default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDTakayuki Okatani
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j27]Thannarot Kunlamai, Tatsuro Yamane, Masanori Suganuma, Pang-jo Chun, Takayuki Okatani:
Improving visual question answering for bridge inspection by pre-training with external data of image-text pairs. Comput. Aided Civ. Infrastructure Eng. 39(3): 345-361 (2024)- [j26]Qian Ye, Masanori Suganuma, Takayuki Okatani:
Improved high dynamic range imaging using multi-scale feature flows balanced between task-orientedness and accuracy. Comput. Vis. Image Underst. 248: 104126 (2024) - [j25]Shuang Liu
, Masanori Suganuma, Takayuki Okatani:
Symmetry-aware Neural Architecture for Embodied Visual Navigation. Int. J. Comput. Vis. 132(4): 1091-1107 (2024) - [j24]Jie Zhang, Masanori Suganuma, Takayuki Okatani:
That's BAD: blind anomaly detection by implicit local feature clustering. Mach. Vis. Appl. 35(2): 31 (2024) - [j23]Zhijie Wang, Masanori Suganuma, Takayuki Okatani:
Rethinking unsupervised domain adaptation for semantic segmentation. Pattern Recognit. Lett. 186: 119-125 (2024) - [c101]Li Sun, Liuan Wang, Jun Sun, Takayuki Okatani:
Temporal Insight Enhancement: Mitigating Temporal Hallucination in Video Understanding by Multimodal Large Language Models. ICPR (7) 2024: 455-473 - [c100]Wenzheng Song, Ran Yan, Boshu Lei, Takayuki Okatani:
Globalizing Local Features: Image Retrieval Using Shared Local Features with Pose Estimation for Faster Visual Localization. ICRA 2024: 6290-6297 - [c99]Jie Zhang, Masanori Suganuma, Takayuki Okatani:
Contextual Affinity Distillation for Image Anomaly Detection. WACV 2024: 148-157 - [c98]Xiangyong Lu, Masanori Suganuma, Takayuki Okatani:
SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers. WACV 2024: 1112-1122 - [c97]Yuki Tanaka, Shuhei M. Yoshida, Takashi Shibata, Makoto Terao, Takayuki Okatani, Masashi Sugiyama:
Appearance-Based Curriculum for Semi-Supervised Learning with Multi-Angle Unlabeled Data. WACV 2024: 2768-2777 - [i56]Li Sun, Liuan Wang, Jun Sun, Takayuki Okatani:
Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models. CoRR abs/2401.09861 (2024) - [i55]Yan Zeng, Masanori Suganuma, Takayuki Okatani:
An Improved Method for Personalizing Diffusion Models. CoRR abs/2407.05312 (2024) - [i54]Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani:
Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability. CoRR abs/2410.15315 (2024) - 2023
- [j22]Zhijie Wang, Xing Liu, Masanori Suganuma, Takayuki Okatani:
Unsupervised domain adaptation for semantic segmentation via cross-region alignment. Comput. Vis. Image Underst. 234: 103743 (2023) - [j21]Li Sun, Ping Wang, Liuan Wang, Jun Sun, Takayuki Okatani:
Zero-shot temporal event localisation: Label-free, training-free, domain-free. IET Comput. Vis. 17(5): 599-613 (2023) - [c96]Liang Xu, Han Zou, Takayuki Okatani:
How Do Label Errors Affect Thin Crack Detection by DNNs. CVPR Workshops 2023: 4414-4423 - [c95]Han Zou, Liang Xu, Takayuki Okatani:
Geometry Enhanced Reference-based Image Super-resolution. CVPR Workshops 2023: 6124-6133 - [c94]Qian Ye, Masanori Suganuma, Takayuki Okatani:
Accurate Single-Image Defocus Deblurring Based on Improved Integration with Defocus Map Estimation. ICIP 2023: 750-754 - [c93]Li Sun, Liuan Wang, Jun Sun, Takayuki Okatani:
Prompt Prototype Learning Based on Ranking Instruction For Few-Shot Visual Tasks. ICIP 2023: 3235-3239 - [c92]Jie Zhang, Masanori Suganuma, Takayuki Okatani:
Network Pruning and Fine-tuning for Few-shot Industrial Image Anomaly Detection. INDIN 2023: 1-6 - [c91]Yuichi Kamata, Moyuru Yamada, Takayuki Okatani:
Self-Modularized Transformer: Learn to Modularize Networks for Systematic Generalization. VISIGRAPP (5: VISAPP) 2023: 599-606 - [c90]Toshimichi Aota, Lloyd Teh Tzer Tong, Takayuki Okatani:
Zero-shot versus Many-shot: Unsupervised Texture Anomaly Detection. WACV 2023: 5553-5561 - [i53]Tatsuro Yamane, Pang-jo Chun, Ji Dang, Takayuki Okatani:
Bridge Damage Cause Estimation Using Multiple Images Based on Visual Question Answering. CoRR abs/2302.09208 (2023) - [i52]Han Zou, Masanori Suganuma, Takayuki Okatani:
Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Image. CoRR abs/2307.02875 (2023) - [i51]Han Zou, Masanori Suganuma, Takayuki Okatani:
RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution. CoRR abs/2307.02897 (2023) - [i50]Jie Zhang, Masanori Suganuma, Takayuki Okatani:
Contextual Affinity Distillation for Image Anomaly Detection. CoRR abs/2307.03101 (2023) - [i49]Jie Zhang, Masanori Suganuma, Takayuki Okatani:
That's BAD: Blind Anomaly Detection by Implicit Local Feature Clustering. CoRR abs/2307.03243 (2023) - [i48]Korawat Charoenpitaks, Van-Quang Nguyen, Masanori Suganuma, Masahiro Takahashi, Ryoma Niihara, Takayuki Okatani:
Visual Abductive Reasoning Meets Driving Hazard Prediction: Problem Formulation and Dataset. CoRR abs/2310.04671 (2023) - [i47]Xiangyong Lu, Masanori Suganuma, Takayuki Okatani:
SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers. CoRR abs/2311.03747 (2023) - 2022
- [c89]Huyen Thi Thanh Tran, Takayuki Okatani:
Bright as the Sun: In-depth Analysis of Imagination-Driven Image Captioning. ACCV (4) 2022: 675-691 - [c88]Shuang Liu, Takayuki Okatani:
Symmetry-aware Neural Architecture for Embodied Visual Exploration. CVPR 2022: 17221-17230 - [c87]Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani:
GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features. ECCV (36) 2022: 167-184 - [c86]Kang-Jun Liu, Masanori Suganuma, Takayuki Okatani:
Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning. NeurIPS 2022 - [i46]Zhijie Wang, Masanori Suganuma, Takayuki Okatani:
Rethinking Unsupervised Domain Adaptation for Semantic Segmentation. CoRR abs/2207.00067 (2022) - [i45]Qian Ye, Masanori Suganuma, Jun Xiao, Takayuki Okatani:
Learning Regularized Multi-Scale Feature Flow for High Dynamic Range Imaging. CoRR abs/2207.02539 (2022) - [i44]Qian Ye, Masanori Suganuma, Takayuki Okatani:
Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation. CoRR abs/2207.03047 (2022) - [i43]Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani:
GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features. CoRR abs/2207.09666 (2022) - [i42]Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani:
More Practical Scenario of Open-set Object Detection: Open at Category Level and Closed at Super-category Level. CoRR abs/2207.09775 (2022) - [i41]Wenzheng Song, Ran Yan, Boshu Lei, Takayuki Okatani:
SuperGF: Unifying Local and Global Features for Visual Localization. CoRR abs/2212.13105 (2022) - 2021
- [j20]Keiji Nagatani, Masato Abe, Koichi Osuka, Pang-jo Chun, Takayuki Okatani, Mayuko Nishio, Shota Chikushi, Takamitsu Matsubara, Yusuke Ikemoto, Hajime Asama:
Innovative technologies for infrastructure construction and maintenance through collaborative robots based on an open design approach. Adv. Robotics 35(11): 715-722 (2021) - [c85]Yuichi Kamata, Moyuru Yamada, Keizo Kato, Akira Nakagawa, Takayuki Okatani:
Symbolizing Visual Features for Pre-training with Unlabeled Images. ACPR (2) 2021: 490-503 - [c84]Wenzheng Song, Masanori Suganuma, Xing Liu, Noriyuki Shimobayashi, Daisuke Maruta, Takayuki Okatani:
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes. ICCV 2021: 6009-6018 - [c83]Tetsuya Tanaka, Yukihiro Sasagawa, Takayuki Okatani:
Learning to Bundle-adjust: A Graph Network Approach to Faster Optimization of Bundle Adjustment for Vehicular SLAM. ICCV 2021: 6230-6239 - [c82]Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani:
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks. IJCAI 2021: 923-930 - [c81]Qian Ye, Jun Xiao, Kin-Man Lam, Takayuki Okatani:
Progressive and Selective Fusion Network for High Dynamic Range Imaging. ACM Multimedia 2021: 5290-5297 - [i40]Engkarat Techapanurak, Takayuki Okatani:
Practical Evaluation of Out-of-Distribution Detection Methods for Image Classification. CoRR abs/2101.02447 (2021) - [i39]Engkarat Techapanurak, Anh-Chuong Dang, Takayuki Okatani:
Bridging In- and Out-of-distribution Samples for Their Better Discriminability. CoRR abs/2101.02500 (2021) - [i38]Liang Xu, Taro Hatsutani, Xing Liu, Engkarat Techapanurak, Han Zou, Takayuki Okatani:
Pushing the Envelope of Thin Crack Detection. CoRR abs/2101.03326 (2021) - [i37]Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani:
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks. CoRR abs/2106.00596 (2021) - [i36]Qian Ye, Jun Xiao, Kin-Man Lam, Takayuki Okatani:
Progressive and Selective Fusion Network for High Dynamic Range Imaging. CoRR abs/2108.08585 (2021) - [i35]Wenzheng Song, Masanori Suganuma, Xing Liu, Noriyuki Shimobayashi, Daisuke Maruta, Takayuki Okatani:
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes. CoRR abs/2109.03585 (2021) - [i34]Zhijie Wang, Xing Liu, Masanori Suganuma, Takayuki Okatani:
Cross-Region Domain Adaptation for Class-level Alignment. CoRR abs/2109.06422 (2021) - [i33]Zhijie Wang, Masanori Suganuma, Takayuki Okatani:
Improved Few-shot Segmentation by Redefinition of the Roles of Multi-level CNN Features. CoRR abs/2109.06432 (2021) - [i32]Shuang Liu, Takayuki Okatani:
Symmetry-aware Neural Architecture for Embodied Visual Navigation. CoRR abs/2112.09515 (2021) - 2020
- [j19]Yan Zhang, Junjie Hu, Takayuki Okatani:
Extending information maximization from a rate-distortion perspective. Neurocomputing 399: 285-295 (2020) - [c80]Engkarat Techapanurak, Masanori Suganuma, Takayuki Okatani:
Hyperparameter-Free Out-of-Distribution Detection Using Cosine Similarity. ACCV (4) 2020: 53-69 - [c79]Hiroto Date, Keisuke Kawasaki, Isao Hasegawa, Takayuki Okatani:
Deep Learning for Channel-Agnostic Brain Decoding across Multiple Subjects. BCI 2020: 1-6 - [c78]Yoshihiro Hirohashi, Kenichi Narioka, Masanori Suganuma, Xing Liu, Yukimasa Tamatsu, Takayuki Okatani:
Removal of Image Obstacles for Vehicle-mounted Surrounding Monitoring Cameras by Real-time Video Inpainting. CVPR Workshops 2020: 857-866 - [c77]Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani:
Efficient Attention Mechanism for Visual Dialog that Can Handle All the Interactions Between Multiple Inputs. ECCV (24) 2020: 223-240 - [c76]Takuya Fuchigami, Sadato Akahori, Takayuki Okatani, Yuanzhong Li:
A hyperacute stroke segmentation method using 3D U-Net integrated with physicians' knowledge for NCCT. Computer-Aided Diagnosis 2020 - [c75]Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani:
Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors. WACV 2020: 1399-1407 - [c74]Pongsate Tangseng, Takayuki Okatani:
Toward Explainable Fashion Recommendation. WACV 2020: 2142-2151 - [i31]Rito Murase, Masanori Suganuma, Takayuki Okatani:
How Can CNNs Use Image Position for Segmentation? CoRR abs/2005.03463 (2020)
2010 – 2019
- 2019
- [j18]Shuang Liu, Mete Ozay, Takayuki Okatani, Hongli Xu, Kai Sun, Yang Lin:
Detection and Pose Estimation for Short-Range Vision-Based Underwater Docking. IEEE Access 7: 2720-2749 (2019) - [c73]Hiroto Date, Keisuke Kawasaki, Isao Hasegawa, Takayuki Okatani:
Deep Learning for Natural Image Reconstruction from Electrocorticography Signals. BIBM 2019: 2331-2336 - [c72]Takayuki Okatani, Xing Liu, Masanori Suganuma:
Improving Generalization Ability of Deep Neural Networks for Visual Recognition Tasks. CCIW 2019: 3-13 - [c71]Xing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani:
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration. CVPR 2019: 7007-7016 - [c70]Masanori Suganuma, Xing Liu, Takayuki Okatani:
Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions. CVPR 2019: 9039-9048 - [c69]Duy-Kien Nguyen, Takayuki Okatani:
Multi-Task Learning of Hierarchical Vision-Language Representation. CVPR 2019: 10492-10501 - [c68]Mingzhen Shao, Zhun Sun, Mete Ozay, Takayuki Okatani:
Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment. FG 2019: 1-5 - [c67]Junjie Hu, Yan Zhang, Takayuki Okatani:
Visualization of Convolutional Neural Networks for Monocular Depth Estimation. ICCV 2019: 3868-3877 - [c66]Shuang Liu, Mete Özay, Hongli Xu, Yang Lin, Takayuki Okatani:
A Generative Model of Underwater Images for Active Landmark Detection and Docking. IROS 2019: 8034-8039 - [c65]Junjie Hu, Mete Ozay, Yan Zhang, Takayuki Okatani:
Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries. WACV 2019: 1043-1051 - [c64]Rito Murase, Yan Zhang, Takayuki Okatani:
Video-Rate Video Inpainting. WACV 2019: 1553-1561 - [p1]Masashi Konyo, Yuichi Ambe, Hikaru Nagano, Yu Yamauchi, Satoshi Tadokoro, Yoshiaki Bando, Katsutoshi Itoyama, Hiroshi G. Okuno, Takayuki Okatani, Kanta Shimizu, Eisuke Ito:
ImPACT-TRC Thin Serpentine Robot Platform for Urban Search and Rescue. Disaster Robotics 2019: 25-76 - [i30]Pongsate Tangseng, Takayuki Okatani:
Toward Explainable Fashion Recommendation. CoRR abs/1901.04870 (2019) - [i29]Xing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani:
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration. CoRR abs/1903.08817 (2019) - [i28]Junjie Hu, Yan Zhang, Takayuki Okatani:
Visualization of Convolutional Neural Networks for Monocular Depth Estimation. CoRR abs/1904.03380 (2019) - [i27]Mingzhen Shao, Zhun Sun, Mete Ozay, Takayuki Okatani:
Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment. CoRR abs/1905.08609 (2019) - [i26]Engkarat Techapanurak, Takayuki Okatani:
Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity. CoRR abs/1905.10628 (2019) - [i25]Xing Liu, Takayuki Okatani:
Evaluating Artificial Systems for Pairwise Ranking Tasks Sensitive to Individual Differences. CoRR abs/1905.13560 (2019) - [i24]Xing Liu, Masanori Suganuma, Takayuki Okatani:
Joint Learning of Multiple Image Restoration Tasks. CoRR abs/1907.04508 (2019) - [i23]Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani:
Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors. CoRR abs/1910.09212 (2019) - [i22]Junjie Hu, Takayuki Okatani:
Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Method. CoRR abs/1911.08790 (2019) - [i21]Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani:
Efficient Attention Mechanism for Handling All the Interactions between Many Inputs with Application to Visual Dialog. CoRR abs/1911.11390 (2019) - 2018
- [c63]Mete Özay, Takayuki Okatani:
Training CNNs With Normalized Kernels. AAAI 2018: 3884-3891 - [c62]Duy-Kien Nguyen, Takayuki Okatani:
Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering. CVPR 2018: 6087-6096 - [c61]Zhun Sun, Mete Ozay, Yan Zhang, Xing Liu, Takayuki Okatani:
Feature Quantization for Defending Against Distortion of Images. CVPR 2018: 7957-7966 - [c60]Masanori Suganuma, Mete Ozay, Takayuki Okatani:
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search. ICML 2018: 4778-4787 - [c59]Fazil Altinel, Mete Ozay, Takayuki Okatani:
Deep Structured Energy-Based Image Inpainting. ICPR 2018: 423-428 - [c58]Pongsate Tangseng, Kota Yamaguchi, Takayuki Okatani:
Recommending Outfits from Personal Closet. WACV 2018: 269-277 - [i20]Fazil Altinel, Mete Ozay, Takayuki Okatani:
Deep Structured Energy-Based Image Inpainting. CoRR abs/1801.07939 (2018) - [i19]Masanori Suganuma, Mete Özay, Takayuki Okatani:
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search. CoRR abs/1803.00370 (2018) - [i18]Junjie Hu, Mete Ozay, Yan Zhang, Takayuki Okatani:
Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries. CoRR abs/1803.08673 (2018) - [i17]Duy-Kien Nguyen, Takayuki Okatani:
Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering. CoRR abs/1804.00775 (2018) - [i16]Pongsate Tangseng, Kota Yamaguchi, Takayuki Okatani:
Recommending Outfits from Personal Closet. CoRR abs/1804.09979 (2018) - [i15]Duy-Kien Nguyen, Takayuki Okatani:
Multi-task Learning of Hierarchical Vision-Language Representation. CoRR abs/1812.00500 (2018) - [i14]Masanori Suganuma, Xing Liu, Takayuki Okatani:
Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions. CoRR abs/1812.00733 (2018) - 2017
- [j17]Ken Sakurada, Daiki Tetsuka, Takayuki Okatani:
Temporal city modeling using street level imagery. Comput. Vis. Image Underst. 157: 55-71 (2017) - [c57]Eisuke Ito, Takayuki Okatani:
Self-Calibration-Based Approach to Critical Motion Sequences of Rolling-Shutter Structure from Motion. CVPR 2017: 4512-4520 - [c56]Yan Zhang, Mete Ozay, Shuohao Li, Takayuki Okatani:
Truncating Wide Networks Using Binary Tree Architectures. ICCV 2017: 2116-2124 - [c55]Pongsate Tangseng, Kota Yamaguchi, Takayuki Okatani:
Recommending Outfits from Personal Closet. ICCV Workshops 2017: 2275-2279 - [i13]Mete Ozay, Takayuki Okatani:
Optimization on Product Submanifolds of Convolution Kernels. CoRR abs/1701.06123 (2017) - [i12]Yan Zhang, Mete Ozay, Shuohao Li, Takayuki Okatani:
Truncating Wide Networks using Binary Tree Architectures. CoRR abs/1704.00509 (2017) - [i11]Yan Zhang, Mete Ozay, Zhun Sun, Takayuki Okatani:
Information Potential Auto-Encoders. CoRR abs/1706.04635 (2017) - [i10]Zhun Sun, Mete Ozay, Takayuki Okatani:
Improving Robustness of Feature Representations to Image Deformations using Powered Convolution in CNNs. CoRR abs/1707.07830 (2017) - [i9]Zhun Sun, Mete Ozay, Takayuki Okatani:
Linear Discriminant Generative Adversarial Networks. CoRR abs/1707.07831 (2017) - [i8]Kota Yamaguchi, Takayuki Okatani, Takayuki Umeda, Kazuhiko Murasaki, Kyoko Sudo:
End-to-end learning potentials for structured attribute prediction. CoRR abs/1708.01892 (2017) - [i7]Zhun Sun, Mete Ozay, Takayuki Okatani:
HyperNetworks with statistical filtering for defending adversarial examples. CoRR abs/1711.01791 (2017) - [i6]Shuang Liu, Mete Ozay, Takayuki Okatani, Hongli Xu, Kai Sun, Yang Lin:
A vision based system for underwater docking. CoRR abs/1712.04138 (2017) - 2016
- [j16]Yasushi Akashi, Takayuki Okatani:
Separation of reflection components by sparse non-negative matrix factorization. Comput. Vis. Image Underst. 146: 77-85 (2016) - [j15]Ken Sakurada, Takayuki Okatani, Kris M. Kitani:
Hybrid macro-micro visual analysis for city-scale state estimation. Comput. Vis. Image Underst. 146: 86-98 (2016) - [j14]Tatsuro Orikasa, Takayuki Okatani:
A Gaze-Reactive Display for Simulating Depth-of-Field of Eyes When Viewing Scenes with Multiple Depths. IEICE Trans. Inf. Syst. 99-D(3): 739-746 (2016) - [c54]Takuya Yashima, Naoaki Okazaki, Kentaro Inui, Kota Yamaguchi, Takayuki Okatani:
Learning to Describe E-Commerce Images from Noisy Online Data. ACCV (5) 2016: 85-100 - [c53]Zhun Sun, Mete Ozay, Takayuki Okatani:
Design of Kernels in Convolutional Neural Networks for Image Classification. ECCV (7) 2016: 51-66 - [c52]Sirion Vittayakorn, Takayuki Umeda, Kazuhiko Murasaki, Kyoko Sudo, Takayuki Okatani, Kota Yamaguchi:
Automatic Attribute Discovery with Neural Activations. ECCV (4) 2016: 252-268 - [c51]Yan Zhang, Mete Ozay, Xing Liu, Takayuki Okatani:
Integrating deep features for material recognition. ICPR 2016: 3697-3702 - [c50]Masayasu Muraoka, Sumit Maharjan, Masaki Saito, Kota Yamaguchi, Naoaki Okazaki, Takayuki Okatani, Kentaro Inui:
Recognizing Open-Vocabulary Relations between Objects in Images. PACLIC 2016 - [i5]Sirion Vittayakorn, Takayuki Umeda, Kazuhiko Murasaki, Kyoko Sudo, Takayuki Okatani, Kota Yamaguchi:
Automatic Attribute Discovery with Neural Activations. CoRR abs/1607.07262 (2016) - [i4]Mete Ozay, Takayuki Okatani:
Optimization on Submanifolds of Convolution Kernels in CNNs. CoRR abs/1610.07008 (2016) - [i3]Eisuke Ito, Takayuki Okatani:
Self-calibration-based Approach to Critical Motion Sequences of Rolling-shutter Structure from Motion. CoRR abs/1611.05476 (2016) - 2015
- [c49]Kota Yamaguchi, Takayuki Okatani, Kyoko Sudo, Kazuhiko Murasaki, Yukinobu Taniguchi:
Mix and Match: Joint Model for Clothing and Attribute Recognition. BMVC 2015: 51.1-51.12 - [c48]Ken Sakurada, Takayuki Okatani:
Change Detection from a Street Image Pair using CNN Features and Superpixel Segmentation. BMVC 2015: 61.1-61.12 - [c47]Masaki Saito, Takayuki Okatani:
Transformation of Markov Random Fields for marginal distribution estimation. CVPR 2015: 797-805 - [c46]Daiki Tetsuka, Takayuki Okatani:
Detecting Building-Level Changes of a City Using Street Images and a 2D City Map. WACV 2015: 349-356 - [i2]Yan Zhang, Mete Ozay, Xing Liu, Takayuki Okatani:
Integrating Deep Features for Material Recognition. CoRR abs/1511.06522 (2015) - [i1]Zhun Sun, Mete Özay, Takayuki Okatani:
Design of Kernels in Convolutional Neural Networks for Image Classification. CoRR abs/1511.09231 (2015) - 2014
- [c45]Ken Sakurada, Takayuki Okatani, Kris M. Kitani:
Massive City-Scale Surface Condition Analysis Using Ground and Aerial Imagery. ACCV (1) 2014: 49-64 - [c44]Makoto Ozeki, Takayuki Okatani:
Understanding Convolutional Neural Networks in Terms of Category-Level Attributes. ACCV (2) 2014: 362-375 - [c43]Yasuhiro Akashi, Takayuki Okatani:
Separation of Reflection Components by Sparse Non-negative Matrix Factorization. ACCV (5) 2014: 611-625 - [r1]Takayuki Okatani:
Curvature. Computer Vision, A Reference Guide 2014: 154-159 - 2013
- [j13]Tomohiro Ushiki, Eisuke Ito, Takayuki Okatani:
Improving Accuracy of Planar Tracking by Resolving Resolution Inconsistencies. IPSJ Trans. Comput. Vis. Appl. 5: 109-113 (2013) - [c42]Masaki Saito, Takayuki Okatani, Koichiro Deguchi:
Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space. CVPR 2013: 57-64 - [c41]Ken Sakurada, Takayuki Okatani, Koichiro Deguchi:
Detecting Changes in 3D Structure of a Scene from Multi-view Images Captured by a Vehicle-Mounted Camera. CVPR 2013: 137-144 - 2012
- [c40]Takayuki Okatani, Koichiro Deguchi:
Optimal integration of photometric and geometric surface measurements using inaccurate reflectance/illumination knowledge. CVPR 2012: 254-261 - [c39]Masaki Saito, Takayuki Okatani, Koichiro Deguchi:
Application of the mean field methods to MRF optimization in computer vision. CVPR 2012: 1680-1687 - [c38]Takayuki Okatani, Jun Yanagisawa, Daiki Tetsuka, Ken Sakurada, Koichiro Deguchi:
Creating Multi-Viewpoint Panoramas of Streets with Sparsely Located Buildings. FSR 2012: 65-79 - [c37]Takashi Abe, Takayuki Okatani, Koichiro Deguchi:
Recognizing surface qualities from natural images based on learning to rank. ICPR 2012: 3712-3715 - 2011
- [c36]Ryosuke Taira, Satoshi Saga, Takayuki Okatani, Koichiro Deguchi:
Optimum method for real-time reconstruction of sensor surface in total-internal-reflection based tactile sensor. World Haptics 2011: 329-334 - [c35]Momotaro Koike, Satoshi Saga, Takayuki Okatani, Koichiro Deguchi:
Sensing method of total-internal-reflection-based tactile sensor. World Haptics 2011: 615-619 - [c34]Takayuki Okatani, Takahiro Yoshida, Koichiro Deguchi:
Efficient algorithm for low-rank matrix factorization with missing components and performance comparison of latest algorithms. ICCV 2011: 842-849 - [c33]Eisuke Ito, Takayuki Okatani, Koichiro Deguchi:
Accurate and robust planar tracking based on a model of image sampling and reconstruction process. ISMAR 2011: 1-8 - 2010
- [j12]Tomoya Okazaki, Takayuki Okatani, Koichiro Deguchi:
A Projector-Camera System for High-Quality Synthesis of Virtual Reflectance on Real Object Surfaces. Inf. Media Technol. 5(2): 691-703 (2010) - [j11]Tomoya Okazaki, Takayuki Okatani, Koichiro Deguchi:
A Projector-Camera System for High-Quality Synthesis of Virtual Reflectance on Real Object Surfaces. IPSJ Trans. Comput. Vis. Appl. 2: 71-83 (2010) - [c32]Daisuke Abe, Takayuki Okatani, Koichiro Deguchi:
Flexible Online Calibration for a Mobile Projector-Camera System. ACCV (4) 2010: 565-579
2000 – 2009
- 2009
- [j10]Takayuki Okatani, Koichiro Deguchi:
Easy Calibration of a Multi-projector Display System. Int. J. Comput. Vis. 85(1): 1-18 (2009) - [j9]Takayuki Okatani, Mikio Wada, Koichiro Deguchi:
Study of Image Quality of Superimposed Projection Using Multiple Projectors. IEEE Trans. Image Process. 18(2): 424-429 (2009) - [c31]Takayuki Okatani, Koichiro Deguchi:
On bias correction for geometric parameter estimation in computer vision. CVPR 2009: 959-966 - [c30]Takayuki Okatani, Koichiro Deguchi:
Improving accuracy of geometric parameter estimation using projected score method. ICCV 2009: 1733-1740 - [c29]Tomoya Okazaki, Takayuki Okatani, Koichiro Deguchi:
Shape Reconstruction by Combination of Structured-Light Projection and Photometric Stereo Using a Projector-Camera System. PSIVT 2009: 410-422 - 2007
- [j8]Takayuki Okatani, Koichiro Deguchi:
On the Wiberg Algorithm for Matrix Factorization in the Presence of Missing Components. Int. J. Comput. Vis. 72(3): 329-337 (2007) - [c28]Takayuki Okatani, Koichiro Deguchi:
Variational Bayes Based Approach to Robust Subspace Learning. CVPR 2007 - [c27]Takayuki Okatani, Koichiro Deguchi:
Estimating Scale of a Scene from a Single Image Based on Defocus Blur and Scene Geometry. CVPR 2007 - [c26]Rui Ishiyama, Takayuki Okatani, Koichiro Deguchi:
Precise 3-D Measurement using Uncalibrated Pattern Projection. ICIP (1) 2007: 225-228 - [c25]Kousuke Kamada, Takayuki Okatani, Koichiro Deguchi:
A Physics-Based Imaging Model of Scanning Electron Microscopes. MVA 2007: 102-105 - 2006
- [j7]Daiki Kawanaka, Takayuki Okatani, Koichiro Deguchi:
HHMM Based Recognition of Human Activity. IEICE Trans. Inf. Syst. 89-D(7): 2180-2185 (2006) - [c24]Takayuki Okatani, Koichiro Deguchi:
Autocalibration of an Ad Hoc Construction of Multi-Projector Displays. CVPR Workshops 2006: 4 - [c23]Manabu Ushizaki, Takayuki Okatani, Koichiro Deguchi:
Video Synchronization Based on Co-occurrence of Appearance Changes in Video Sequences. ICPR (3) 2006: 71-74 - [c22]Shun Ushida, Kousuke Yoshimi, Takayuki Okatani, Koichiro Deguchi:
The Importance of Gaze Control Mechanism on Vision-based Motion Control of a Biped Robot. IROS 2006: 4447-4452 - 2005
- [j6]Takayuki Okatani, Koichiro Deguchi:
Autocalibration of a Projector-Camera System. IEEE Trans. Pattern Anal. Mach. Intell. 27(12): 1845-1855 (2005) - [c21]Shota Takizawa, Shun Ushida, Takayuki Okatani, Koichiro Deguchi:
2DOF motion stabilization of biped robot by gaze control strategy. IROS 2005: 1102-1107 - [c20]Shota Takizawa, Shun Ushida, Takayuki Okatani, Koichiro Deguchi:
Motion Stabilization of Biped Robot by Gaze Control. MVA 2005: 324-327 - [c19]Daiki Kawanaka, Shun Ushida, Takayuki Okatani, Koichiro Deguchi:
HHMM Based Recognition of Human Activity Motion Trajectories in Image Sequences. MVA 2005: 578-581 - 2004
- [c18]Takayuki Okatani:
A Probabilistic Approach to Linear Subspace Fitting for Computer Vision Problems. CVPR Workshops 2004: 185 - [c17]Yoshinori Satoh, Takayuki Okatani, Koichiro Deguchi:
A Color-based Tracking by Kalman Particle Filter. ICPR (3) 2004: 502-505 - [c16]Koichiro Deguchi, Oki Kawanaka, Takayuki Okatani:
Object Tracking by the Mean-Shift of Regional Color Distribution Combined with the Particle-Filter Algorithm. ICPR (3) 2004: 506-509 - [c15]Yoshinori Satoh, Takayuki Okatani, Koichiro Deguchi:
A color-based probabilistic tracking by using graphical models. IROS 2004: 631-636 - 2003
- [j5]Yoshinori Satoh, Takayuki Okatani, Koichiro Deguchi:
Binocular motion tracking by gaze fixation control and three-dimensional shape reconstruction. Adv. Robotics 17(10): 1057-1072 (2003) - [c14]Takayuki Okatani, Koichiro Deguchi:
Toward a Statistically Optimal Method for Estimating Geometric Relations from Noisy Data: Cases of Linear Relations. CVPR (1) 2003: 432-439 - [c13]Takayuki Okatani, Koichiro Deguchi:
Autocalibration of a Projector-Screen-Camera System: Theory and Algorithm for Screen-to-Camera Homography Estimation. ICCV 2003: 774-781 - [c12]Koji Hamasaki, Taira Nakajima, Takayuki Okatani, Koichiro Deguchi:
Tracking multiple three-dimensional motions by using modified condensation algorithm and multiple images. IROS 2003: 236-241 - 2002
- [c11]Takayuki Okatani, Koichiro Deguchi:
Robust Estimation of Camera Translation Between Two Images Using a Camera With a 3D Orientation Sensor. ICPR (1) 2002: 275-278 - [c10]Yoshinori Satoh, Tomohiro Nakagawa, Takayuki Okatani, Koichiro Deguchi:
A motion tracking by extracting 3D feature of moving objects with binocular cooperative fixation. IROS 2002: 13-18 - [c9]Koichiro Deguchi, Koji Hamasaki, Taira Nakajima, Takayuki Okatani:
3-Dimensional Tracking of Multiple Object Motions from Multi-view Images by Mixed-state CONDENSATION Algorithm. MVA 2002: 408-411 - 2001
- [j4]Takayuki Okatani, Koichiro Deguchi:
On Uniqueness of Solutions of the Three-Light-Source Photometric Stereo: Conditions on Illumination Configuration and Surface Reflectance. Comput. Vis. Image Underst. 81(2): 211-226 (2001) - [c8]Takayuki Okatani, Koichiro Deguchi:
On Photometric Aspects of Catadioptric Cameras. CVPR (1) 2001: 1106-1113 - 2000
- [j3]Takayuki Okatani, Koichiro Deguchi:
Closed Form Solution of Local Shape from Shading at Critical Points. Int. J. Comput. Vis. 40(2): 169-178 (2000) - [c7]Takayuki Okatani, Koichiro Deguchi:
Estimation of Illumination Distribution Using a Specular Sphere. ICPR 2000: 3596-3599 - [c6]Takayuki Okatani, Koichiro Deguchi:
Yet Another Appearance-Based Method for Pose Estimation Based on a linear Model. MVA 2000: 258-261 - [c5]Takayuki Okatani, Koichiro Deguchi:
Recovering Camera Motion from Image Sequence Based on Registration of Silhouette Cones: Shape from Silhouette Using a Mobile Camera with a Gyro Sensor. MVA 2000: 451-454
1990 – 1999
- 1999
- [j2]Takayuki Okatani, Koichiro Deguchi:
Computation of the Sign of the Gaussian Curvature of a Surface from Multiple Unknown Illumination Images without Knowledge of the Reflectance Property. Comput. Vis. Image Underst. 76(2): 125-134 (1999) - 1998
- [c4]Takayuki Okatani, Koichiro Deguchi:
On the Classification of Singular Points for the Global Shape from Shading Problem: A Study of the Constraints Imposed by Isophotes. ACCV (1) 1998: 48-55 - [c3]Takayuki Okatani, Koichiro Deguchi:
Determination of Sign of Gaussian Curvature of Surface Having General Reflectance Property. ACCV (1) 1998: 56-63 - [c2]Takayuki Okatani, Koichiro Deguchi:
On identification of singular points using photometric invariants for global shape from shading problem. ICPR 1998: 1787-1790 - 1997
- [j1]Takayuki Okatani, Koichiro Deguchi:
Shape Reconstruction from an Endoscope Image by Shape from Shading Technique for a Point Light Source at the Projection Center. Comput. Vis. Image Underst. 66(2): 119-131 (1997) - 1996
- [c1]Takayuki Okatani, Koichiro Deguchi:
Reconstructing shape from shading with a point light source at the projection center: shape reconstruction from an endoscope image. ICPR 1996: 830-834
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-15 02:20 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
