Tatsuya Harada Tatsuya Harada Doctor of Engineering, Professor Research Center for Advanced Science and Technology The University of Tokyo Team leader at RIKEN AIP Vice director of Research Center for Medical Bigdata at National Institute of Informatics (NII), Japan Japanese page is here.

News

• Mar. 14, 2024. One paper has been accepted for publication in NAACL 2024.
• Jan. 17, 2024. One paper has been accepted for publication in ICLR 2024.
• Dec. 16, 2023. Our paper has been accepted for publication in IJCV.
• Dec. 9, 2023. Two papers have been accepted for publication in AAAI 2024.
• Sep. 22, 2023. One paper has been accepted for publication in NeurIPS 2023.
• July. 14, 2023. One paper has been accepted (1 oral) for publication in ICCV 2023.
• Sep. 15, 2022. One paper has been accepted for publication in NeurIPS 2022.
• July. 4, 2022. Four papers have been accepted for publication in ECCV 2022.
• Mar. 3, 2022. Three papers have been accepted for publication in CVPR 2022.
• Dec. 1, 2021. One paper has been accepted for publication in AAAI 2022.
• July. 23, 2021. Two papers have been accepted for publication in ICCV 2021.
• Mar. 4, 2021. Two papers have been accepted for publication in CVPR 2021.
• Feb. 28, 2021. Two papers have been accepted for publication in ICRA 2021.
• Jan. 13, 2021. One paper has been accepted for publication in ICLR 2021.
• Dec. 2, 2020. One paper has been accepted for publication in AAAI 2021.
• Sep. 26, 2020. One paper has been accepted for publication in NeurIPS 2020.
• July. 3, 2020. One paper has been accepted (1 spotlight) for publication in ECCV 2020.
• Feb. 24, 2020. Two papers have been accepted (1 oral, 1 poster) for publication in CVPR 2020.
• Dec. 20, 2019. One paper has been accepted for publication in ICLR 2020.
• Nov. 11, 2019. One paper has been accepted for publication in AAAI 2020.
• July 23, 2019. Three papers have been accepted for publication in ICCV 2019.
• Feb. 25, 2019. Five papers have been accepted (3 orals, 2 posters) for publication in CVPR 2019.
• Jul. 3, 2018. Two papers have been accepted for publication in ECCV 2018.
• Feb. 19, 2018. Five papers have been accepted (1 oral, 3 spotlights, 1 poster) for publication in CVPR 2018.
• Jan. 31, 2018. Two papers have been accepted for publication in ICLR 2018.
• Oct. 26, 2017. We got Honorable Mention Open source software Award 2017 for WebDNN at ACM Multimedia 2017.
• July 17, 2017. Our paper has been accepted for publication in ICCV 2017.
• May 28, 2017. We have released WebDNN which executes DNN on a modern browser without installing any software.
• May 25, 2017. My textbook "image recognition (in Japanese)" has been published.
• May 13, 2017. Our paper has been accepted for publication in ICML 2017.
• June 26, 2016. We win the VQA challenge (Abstract Scenes) at CVPR 2016, Las Vegas, USA.
• March 5, 2016. Three papers have been accepted for publication in CVPR 2016.
• Dec. 10, 2015. Third place in Object Detection (DET) with "external" data, ImageNet Large Scale Visual Recognition Challenge 2015 (ILSVRC2015)
• Sep. 3, 2015. Our paper has been accepted for publication in ICCV 2015.
• April 13, 2014. Our paper has been accepted for publication in ICML 2014.
• Feb. 25, 2014. Two papers have been accepted for publication in CVPR 2014.

Projects

• Visual recognition
• Machine learning
• Multimedia learning (vision, natural language, sound, etc.)
• Causality
• Intelligent robot

Teaching

• May 31, 2017. Special Topics in Mechano‐Informatics II[pdf]

Publications

• 2024
  • Kohtaro Tanaka, Kohei Uehara, Lin Gu, Yusuke Mukuta, Tatsuya Harada. Content-Specific Humorous Image Captioning Using Incongruity Resolution Chain-of-Thought. 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), accepted, 2024
  • Xuangeng Chu, Yu Li, Ailing Zeng, Tianyu Yang, Lijian Lin, Yunfei Liu, Tatsuya Harada. GPAvatar: Generalizable and Precise Head Avatar from Image(s). The Twelfth International Conference on Learning Representations (ICLR), accepted, 2024.
  • Kohei Uehara, Tatsuya Harada. Learning by Asking Questions for Knowledge-based Novel Object Recognition. International Journal of Computer Vision (IJCV), accepted, 2024.
  • Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada. Symmetric Q-Learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning. Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), accepted, 2024.
  • Ziteng Cui, Lin Gu, Xiao Sun, xianzheng ma, Yu Qiao, Tatsuya Harada. Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption. Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), accepted, 2024.
  • Thomas Westfechtel, Hao-Wei Yeh, Dexuan Zhang, Tatsuya Harada. Gradual Source Domain Expansion for Unsupervised Domain Adaptation. Winter Conference on Applications of Computer Vision (WACV), accepted, 2024.
  • Kai Katsumata, Duc Minh Vo, Tatsuya Harada, Hideki Nakayama. Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data. Winter Conference on Applications of Computer Vision (WACV), accepted, 2024.
• 2023
  • Yuki Kawana, Tatsuya Harada. Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), accepted, 2023.
  • Yosuke Shinya, Kenichi Yoneji, Akihiro Tsukada, Tatsuya Harada. 3D Lighter: Learning to Generate Emissive Textures. SIGGRAPH Asia 2023, accepted, poster, 2023.
  • Hu, X., Gu, L., An, Q., Zhang, M., liu, l., Kobayashi, K., Harada, T.,Summers, R., & Zhu, Y. (2023). Medical-Diff-VQA: A Large-Scale Medical Datasetfor Difference Visual Question Answering on Chest X-Ray Images (version1.0.0). PhysioNet. https://doi.org/10.13026/5jes-bx23.
  • Yujin Tang, Wenhao Yu, Jie Tan, Heiga Zen, Aleksandra Faust, Tatsuya Harada. SayTap: Language to Quadrupedal Locomotion. 7th Annual Conference on Robot Learning (CoRL), accepted, 2023.
  • Takayuki Hara, Yusuke Mukuta, Tatsuya Harada. Spherical Image Generation from a Few Normal-Field-of-View Images by Considering Scene Symmetry. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 45, no. 5, pp. 6339-6353, 1 May 2023, doi: 10.1109/TPAMI.2022.3215933.
  • Takayuki Osa, Naoto Osajima, Masanori Aizawa, Tatsuya Harada. Learning Adaptive Policies for Autonomous Excavation Under Various Soil Conditions by Adversarial Domain Sampling. IEEE Robotics and Automation Letters (RA-L), accepted, 2023.
  • Yusuke Mukuta, Tatsuya Harada. Invariant Feature Coding using Tensor Product Representation. Transactions on Machine Learning Research (TMLR), accepted, 2023.
  • Dexuan Zhang, Tatsuya Harada. Unsupervised Domain Adaptation via Minimized Joint Error. Transactions on Machine Learning Research (TMLR), accepted, 2023.
  • Ayako Nakada, Ryota Niikura, Keita Otani, Yusuke Kurose, Yoshito Hayashi, Kazuya Kitamura, Hiroyoshi Nakanishi, Seiji Kawano, Testuya Honda, Kenkei Hasatani, Tetsuya Sumiyoshi, Tsutomu Nishida, Atsuo Yamada, Tomonori Aoki, Tatsuya Harada, Takashi Kawai, and Mitsuhiro Fujishiro. 2023. "Improved Object Detection Artificial Intelligence Using the Revised RetinaNet Model for the Automatic Detection of Ulcerations, Vascular Lesions, and Tumors in Wireless Capsule Endoscopy" Biomedicines 11, no. 3: 942. https://doi.org/10.3390/biomedicines11030942
  • Yusuke Mori, Hiroaki Yamane, Ryohei Shimizu, Yusuke Mukuta, Tatsuya Harada. COMPASS: a Creative Support System that Alerts Novelists to the Unnoticed Missing Contents. Computer Speech & Language, vol.80, pages 101484, 2023. https://doi.org/10.1016/j.csl.2023.101484
  • Hao-Wei Yeh, Qier Meng, Tatsuya Harada. Misalignment-Free Relation Aggregation for Multi-Source-Free Domain Adaptation. Out Of Distribution Generalization in Computer Vision in conjunction with ICCV 2023, accepted, 2023.
  • Ayaka Ideno, Takuhiro Kaneko, Tatsuya Harada. Frame-Level Event Representation Learning for Semantic-Level Generation and Editing of Avatar Motion. ACM International Conference on Multimodal Interaction (ICMI), accepted, 2023. (Oral, LONG paper)
  • Shenghan Su, Lin Gu, Yue Yang, Zenghui Zhang, Tatsuya Harada. Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer. International Conference on Computer Vision (ICCV), accepted, 2023. (oral)
  • Yutong Xie, Lin Gu, Tatsuya Harada, Jianpeng Zhang, Yong Xia, Qi Wu. MedIM: Boost Medical Image Representation via Radiology Report-guided Masking. Medical Image Computing and Computer-Assisted Intervention (MICCAI), accepted, 2023.
  • Kazuma Kobayashi, Lin Gu, Ryuichiro Hataya, Mototaka Miyake, Yasuyuki Takamizawa, Sono Ito, Hirokazu Watanabe, Yukihiro Yoshida, Hiroki Yoshimura, Tatsuya Harada, Ryuji Hamamoto. Towards AI-driven radiology education: A self-supervised segmentation-based framework for high-precision medical image editing. Medical Image Computing and Computer-Assisted Intervention (MICCAI), accepted, 2023.
  • Xinyue Hu, Lin Gu, Qiyuan An, Zhang Mengliang, Liangchen Liu, Kazuma Kobayashi, Tatsuya Harada, Ronald M. Summers, Yingying Zhu. Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering. 29th SIGKDD Conference on Knowledge Discovery and Data Mining - Applied Data Science Track, accepted, 2023.
  • Kohei Shiba, Yusuke Mukuta, Tatsuya Harada. Zero-shot Object Classification with Large-scale Knowledge Graph. the Workshop on Learning with Limited Labelled Data (CVPR 2023), accepted, 2023.
  • Shusuke Takahama, Yusuke Kurose, Yusuke Mukuta, Hiroyuki Abe, Akihiko Yoshizawa, Tetsuo Ushiku, Masashi Fukayama, Masanobu Kitagawa, Masaru Kitsuregawa, Tatsuya Harada. Domain Adaptive Multiple Instance Learning for Instance-level Prediction of Pathological Images. IEEE International Symposium on Biomedical Imaging (ISBI) 2023, accepted, 2023.
  • Zhennan Wu, Yang Li, Yifei Huang, Lin Gu, Tatsuya Harada, Hiroyuki Sato. 3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation. Eleventh International Conference on Learning Representations (ICLR), accepted, 2023.
  • Junjie Zhu, Lin Gu, Xiaoxiao Wu, Zheng Li, Tatsuya Harada, Yingying Zhu. People taking photos that faces never share: Privacy Protection and Fairness Enhancement from Camera to User. Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), accepted, 2023.
  • Kohei Uehara, Tatsuya Harada. K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition. Winter Conference on Applications of Computer Vision (WACV), accepted, 2023.
  • Thomas Westfechtel, Hao-Wei Yeh, Qier Meng, Yusuke Mukuta, Tatsuya Harada. Backprop Induced Feature Weighting for Adversarial Domain Adaptation with Iterative Label Distribution Alignment. Winter Conference on Applications of Computer Vision (WACV), accepted, 2023.
• 2022
  • Yang Li, Tatsuya Harada. Non-rigid Point Cloud Registration with Neural Deformation Pyramid. Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), accepted, 2022.
  • Daiki Naruse, Tomoyuki Takahata, Yusuke Mukuta, Tatsuya Harada. Pop Music Generation with Controllable Phrase Lengths. The 23rd International Society for Music Information Retrieval Conference (ISMIR), accepted, 2022.
  • Hiroyuki Abe, Yusuke Kurose, Shusuke Takahama, Ayako Kume, Shu Nishida, Miyako Fukasawa, Yoichi Yasunaga, Tetsuo Ushiku, Youichiro Ninomiya, Akihiko Yoshizawa, Kohei Murao, Shin’ichi Sato, Masaru Kitsuregawa, Tatsuya Harada, Masanobu Kitagawa, Masashi Fukayama. Development and multi-institutional validation of an artificial intelligence-based diagnostic system for gastric biopsy. Cancer Science, 2022. DOI: https://doi.org/10.1111/cas.15514
  • Yuki Kawana, Yusuke Mukuta, Tatsuya Harada. Unsupervised Pose-aware Part Decomposition for Man-made Articulated Objects. The European Conference on Computer Vision (ECCV), accepted, 2022. (oral)
  • Atsuhiro Noguchi, Xiao Sun, Stephen Lin, Tatsuya Harada. Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations. The European Conference on Computer Vision (ECCV), accepted, 2022.
  • Tianhan Xu, Tatsuya Harada. Deforming Radiance Fields with Cages. The European Conference on Computer Vision (ECCV), accepted, 2022.
  • Ziteng Cui, Yingying Zhu, Lin Gu, Guo-Jun Qi, Xiaoxiao Li, Renrui Zhang, Zenghui Zhang, Tatsuya Harada. Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection. The European Conference on Computer Vision (ECCV), accepted, 2022.
  • Nabarun Goswami and Tatsuya Harada. SATTS: Speaker Attractor Text to Speech, Learning to Speak by Learning to Separate. Interspeech, accepted, 2022.
  • Yang Li, Tatsuya Harada. Lepard: Learning partial point cloud matching in rigid and deformable scenes. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), accepted, 2022. (oral)
  • Atsuhiro Noguchi, Umar Iqbal, Jonathan Tremblay, Tatsuya Harada, Orazio Gallo. Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), accepted, 2022.
  • Jiawei Zhang, Xiang Wang, Xiao Bai, Chen Wang, Lei Huang, Yimin Chen, Lin Gu, Jun Zhou, Tatsuya Harada, Hancock Edwin. Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), accepted, 2022.
  • Hiromichi Kamata, Yusuke Mukuta, Tatsuya Harada. Fully Spiking Variational Autoencoder. Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), accepted, 2022.
  • Ziteng Cui, Kunchang Li, Lin Gu, Shenghan Su, Peng Gao, ZhengKai Jiang, Yu Qiao, Tatsuya Harada. You Only Need 90K Parameters to Adapt Light: a Light Weight Transformer for Image Enhancement and Exposure Correction. accepted, British Machine Vision Conference (BMVC), 2022.
  • Baoyao Yang, Hao-Wei Yeh, Tatsuya Harada, Pong C. Yuen. Model-Induced Generalization Error Bound for Information-Theoretic Representation Learning in Source-Data-Free Unsupervised Domain Adaptation. IEEE Transactions on Image Processing. pp.419-432, 2022. Digital Object Identifier: 10.1109/TIP.2021.3130530
  • Mohammad Reza Motallebi, Thomas Westfechtel, Yang Li, Tatsuya Harada. Unsupervised Hierarchical Disentanglement for Video Prediction. 26th International Conference on Pattern Recognition (ICPR), accepted, 2022.
  • Hao-Wei Yeh, Thomas Westfechtel, Jia-Bin Huang, Tatsuya Harada. Boosting Source-free Domain Adaptation via Confidence-based Subsets Feature Alignment. 26th International Conference on Pattern Recognition (ICPR), accepted, 2022.
  • Kohei Uehara, Nan Duan, Tatsuya Harada. Learning to Ask Informative Sub-Questions for Visual Question Answering. 5th MUltimodal Learning and Applications Workshop (MULA 2022) in conjunction with CVPR 2022, accepted, 2022.
  • Kohei Uehara, Yusuke Mori, Yusuke Mukuta and Tatsuya Harada. ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer. The 1st International Workshop on Multimodal Understanding for the Web and Social Media (MUWS), co-located with The WebConf (WWW) 2022, accepted, 2022.
  • Yusuke Mori, Hiroaki Yamane, Ryohei Shimizu, Tatsuya Harada. Plug-and-Play Controller for Story Completion: A Pilot Study toward Emotion-aware Story Writing Assistance. The First Workshop on Intelligent and Interactive Writing Assistants (In2Writing), accepted, 2022.
  • Bumjun Jung, Lin Gu, Tatsuya Harada. Graph interaction for automated diagnosis of thoracic disease using x-ray images. Proc. SPIE 12032, Medical Imaging 2022: Image Processing, 120320L (4 April 2022)
• 2021
  • Atsuhiro Noguchi, Xiao Sun, Stephen Lin, Tatsuya Harada. Neural Articulated Radiance Field. International Conference on Computer Vision (ICCV), pp.5762-5772, 2021.
  • Ziteng Cui, Guo-Jun Qi, Lin Gu, Shaodi You, Zenghui Zhang, Tatsuya Harada. Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection. International Conference on Computer Vision (ICCV), pp.2553-2562, 2021.
  • Yifei Huang, Xiaoxiao Li, Lijin Yang, Lin Gu, Yingying Zhu, Hirofumi Seo, Qiuming Meng, Tatsuya Harada, Yoichi Sato. Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data. British Machine Vision Conference, 517-paper, 2021.
  • Takuhiro Kaneko, Tatsuya Harada. Blur, Noise, and Compression Robust Generative Adversarial Networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.13579-13589, 2021.
  • Yang Liu, Lei Zhou, Xiao Bai, Yifei Huang , Lin Gu , Jun Zhou, Tatsuya Harada. Goal-Oriented Gaze Estimation for Zero-Shot Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.3794-3803, 2021.
  • Ryohei Shimizu, Yusuke Mukuta, Tatsuya Harada. Hyperbolic Neural Networks++. International Conference on Learning Representations (ICLR), 25 pages, online, May 4-8, 2021.
  • Takayuki Hara, Yusuke Mukuta, Tatsuya Harada. Spherical Image Generation from a Single Image by Considering Scene Symmetry. Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 35(2), pp.1513-1521, 2021.
  • Wataru Kawai, Yusuke Mukuta, Tatsuya Harada. Real-Time Mesh Extraction from Implicit Functions via Direct Reconstruction of Decision Boundary. IEEE International Conference on Robotics and Automation (ICRA), 7 pages, online, May 30 - Jun. 25, 2021.
  • Thomas Westfechtel, Kazunori Ohno, Tetsu Akegawa, Kento Yamada, Ranulfo Bezerra, Shotaro Kojima, Taro Suzuki, Tomohiro Komatsu, Shibata Shibata Yukinori, Kimitaka Asano, Keiji Nagatani, Naoto Miyamoto, Takahiro Suzuki, Tatsuya Harada, Satoshi Tadokoro. Semantic Mapping of Construction Site from Multiple Daily Airborne LiDAR Data. IEEE International Conference on Robotics and Automation (ICRA), accepted, 2021.
  • Hao-Wei Yeh, Baoyao Yang, PongChi Yuen, Tatsuya Harada. SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation. Winter Conference on Applications of Computer Vision 2021 (WACV), pp.474-483, 2021.
  • Yanli Ji, Yang Yang, Heng Tao Shen, Tatsuya Harada. View-invariant action recognition via Unsupervised AttentioN Transfer (UANT). Pattern Recognition, Volume 113, 107807, 2021.
  • Hiroaki Yamane, Yusuke Mori, Tatsuya Harada. Humor Meets Morality: Joke Generation Based on Moral Judgement. Information Processing and Management, Volume 58, Issue 3, 2021, 102520, ISSN 0306-4573, https://doi.org/10.1016/j.ipm.2021.102520.
  • Yusuke Mori, Hiroaki Yamane, Yusuke Mukuta, Tatsuya Harada. The Nectar of Missing Position Prediction for Story Completion. Workshop on Text2Story co-located with the 43rd European Conference on Information Retrieval (ECIR 2021), 2021.
  • Antonio Tejero-de-Pablos, Hiroaki Yamane, Yusuke Kurose, Junichi Iho, Youji Tokunaga, Makoto Horie, Keisuke Nishizawa, Yusaku Hayashi, Yasushi Koyama, Tatsuya Harada. Beam Stack Search-based Reconstruction of Coronary Artery Wall Segmentations in CPR Scans. the 2021 IEEE International Symposium on Biomedical Imaging (ISBI), accepted, 2021.
• 2020
  • Yuki Kawana, Yusuke Mukuta, Tatsuya Harada. Neural Star Domain as Primitive Representation. Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), accepted, 2020.
  • Kazuma Kobayashi, Ryuichiro Hataya, Yusuke Kurose, Tatsuya Harada, Ryuji Hamamoto. Decomposing Normal and Abnormal Features of Medical Images for Content-based Image Retrieval. ML4H: Machine Learning for Health Workshop at NeurIPS 2020, accepted, 2020.
  • Kohei Uehara and Tatsuya Harada. Unsupervised Keyword Extraction for Full-sentence VQA. EMNLP workshop on NLP Beyond Text, accepted, 2020.
  • Hayato Sumino, Adrien Bitton, Lisa Kawai, Philippe Esling, and Tatsuya Harada. Automatic Music Transcription and Instrument Transposition with Differentiable Rendering. The 2020 Joint Conference on AI Music Creativity, accepted, 2020.
  • Ren Harada, Antonio Tejero-de-Pablos, Tatsuya Harada. Accurate Parts Visualization for Explaining CNN Reasoning via Semantic Segmentation. British Machine Vision Conference (BMVC), accepted, 2020.
  • Lisa Kawai, Philippe Esling, Tatsuya Harada. Attributes-aware Deep Music Transformation. the 21st International Society for Music Information Retrieval Conference (ISMIR), accepted, 2020.
  • Sho Inayoshi, Keita Otani, Antonio Tejero de Pablos, Tatsuya Harada. Bounding-box Channels for Visual Relationship Detection. The 16th European Conference on Computer Vision (ECCV), accepted, 2020. (spotlight)
  • Takuhiro Kaneko, Tatsuya Harada. Noise Robust Generative Adversarial Networks. The 33rd IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), accepted, 2020.
  • Yang Li, Aljaz Bozic, Tianwei Zhang, Yanli Ji, Tatsuya Harada, Matthias Niessner. Learning to Optimize Non-Rigid Tracking. The 33rd IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), accepted, 2020. (oral)
  • Atsuhiro Noguchi, Tatsuya Harada. RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis. ICLR, accepted, 2020.
  • Toshihiko Matsuura, Tatsuya Harada. Domain Generalization Using a Mixture of Multiple Latent Domains. Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), accepted, 2020.
  • Yang Li, Tianwei Zhang, Yoshihiko Nakamura, Tatsuya Harada. SplitFusion: Simultaneous Tracking and Mapping for Non-Rigid Scenes. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), accepted, 2020.
  • Yujin Tang, Jie Tan, Tatsuya Harada. Learning Agile Locomotion via Adversarial Training. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), accepted, 2020.
  • Kenzo Lobos-Tsunekawa, Tatsuya Harada. Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), accepted, 2020.
  • Kaikai Huang, Antonio Tejero-de-Pablos, Hiroaki Yamane, Yusuke Kurose, Junichi Iho, Youji Tokunaga, Makoto Horie, Keisuke Nishizawa, Yusaku Hayashi, Yasushi Koyama, Tatsuya Harada. Coronary Wall Segmentation in CCTA Scans via a Hybrid Net with Contours Regularization. The IEEE International Symposium on Biomedical Imaging (ISBI'20), accepted, 2020.
• 2019
  • Atsuhiro Noguchi, Tatsuya Harada. Image generation from small datasets via batch statistics adaptation. International Conference on Computer Vision (ICCV), accepted, 2019.
  • Mikihiro Tanaka, Takayuki Itamochi, Kenichi Narioka, Ikuro Sato, Yoshitaka Ushiku, Tatsuya Harada. Towards Human-Friendly Referring Expression Generation. International Conference on Computer Vision (ICCV), accepted, 2019.
  • Shusuke Takahama, Yusuke Kurose, Yusuke Mukuta, Hiroyuki Abe, Masashi Fukayama, Akihiko Yoshizawa, Masanobu Kitagawa, Tatsuya Harada. Multi-Stage Pathological Image Classification using Semantic Segmentation. International Conference on Computer Vision (ICCV), accepted, 2019.
  • Atsushi Kanehira, Kentaro Takemoto, Sho Inayoshi, Tatsuya Harada. Multimodal Explanations by Predicting Counterfactuality in Videos. The 32nd IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8594-8602, 2019. (oral)
  • Hiroharu Kato, Tatsuya Harada. Learning View Priors for Single-view 3D Reconstruction. The 32nd IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9778-9787, 2019.
  • Takuhiro Kaneko, Yoshitaka Ushiku, Tatsuya Harada. Label-Noise Robust Generative Adversarial Networks. The 32nd IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2467-2476, 2019. (oral)
  • Atsushi Kanehira, Tatsuya Harada. Learning to Explain with Complemental Examples. The 32nd IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8603-8611, 2019. (oral)
  • Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada, Kate Saenko. Strong-Weak Distribution Alignment for Adaptive Object Detection. The 32nd IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6956-6965, 2019.
  • Takuhiro Kaneko, Yoshitaka Ushiku, Tatsuya Harada. Class-Distinct and Class-Mutual Image Generation with GANs. 30th British Machine Vision Conference (BMVC), accepted, 2019.
  • Yanli Ji, Feixiang Xu, Yang Yang, Ning Xie, Heng Tao Shen and Tatsuya Harada. Attention Transfer (ANT) Network for View-invariant Action Recognition. 27th ACM International Conference on Multimedia (ACMMM), accepted, 2019.
  • Akane Iseki, Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada. Estimating the Causal Effect from Partially Observed Time Series. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), accepted, 2019.
  • Yang Li, Yoshitaka Ushiku, Tatsuya Harada. Pose Graph Optimization for Unsupervised Monocular Visual Odometry. The 2019 International Conference on Robotics and Automation (ICRA), pp.5439-5445, 2019.
  • Jen-Yen Chang, Antonio Tejero-de-Pablos, Tatsuya Harada. Improved Optical Flow for Gesture-based Human Robot Interaction. The 2019 International Conference on Robotics and Automation (ICRA), pp.7983-7989, 2019.
  • Atsuro Okazawa, Tomoyuki Takahata, Tatsuya Harada. Simultaneous transparent and non-transparent objects segmentation with multispectral scenes. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), accepted, 2019.
  • Takayoshi Takayanagi, Yusuke Kurose, Tatsuya Harada. Hierarchical Task Planning from Object Goal State for Human-Assist Robot. 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), accepted, 2019.
  • Teppei Kanayama, Yusuke Kurose, Kiyohito Tanaka, Kento Aida, Shin'ichi Satoh, Masaru Kitsuregawa, Tatsuya Harada. Gastric cancer detection from endoscopic images using synthesis by GAN. Medical Image Computing and Computer Assisted Interventions 2019 (MICCAI), accepted, 2019.
  • Antonio Tejero-de-Pablos, Kaikai Huang, Hiroaki Yamane, Yusuke Kurose, Yusuke Mukuta, Yasushi Koyama, Junichi Iho, Youji Tokunaga, Makoto Horie, Keisuke Nishizawa, Yusaku Hayashi, Tatsuya Harada. Texture-based classification of significant stenosis in CCTA multi-view images of coronary arteries. Medical Image Computing and Computer Assisted Interventions 2019 (MICCAI), accepted, 2019.(oral)
  • Akio Hayakawa, Yusuke Kurose, Kiyohito Tanaka, Kento Aida, Shin’ichi Satoh, Masaru Kitsuregawa, Tatsuya Harada. Gastric cancer detection for gastroenterological endoscopy with local and multi-scale global information. The International Conference of Computer Assisted Radiology and Surgery (CARS), accepted, 2019.
• 2018
  • Kohei Uehara, Antonio Tejero-de-Pablos, Yoshitaka Ushiku, Tatsuya Harada. Visual Question Generation for Class Acquisition of Unknown Objects. The 15th European Conference on Computer Vision (ECCV), pp. 481-496, 2018. [pdf]
  • Kuniaki Saito, Shohei Yamamoto, Yoshitaka Ushiku, Tatsuya Harada. Adversarial Open Set Domain Adaptation. The 15th European Conference on Computer Vision (ECCV), pp. 153-168, 2018. [pdf]
  • Kohei Watanabe, Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada. Multichannel Semantic Segmentation with Unsupervised Domain Adaptation. First International Workshop On Autonomous Navigation in Unconstrained Environments In Conjunction with ECCV 2018 (AUTONUE2018), accepted, 2018.
  • Toshihiko Matsuura, Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada. Generalized Bayesian Canonical Correlation Analysis with Missing Modalities. 1st Multimodal Learning and Applications Workshop In conjunction with ECCV 2018 (MULA2018), accepted, 2018.
  • Hiroharu Kato, Yoshitaka Ushiku, Tatsuya Harada. Neural 3D Mesh Renderer. The 31st IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.3907-3916, 2018. (spotlight oral) [pdf]
  • Yuji Tokozume, Yoshitaka Ushiku, Tatsuya Harada. Between-class Learning for Image Classification. The 31st IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.5486-5494, 2018.[pdf]
  • Kuniaki Saito, Kohei Watanabe, Yoshitaka Ushiku, Tatsuya Harada. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation. The 31st IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.3723-3732, 2018. (oral) [pdf]
  • Atsushi Kanehira, Luc Van Gool, Yoshitaka Ushiku, Tatsuya Harada. Viewpoint-aware Video Summarization. The 31st IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.7435-7444, 2018. (spotlight oral) [pdf]
  • Andrew Shin, Yoshitaka Ushiku, Tatsuya Harada. Customized Image Narrative Generation via Interactive Visual Question Generation and Answering. The 31st IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.8925-8933, 2018. (spotlight oral) [pdf]
  • Yuji Tokozume, Yoshitaka Ushiku, Tatsuya Harada. Learning from Between-class Examples for Deep Sound Recognition. 6th International Conference on Learning Representations (ICLR), 2018.[pdf]
  • Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada, Kate Saenko. Adversarial Dropout Regularization. 6th International Conference on Learning Representations (ICLR), 2018.[pdf]
  • Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada. Alternating Circulant Random Features for Semigroup Kernels. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), pp.3836-3843, 2018.[pdf]
  • Katsunori Ohnishi, Shohei Yamamoto, Yoshitaka Ushiku, Tatsuya Harada. Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), pp.2387-2394, 2018. (oral) [pdf]
• 2017
  • Hanna Tseran and Tatsuya Harada. Memory Augmented Neural Network with Gaussian Embeddings for One-Shot Learning. NIPS Workshop on Bayesian Deep Learning, 12, 2017.
  • Masataka Yamaguchi, Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada. Spatio-temporal Person Retrieval via Natural Language Queries. In the 16th International Conference on Computer Vision (ICCV), pp.1462-1471, 2017. [pdf]
  • Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada. Spatial-Temporal Weighted Pyramid using Spatial Orthogonal Pooling. ICCV 2017 Workshop on CEFRL: Compact and Efficient Feature Representation and Learning in Computer Vision, pp.1041-1049, 2017. [pdf]
  • Kuniaki Saito, Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada. Deep Modality Invariant Adversarial Network for Shared Representation Learning. ICCV 2017 Workshop on TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision, pp.2623-2629, 2017. [pdf]
  • Kuniaki Saito, Yoshitaka Ushiku, and Tatsuya Harada. Asymmetric Tri-training for Unsupervised Domain Adaptation. International Conference on Machine Learning (ICML), PMLR 70:2988-2997, 2017. [pdf]
  • Masatoshi Hidaka, Yuichiro Kikura, Yoshitaka Ushiku, Tatsuya Harada. WebDNN: Fastest DNN Execution Framework on Web Browser. ACM Multimedia Open Source Software Competition, pp.1213-1216, 2017. (Honorable Mention Open source software Award) [pdf]
  • Takumi Karasawa, Kohei Watanabe, Qishen Ha, Antonio Tejero-De-Pablos, Yoshitaka Ushiku, Tatsuya Harada. Multispectral Object Detection for Autonomous Vehicles. ACM Multimedia Thematic Workshops, pp.35-43, 2017. [pdf]
  • Qishen Ha, Kohei Watanabe, Takumi Karasawa, Yoshitaka Ushiku, Tatsuya Harada. MFNet: Towards Real-Time Semantic Segmentation for Autonomous Vehicles with Multi-Spectral Scenes. The 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.5108-5115, 2017. [pdf]
  • Masatoshi Hidaka, Ken Miura, Tatsuya Harada. Development of JavaScript-based deep learning platform and application to distributed training. The 5th International Conference on Learning Representations (ICLR), workshop track, 2017. [pdf]
  • Yuji Tokozume, Tatsuya Harada. Learning Environmental Sounds with End-to-end Convolutional Neural Network. The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017. [pdf]
  • Kuniaki Saito, Andrew Shin, Yoshitaka Ushiku, Tatsuya Harada. DUALNET: Domain-invariant Network for Visual Question Answering. The 18th IEEE International Conference on Multimedia and Expo (ICME), 2017. [pdf]
  • Qianru Sun, Hong Liu, Tatsuya Harada. Online growing neural gas for anomaly detection in changing surveillance scenes. Pattern Recognition, vol.64, pp.187-201, 2017.
• 2016
  • Yusuke Mukuta, Tatsuya Harada. Kernel Approximation via Empirical Orthogonal Decomposition for Unsupervised Feature Learning. The Twenty-Nineth IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [pdf]
  • Katsunori Ohnishi, Atsushi Kanehira, Asako Kanezaki, Tatsuya Harada. Recognizing Activities of Daily Living with a Wrist-mounted Camera. The Twenty-Nineth IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (spotlight oral) [pdf]
  • Atsushi Kanehira, Tatsuya Harada. Multi-label Ranking from Positive and Unlabeled Data. The Twenty-Nineth IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [pdf]
  • Andrew Shin, Yoshitaka Ushiku, Tatsuya Harada. Image Captioning with Sentiment Terms via Weakly-Supervised Sentiment Dataset. The British Machine Vision Conference (BMVC), pp.53.1-53.12, 2016. [pdf]
  • Atsushi Kanehira, Andrew Shin, Tatsuya Harada. True-negative Label Selection for Large-scale Multi-label Learning. 23rd International Conference on Pattern Recognition (ICPR), pp.3673-3678, 2016. [pdf]
  • Tetsuaki Mano, Hiroaki Yamane, Tatsuya Harada. Scene Image Synthesis from Natural Sentences Using Hierarchical Syntactic Analysis. ACM Multimedia, pp.112-116, 2016. [pdf]
  • Katsunori Ohnishi, Masatoshi Hidaka, Tatsuya Harada. Improved Dense Trajectory with Cross Streams. ACM Multimedia, pp.257-261, 2016. [pdf]
  • Shohei Yamamoto, Tatsuya Harada. Video Generation Using 3D Convolutional Neural Network. ACM Multimedia, pp.576-580, 2016. [pdf]
  • Andrew Shin, Katsunori Ohnishi, Tatsuya Harada. Beyond Caption To Narrative: Video Captioning With Multiple Sentences. ICIP, pp.3364-3368, 2016. [pdf]
  • Tomoaki Saito, Asako Kanezaki, Tatsuya Harada. IBC127: Video Dataset for Fine-grained Bird Classification. 2016 IEEE International Conference on Multimedia and Expo (ICME), 2016. [pdf]
• 2015
  • Yoshitaka Ushiku, Yusuke Mukuta, Masataka Yamaguchi, Tatsuya Harada. Common Subspace for Model and Similarity: Phrase Learning for Sentence Generation from Images. In the 15th International Conference on Computer Vision (ICCV), pp.2668-2676, 2015.
  • Asako Kanezaki, Tatsuya Harada. 3D Selective Search for Obtaining Object Candidates. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 82-87, 2015.
  • Chie Kamada, Asako Kanezaki, Tatsuya Harada. Probabilistic Semi-Canonical Correlation Analysis. Proceedings of the 23th Annual ACM International Conference on Multimedia (ACMMM), pp. 1131-1134, 2015.
  • Hiroharu Kato and Tatsuya Harada. Image Reconstruction from Bag-of-Visual-Words. arXiv preprint arXiv:1505.05190.
  • Hiroharu Kato and Tatsuya Harada. Visual Language Modeling on CNN Image Representations. arXiv preprint arXiv:1511.02872.
  • Katsunori Ohnishi, Atsushi Kanehira, Asako Kanezaki, Tatsuya Harada. Recognizing Activities of Daily Living with a Wrist-mounted Camera. arXiv preprint arXiv:1603.06208.
  • Ken Miura, Tetsuaki Mano, Atsushi Kanehira, Yuichiro Tsuchiya, Tatsuya Harada. MILJS : Brand New JavaScript Libraries for Matrix Calculation and Machine Learning. arXiv:1502.06064.
  • Ken Miura, Tatsuya Harada. Implementation of a Practical Distributed Calculation System with Browsers and JavaScript, and Application to Distributed Deep Learning. arXiv:1503.05743.
• 2014
  • Yusuke Mukuta, Tatsuya Harada. Probabilistic Partial Canonical Correlation Analysis. In Proceedings of the 31st International Conference on Machine Learning (ICML), pp.1449-1457, 2014.
  • Hiroharu Kato, Tatsuya Harada. Image Reconstruction from Bag-of-Visual-Words. In The Twenty-Seventh IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.955-962, 2014.
  • Yoshitaka Ushiku, Masatoshi Hidaka, Tatsuya Harada. Three Guidelines of Online Learning for Large-Scale Visual Recognition. In The Twenty-Seventh IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.3574-3581, 2014.
  • Asako Kanezaki, Sho Inaba, Yoshitaka Ushiku, Yuya Yamashita, Hiroshi Muraoka, Yasuo Kuniyoshi, Tatsuya Harada. Hard Negative Classes for Multiple Object Detection. 2014 IEEE International Conference on Robotics and Automation (ICRA), pp.3066-3073, 2014.
  • Asako Kanezaki, Emanuele Rodolà, Daniel Cremers, Tatsuya Harada. Learning Similarities for Rigid and Non-Rigid Object Detection. 2014 2nd International Conference on 3D Vision (3DV), pp.720-727, 2014.
  • Sho Inaba, Asako Kanezaki, Tatsuya Harada. Automatic Image Synthesis from Keywords Using Scene Context. Proceedings of the 22th Annual ACM International Conference on Multimedia (ACMMM), pp.1149-1152, 2014.
  • Masaru Mizuochi, Asako Kanezaki, Tatsuya Harada. Clothing Retrieval Based on Local Similarity with Multiple Images. Proceedings of the 22th Annual ACM International Conference on Multimedia (ACMMM), pp.1165-1168, 2014.
  • Asako Kanezaki, Yusuke Mukuta, Tatsuya Harada. Mirror Reflection Invariant HOG descriptors for Object Detection. In IEEE International Conference on Image Processing (ICIP), pp.1594-1598, 2014.
• 2013
  • Emanuele Rodolà, Andrea Torsello, Tatsuya Harada, Yasuo Kuniyoshi, Daniel Cremers. Elastic Net Constraints for Shape Matching. In the 14th International Conference on Computer Vision (ICCV), pp.1169-1176, 2013.
  • Asako Kanezaki, Yasuo Kuniyoshi, and Tatsuya Harada. Weakly-supervised Multi-class Object Detection Using Multi-type 3D Features. Proceedings of the 21th Annual ACM International Conference on Multimedia (ACMMM), pp. 605-608, 2013.
  • Emanuele Rodolà, Tatsuya Harada, Yasuo Kuniyoshi, and Daniel Cremers. Efficient Shape Matching using Vector Extrapolation. In The British Machine Vision Conference (BMVC), pp. 91.1-91.11, 2013.
• 2012
  • Tatsuya Harada, and Yasuo Kuniyoshi. Graphical Gaussian Vector for Image Categorization. The Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS), pp.1556-1564, 2012.
  • Yoshitaka Ushiku, Tatsuya Harada, and Yasuo Kuniyoshi. Efficient Image Annotation for Automatic Sentence Generation. The 20th Annual ACM International Conference on Multimedia (ACMMM), pp.549-558, 2012.
  • Hiroharu Kato, Tatsuya Harada, and Yasuo Kuniyoshi. Visual Anomaly Detection from Small Samples for Mobile Robots. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.3171-3178, 2012.
  • Fumihiro Bessho, Tatsuya Harada and Yasuo Kuniyoshi. Dialog System Using Real-Time Crowdsourcing and Twitter Large-Scale Corpus. Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp.227-231, 2012.
  • Yuya Yamashita, Tatsuya Harada, and Yasuo Kuniyoshi. Causal Flow. IEEE Transactions on Multimedia, Vol.3, No.3, pp.619-629, 2012.

Talk

• Yahoo! Japan Deep Learning Tokyo 2016, Yahoo! Japan, 3/20/2016 [slides]

Laboratory

Contact
Rm. 427 4th Bldg. 4-6-1 Komaba Meguro-ku, Tokyo 153-8904 JAPAN
Tel: +81-3-5452-5495
E-mail: harada [at] mi.t.u-tokyo.ac.jp