Okatani Takayuki
Okatani Takayuki
Professor, Graduate School of Information Sciences, Tohoku University / RIKEN Center for AIP
Bestätigte E-Mail-Adresse bei - Startseite
Zitiert von
Zitiert von
Revisiting single image depth estimation: Toward higher resolution maps with accurate object boundaries
J Hu, M Ozay, Y Zhang, T Okatani
IEEE Winter Conference on Applications of Computer Vision (WACV), 1043-1051, 2019
Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering
DK Nguyen, T Okatani
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6087-6096, 2018
Shape reconstruction from an endoscope image by shape from shading technique for a point light source at the projection center
T Okatani, K Deguchi
Computer vision and image understanding 66 (2), 119-131, 1997
Dual residual networks leveraging the potential of paired operations for image restoration
X Liu, M Suganuma, Z Sun, T Okatani
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7007-7016, 2019
A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks
CV Dung, H Sekiya, S Hirano, T Okatani, C Miki
Automation in Construction 102, 217-229, 2019
On the Wiberg algorithm for matrix factorization in the presence of missing components
T Okatani, K Deguchi
International Journal of Computer Vision 72, 329-337, 2007
Change detection from a street image pair using cnn features and superpixel segmentation
K Sakurada, T Okatani
British Machine Vision Conference (BMVC) 61, 1-12, 2015
Object tracking by the mean-shift of regional color distribution combined with the particle-filter algorithms
K Deguchi, O Kawanaka, T Okatani
Proceedings of the 17th International Conference on Pattern Recognition …, 2004
Separation of reflection components by sparse non-negative matrix factorization
Y Akashi, T Okatani
Asian Conference on Computer Vision (ACCV), 611-625, 2015
Efficient algorithm for low-rank matrix factorization with missing components and performance comparison of latest algorithms
T Okatani, T Yoshida, K Deguchi
International Conference on Computer Vision (ICCV), 842-849, 2011
Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search
M Suganuma, M Ozay, T Okatani
International Conference on Machine Learning, 4771-4780, 2018
Attention-based adaptive selection of operations for image restoration in the presence of unknown combined distortions
M Suganuma, X Liu, T Okatani
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9039-9048, 2019
Detecting changes in 3D structure of a scene from multi-view images captured by a vehicle-mounted camera
K Sakurada, T Okatani, K Deguchi
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 137-144, 2013
Deep learning
T Okatani
Machine Learning Professional Series, Kodansha Ltd, 2015
Mix and Match: Joint Model for Clothing and Attribute Recognition.
K Yamaguchi, T Okatani, K Sudo, K Murasaki, Y Taniguchi
British Machine Vision Conference (BMVC) 1 (2), 4, 2015
Hyperparameter-free out-of-distribution detection using cosine similarity
E Techapanurak, M Suganuma, T Okatani
Proceedings of the Asian conference on computer vision, 2020
Autocalibration of a projector-camera system
T Okatani, K Deguchi
IEEE Transactions on Pattern Analysis and Machine Intelligence 27 (12), 1845 …, 2005
Visualization of convolutional neural networks for monocular depth estimation
J Hu, Y Zhang, T Okatani
IEEE/CVF International Conference on Computer Vision (ICCV), 3869-3878, 2019
Grit: Faster and better image captioning transformer using dual visual features
VQ Nguyen, M Suganuma, T Okatani
European Conference on Computer Vision, 167-184, 2022
Automatic attribute discovery with neural activations
S Vittayakorn, T Umeda, K Murasaki, K Sudo, T Okatani, K Yamaguchi
European Conference on Computer Vision (ECCV), 252-268, 2016
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20