データ拡張最適化のためのメタ的アプローチ",第23回 画像の認識・理解シンポジウム,2020.
  • 西田典起,中山英樹,"談話の削除不可能性に基づく教師なし談話核性分類",言語処理学会第26回年次大会,2020.
  • 朱中元,Jason Lee(ニューヨーク大学),Kyunghyun Cho(ニューヨーク大学),中山英樹,"潜在変数の精緻化による非自己回帰型ニューラル機械翻訳",言語処理学会第26回年次大会,2020.
  • 陳宏,西田典起,朱中元,岡崎直観(東京工業大学,産業技術総合研究所),中山英樹,"RST Discourse Structure Improves Story Ending",言語処理学会第26回年次大会,2020.
  • 桑原亮介,鈴木潤(東北大),中山英樹,"擬似タグと線形移動ベクトルを用いた単一モデルによる擬似モデルアンサンブル",言語処理学会第26回年次大会,2020.
  • 桑原亮介,斉藤いつみ(NTT),西田 京介(NTT),富田 準二(NTT),中山英樹,"抽出型自動要約における低リソース環境下での他言語データ活用方法の検証",言語処理学会第26回年次大会,2020.
  • 杉浦昇太,西田典起,中山英樹,"名詞句の並び替えによる教師なし言い換え生成の検討",言語処理学会第26回年次大会,2020.
  • Ryuichiro Hataya; Jan Zdenek; Kazuki Yoshizoe; Hideki Nakayama. "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation". 情報論的学習理論ワークショップ (IBIS),2019.
  • Ryuichiro Hataya, Hideki Nakayama. "Unifying semi-supervised and robust learning by mixup". 画像の認識・理解シンポジウム(MIRU),2019.
  • Jan Zdenek, Hideki Nakayama. "Erasing Scene Text Using a General Inpainting Network". 画像の認識・理解シンポジウム(MIRU),2019.
  • Changhee Han, Leonardo Rundo, Jin Zhang, Ryuichiro Hataya, Yudai Nagano, Giancarlo Mauri, Hideki Nakayama, "CNN-based Prostate Zonal Segmentation on Magnetic Resonance Images", 画像の認識・理解シンポジウム(MIRU), 2018. pdf
  • Changhee Han, Leonardo Rundo, Rundo Araki, Yujiro Furukawa, Giancarlo Mauri, Hideki Nakayama, Hideaki Hayashi, "Infinite Brain Tumor Images: Can GAN-based Data Augmentation Improve Tumor Detection on MR Images?", 画像の認識・理解シンポジウム(MIRU), 2018. pdf
  • Changhee Han, Hideki Nakayama, "Infinite Brain MR Images: PGGAN-based Data Augmentation for Tumor Detection", 東京大学生命科学シンポジウム(BIO UT), 2018.
  • 西田典起,中山英樹,"テキストの局所一貫性に基づく半教師あり暗黙的談話関係認識",言語処理学会第24回年次大会,2018.pdf
  • Changhee Han, Jin Zhang, Ryuichiro Hataya, Yudai Nagano, Hideki Nakayama, and Leonardo Rundo, "Prostate Zonal Segmentation Using Deep Learning", 医用画像研究会, 2018. pdf
  • 西田典起,中山英樹,"Learning Syntactically Plausible Word Representations by Solving Word Ordering",人工知能学会全国大会第31回,2017.pdf
  • ズデニェク・ヤン,中山英樹,"Script Identification using Bag-of-Words with Entropy-weighted Patches",人工知能学会全国大会第31回,2017.pdf
  • 福田竣,指田岳彦(コニカミノルタ),中山英樹,"画像領域分割のための少量訓練データからの畳み込みニューラルネットワークの解析的な初期化法",人工知能学会全国大会第31回,2017.pdf
  • 朱中元,中山英樹,"文脈を考慮したアテンションメカニズムによって計算量の削減",人工知能学会全国大会第31回,2017.pdf
  • 横田匡史,中山英樹,"シーングラフを用いた質問文生成によるデータ拡張の手法",人工知能学会全国大会第31回,2017.pdf
  • 岩本恵太,中山英樹,"Extreme Learning Machine を用いたハフフォレストによる物体検出",情報処理学会第78回全国大会,2016.pdf
  • 岩瀬智亮,中山英樹,"深層一般化正準相関分析",情報処理学会第78回全国大会,2016.pdf
  • 玉那覇貴紀,中山英樹,"大域的なグラフマッチングに基づく教師なしCosegmentation",情報処理学会第78回全国大会,2016.pdf
  • 富樫陸,佐藤育郎(デンソーアイティーラボラトリ),中山英樹,"非対称空間プーリングを用いた畳み込みニューラルネットワークによる高精度物体位置回帰",情報処理学会第78回全国大会,2016.pdf
  • 舟木類佳,中山英樹,"Zero-Shot言語横断文書検索のための画像媒介学習",情報処理学会第78回全国大会,2016.pdf
  • 山元浩平, 茂木哲矢(ヤフー), 田頭幸浩(ヤフー), 小林隼人(ヤフー), 小野真吾(ヤフー), 中山英樹, "内容ベースアイテム推薦とユーザ属性分布の予測”, 画像の認識・理解シンポジウム (MIRU), 2015. pdf
  • 岩本恵太, 中山英樹, "Extreme Learning Machineによる特徴抽出を用いた決定木とセマンティックセグメンテーションへの応用", 画像センシングシンポジウム (SSII), 2015. pdf
  • 玉那覇貴紀, 中山英樹, "大域的なグラフマッチングに基づくCosegmentation", 画像センシングシンポジウム (SSII), 2015. pdf
  • 宮谷大輝, 中山英樹, “スペクトログラム画像を用いた楽曲印象分類による時間及び周波数情報と印象の関係分析手法の提案”, 第106回情報処理学会音楽情報科学研究会(SIGMUS), 2015. pdf
  • 山元浩平, 茂木哲矢, 田頭幸浩, 小林隼人, 小野真吾, 中山英樹, "一般画像認識手法を応用したディスプレイ広告のユーザ属性推定とクリック率予測”, パターン認識・メディア理解研究会(PRMU), 2015. pdf
  • 岡本昌也, 中山英樹, "付加情報を用いた教師なし転移学習手法の提案", 画像の認識・理解シンポジウム (MIRU), 2014. pdf
  • 山元浩平, 中山英樹, "低次画像特徴量を用いた動画像の視聴者層推定", 画像の認識・理解シンポジウム (MIRU), 2014. pdf
  • 岡本昌也, 中山英樹, "距離情報を手がかりとした画像認識における転移学習手法の改良", 画像センシングシンポジウム (SSII), 2014. pdf
  • 津田智哉, 中山英樹, "確率的正準相関分析による単語ラベルを用いた局所特徴量の圧縮と詳細画像識別への利用", 画像センシングシンポジウム (SSII), 2014. pdf
  • 中山英樹, "階層フィッシャー重みマップを用いた識別的初期化による深層畳み込みニューラルネットワーク構築法", 画像センシングシンポジウム (SSII), 2014. pdf
  • 中山英樹, "局所特徴の共起表現の埋め込みとFisher Vectorを用いた詳細画像カテゴリ識別", 画像の認識・理解シンポジウム (MIRU), 2013. poster pdf

解説・その他

  • 中山英樹,"実世界へ挑む機械学習",電子情報通信学会誌, Vol.104, No.12, pp.1263-1270, 2021.pdf
  • 中山英樹,"5分で分かる!?有名論文ナナメ読み:Ian J. Goodfellow et al. : Generative Adversarial Nets",情報処理, Vol.61, No.1, pp.92-93, 2019.
  • 中山英樹,"画像認識コンペティションの新展開",映像情報メディア学会誌, Vol.73, No.6, 2019.
  • 中山英樹,"マルチモーダル機械翻訳",映像情報メディア学会誌, Vol.72, No.5, 2018.
  • 中山英樹,"深層学習の発展と画像認識",機械学会計算力学部門ニュースレター, No.58, 2017.
  • 中山英樹,"画像解析関連コンペティションの潮流",電子情報通信学会誌, 2017年5月号.pdf
  • 中山英樹,"オープンワールド認識理解のための機械学習と評価",日本ロボット学会誌, 2016年7月号.
  • 中山英樹,"画像認識分野における深層学習の発展と最新動向(後編)",画像ラボ, 日本工業出版, 2016年5月号.
  • 中山英樹,"画像認識分野における深層学習の発展と最新動向(前編)",画像ラボ, 日本工業出版, 2016年4月号.

書籍

  • 中山英樹,"画像認識分野におけるディープラーニングの発展と最新動向", 人工知能テクノロジー総覧(第3章), 日経BP社, 2015.