論文等

 

 

2023 


Unsupervised domain adaptation for semantic segmentation via cross-region alignment
Computer Vision and Image Understanding (CVIU)
Zhijie Wang, Xing Liu, Masanori Suganuma, and Takayuki Okatani
 
Accurate Single-Image Defocus Deblurring Based on Improved Integration with Defocus Map Estimation
IEEE Conference on Image Processing (ICIP)
Qian Ye, Masanori Suganuma, and Takayuki Okatani
 
 

 

2022 


Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning
Neural Information Processing Systems (NeurIPS)
Kang-Jun Liu, Masanori Suganuma, Takayuki Okatani
 
GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features
European Conference on Computer Vision (ECCV)
Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
 
Symmetry-aware Neural Architecture for Embodied Visual Navigation
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Shuang Liu, Takayuki Okatani
 

 

2021


Learning to Bundle-adjust: A Graph Network Approach to Faster Optimization of Bundle Adjustment for Vehicular SLAM
International Conference on Computer Vision (ICCV)
Tetsuya Tanaka, Yukihiro Sasagawa, Takayuki Okatani
 
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes
International Conference on Computer Vision (ICCV)
Wenzheng Song, Masanori Suganuma, Xing Liu, Noriyuki Shimobayashi, Daisuke Maruta, Takayuki Okatani
 
Progressive and Selective Fusion Network for High Dynamic Range Imaging
ACM International Conference on Multimedia (ACMMM)
Qian Ye, Jun Xiao, Kin-man Lam, Takayuki Okatani
 
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks
International Joint Conferences on Artificial Intelligence (IJCAI)
Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani

 

2020 


 
Hyperparameter-Free Out-of-Distribution Detection Using Cosine Similarity
Asian Conference on Computer Vision (ACCV)
Engkarat Techapanurak, Masanori Suganuma, Takayuki Okatani
 
Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs
European Conference on Computer Vision (ECCV)
Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
[arXiv]
 
Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors
IEEE Winter Conference on Applications of Computer Vision (WACV)
Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
[arXiv]
 
 

2019 


Visualization of Convolutional Neural Networks for Monocular Depth Estimation
International Conference on Computer Vision (ICCV)
Junjie Hu, Yan Zhang, Takayuki Okatani
[arXiv] [code]
 
Guaranteed Matrix Completion under Multiple Linear Transformations
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Chao Li, Wei He, Longhao Yuan, Zhun Sun, Qibin Zhao
 
Multi-task Learning of Hierarchical Vision-Language Representation
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Duy-Kien Nguyen, Takayuki Okatani
 
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Xing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani
[PDF] [arXiv] [code]
 
Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Masanori Suganuma, Xing Liu, Takayuki Okatani
[PDF] [arXiv] [code]
 
Low-Rank Embedding of Kernels in Convolutional Neural Networks under Random Shuffling
International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Chao Li, Zhun Sun, Jinshi Yu, Ming Hou, Qibin Zhao
 
Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment
IEEE International Conference on Automatic Face & Gesture Recognition  (FG2019)
Mingzhen Shao, Zhun Sun, Mete Ozay, Takayuki Okatani
 
Video-rate Video Inpainting
IEEE Winter Conference on Applications of Computer Vision (WACV)
Rito Murase, Yan Zhang, Takayuki Okatani
 
Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries
IEEE Winter Conference on Applications of Computer Vision (WACV)
Junjie Hu,  Mete Ozay, Yan Zhang, Takayuki Okatani
 
 

 

2018


Encoding the local connectivity patterns of fMRI for cognitive task and state classification
Brain Imaging and Behavior, 2018
I. Onal, M. Ozay, and F. Yarman-Vural
 
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
International Conference on Machine Learning (ICML) 2018 (Oral Presentation, short talk)
Masanori Suganuma, Mete Ozay, Takayuki Okatani
 
A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
Sister Conference Best Paper Track at IJCAI-2018
Masanori Suganuma, Shinichi Shirakawa, Tomoharu Nagao
 
Deep Structured Energy-Based Image Inpainting
International Conference on Pattern and Recognition (ICPR) 2018
Fazil Altinel, Mete Ozay, Takayuki Okatani
 
Learning Deep Representations for Detection of Docking Stations using Underwater Imaging
OCEANS'18
Shuang Liu, Mete Ozay, Takayuki Okatani, Hongli Xu, Yang Lin, Haitao Gu
 
Perturbation Tolerance of Deep Neural Networks and Humans in Material Recognition
Annual Meeting of the Vision Sciences Society (VSS) 2018
Xing Liu, Masataka Sawayama, Ryusuke Hayashi, Mete Ozay, Takayuki Okatani and Shin'ya Nishida
 
Improved Fusion of Visual and Language Representations by Dense Symmetric Coattention for Visual Question Answering
Computer Vision and Pattern Recognition (CVPR) Oral Presentation
Nguyen Duy Kien and Takayuki Okatani
[pdf]
 
Feature Quantization for Defending Against Distortion of Images
Computer Vision and Pattern Recognition (CVPR)
Zhun Sun, Mete Ozay, Yan Zhang, Xing Liu and Takayuki Okatani
[pdf]

Training CNNs with Normalized Kernels
The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI) Oral Presentation
Mete Ozay and Takayuki Okatani

Recommending Outfit from Personal Closet
IEEE Winter Conference on Applications of Computer Vision (WACV)
Pongsate Tangseng, Kota Yamaguchi, Takayuki Okatani 
 
 


A vision based system for underwater docking
arXiv preprint
Shuang Liu, Mete Ozay, Takayuki Okatani, Hongli Xu, Kai Sun and Yang Lin
 
HyperNetworks with statistical filtering for defending adversarial examples
arXiv preprint
Zhun Sun, Mete Ozay and Takayuki Okatani
 
End-to-end learning potentials for structured attribute prediction
arXiv preprint
Kota Yamaguchi, Takayuki Okatani, Takayuki Umeda, Kazuhiko Murasaki, Kyoko Sudo
 
Temporal city modeling using street level imagery
Computer Vision and Image Understanding
Ken Sakurada, Daiki Tetsuka, Takayuki Okatani
 
Hierarchical Multi-resolution Mesh Networks for Brain Decoding 
Brain Imaging and Behavior , 2017
I. Onal, M. Ozay, and F. Yarman-Vural
[link][arxiv]
 

Self-calibration-based Approach to Critical Motion Sequences of Rolling-shutter Structure from Motion
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Ito, E., & Okatani, T.
[arxiv]

 

Temporal city modeling using street level imagery
Computer Vision and Image Understanding (CVIU)
Sakurada, K., Tetsuka, D., & Okatani, T.
[link]
 
A New Representation of fMRI Signal by a Set of Local Meshes for Brain Decoding
IEEE Transactions on Signal and Information Processing over Networks,
I. Onal, M. Ozay, E. Mizrak, I. Oztekin, and F. Yarman-Vural.
[link] [code]
 
Truncating Wide Networks using Binary Tree Architectures
International Conference on Computer Vision (ICCV)
Y. Zhang, M. Ozay, S. Li, and T. Okatani.
 
Optimization on Product Submanifolds of Convolution Kernels
arXiv preprint
M. Ozay and T. Okatani.
 
Information Potential Auto-Encoders
arXiv preprint
Y. Zhang, M. Ozay, Z. Sun, and T. Okatani.
[arXiv]
 
Linear Discriminant Generative Adversarial Networks
arXiv preprint
Z. Sun, M. Ozay, and T. Okatani.

Learning to Describe E-Commerce Images from Noisy Online Data
Asian Conference on Computer Vision (ACCV)
Yashima, T., Okazaki, N., Inui, K., Yamaguchi, K., & Okatani, T.
[pdf]

Recognizing Open-Vocabulary Relations between Objects in Images
Pacific Asia Conference on Language, Information and Computation (PACLIC)
Muraoka, M., Maharjan, S., Saito, M., Yamaguchi, K., Okazaki, N., Okatani, T., & Inui, K.
[pdf

Large Scale Retrieval and Generation of Image Descriptions
International Journal of Computer Vision (IJCV)
Ordonez, V., Han, X., Kuznetsova, P., Kulkarni, G., Mitchell, M., Yamaguchi, K., Stratos, K., Goyal, A., Dodge, J., Mensch, A., Daumé III, H., Berg, A.C., Choi, Y, and Berg, T.L.
[link

Separation of reflection components by sparse non-negative matrix factorization
Computer Vision and Image Understanding (CVIU)
Akashi, Y., & Okatani, T.
[pdf]

Hybrid macro–micro visual analysis for city-scale state estimation
Computer Vision and Image Understanding (CVIU)
Sakurada, K., Okatani, T., & Kitani, K. M.
[link

A Gaze-Reactive Display for Simulating Depth-of-Field of Eyes When Viewing Scenes with Multiple Depths
IEICE Transactions on Information and Systems
Orikasa, T., & Okatani, T.
[link

Design of Kernels in Convolutional Neural Networks for Image Classification
European Conference on Computer Vision (ECCV)
Sun, Z., Ozay, M., & Okatani, T.
[link, arxiv]

Automatic Attribute Discovery with Neural Activations
European Conference on Computer Vision (ECCV)
Vittayakorn, S., Umeda, T., Murasaki, K., Sudo, K., Okatani, T., & Yamaguchi, K.
[arxiv, project page, poster]

Integrating Deep Features for Material Recognition
International Conference on Pattern Recognition (ICPR)
Zhang, Y., Ozay, M., Liu, X., & Okatani, T.
[arxiv, poster]

Hierarchical distance learning by stacking nearest neighbor classifiers
Information Fusion
Ozay, M., & Yarman-Vural, F. T.
[arxiv, code, data

Optimization on Submanifolds of Convolution Kernels in CNNs
arXiv preprint
Ozay, M., Okatani, T.
[arxiv]
 
Encoding the Local Connectivity Patterns of fMRI for Cognitive State Classification
arXiv preprint
Onal Ertugrul, I., Ozay, M., Yarman Vural, F. T.
[arxiv
 
Modeling the Sequence of Brain Volumes by Local Mesh Models for Brain Decoding
arXiv preprint
Onal, I., Ozay, M., Mizrak, E., Oztekin, I., Yarman Vural, F. T.
[arxiv
 
A Hierarchical Multi-resolution Mesh Network for Brain Decoding
arXiv preprint
Onal, I., Ozay, M., Yarman Vural, F. T.
[arxiv]

 


Mix and match: joint model for clothing and attribute recognition
Proceedings of the British Machine Vision Conference (BMVC)
Yamaguchi, K., Okatani, T., Sudo, K., Murasaki, K., & Taniguchi, Y.
[pdf

Change detection from a street image pair using cnn features and superpixel segmentation
Proceedings of the British Machine Vision Conference (BMVC)
Sakurada, K., & Okatani, T.
[pdf

Transformation of Markov Random Fields for Marginal Distribution Estimation
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Saito, M., & Okatani, T.
[pdf, extended abstract

Detecting Building-level Changes of a City Using Street Images and a 2D City Map
IEEE Winter Conference on Applications of Computer Vision (WACV)
Tetsuka, D., & Okatani, T.
[pdfsupplementary material]

Runway to realway: Visual analysis of fashion
IEEE Winter Conference on Applications of Computer Vision (WACV)
Vittayakorn, S., Yamaguchi, K., Berg, A. C., & Berg, T. L.
[project page]

Functional Mesh Model with Temporal Measurements for Brain Decoding
Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Onal, I., Ozay, M., & Vural, F. T. Y.
[link

Modeling Voxel Connectivity for Brain Decoding
The International Workshop on Pattern Recognition in Neuroimaging (PRNI)
Onal, I., Ozay, M., & Vural, F. T. Y.
[link

Machine Learning Methods for Attack Detection in the Smart Grid
IEEE Transactions on Neural Networks and Learning Systems
Ozay, M., Esnaola, I., Vural, F. T. Y., Kulkarni, S. R., & Poor, H. V.
[link, arxiv

Compositional Hierarchical Representation of Shape Manifolds for Classification of Non-manifold Shapes
International Conference on Computer Vision (ICCV)
Ozay, M., Rusen Aktas, U., Wyatt, J. L., & Leonardis, A.
[linkproject page, code]

Retrieving Similar Styles to Parse Clothing
IEEE transactions on pattern analysis and machine intelligence (TPAMI)
Yamaguchi, K., Kiapour, M. H., Ortiz, L. E., & Berg, T. L.
[link]

 


Massive City-scale Surface Condition Analysis using Ground and Aerial Imagery
Asian Conference on Computer Vision (ACCV) Oral presentation
Sakurada, K., Okatani, T., & Kitani, K. M.
[pdf]

Understanding convolutional neural networks in terms of category-level attributes
Asian Conference on Computer Vision (ACCV)
Ozeki, M., & Okatani, T. 
[pdf

Separation of reflection components by sparse non-negative matrix factorization
Asian Conference on Computer Vision (ACCV)

Akashi, Y., & Okatani, T.
[pdf]

Hipster wars: Discovering elements of fashion styles
European Conference on Computer Vision (ECCV)
Kiapour, M. H., Yamaguchi, K., Berg, A. C., & Berg, T. L.
[project page]

Chic or Social: Visual Popularity Analysis in Online Fashion Networks
ACM Multimedia
Yamaguchi, K., Berg, T. L., & Ortiz, L. E.
[pdf, project page]

 


Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Oral presentation
Saito, M., Okatani, T., & Deguchi, K.
[pdf, supplementary material, poster

Detecting changes in 3D structure of a scene from multi-view images captured by a vehicle-mounted camera
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Sakurada, K., Okatani, T., & Deguchi, K. 
[pdf, supplementary material, poster, project page]

 


Optimal integration of photometric and geometric surface measurements using inaccurate reflectance/illumination knowledge
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Okatani, T., & Deguchi, K.
[link

Application of the mean field methods to MRF optimization in computer vision
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Saito, M., Okatani, T., & Deguchi, K.
[pdf

Creating multi-viewpoint panoramas of streets with sparsely located buildings
Proceedings of International Conference on Field and Service Robotics (FSR)
Okatani, T., Yanagisawa, J., Tetsuka, D., Sakurada, K., & Deguchi, K.
[link

Recognizing surface qualities from natural images based on learning to rank
Proceedings of International Conference on Pattern Recognition (ICPR)
Abe, T., Okatani, T., & Deguchi, K.
[pdf

 


Optimum method for real-time reconstruction of sensor surface in total-internal-reflection based tactile sensor
World Haptics Conference (WHC)

Taira, R., Saga, S., Okatani, T., & Deguchi, K.
[link

Sensing method of total-internal-reflection-based tactile sensor
World Haptics Conference (WHC)

Koike, M., Saga, S., Okatani, T., & Deguchi, K.
[link

Efficient algorithm for low-rank matrix factorization with missing components and performance comparison of latest algorithms
International Conference on Computer Vision (ICCV)
Okatani, T., Yoshida, T., & Deguchi, K.
[pdf

Accurate and robust planar tracking based on a model of image sampling and reconstruction process
IEEE International Symposium on Mixed and Augmented Reality (ISMAR)
Ito, E., Okatani, T., & Deguchi, K.
[link

 


Flexible online calibration for a mobile projector-camera system
Asian Conference on Computer Vision (ACCV)
Abe, D., Okatani, T., & Deguchi, K.
[link



Recommending Outfits From Personal Closet
International Conference on Computer Vision (ICCV)
Pongsate Tangseng, Kota Yamaguchi, Takayuki Okatani
 

 


Modeling electrocorticography signals on the macaque inferior temporal cortex in space, time and frequency domains using hierarchical visual features of a convolutional neural network
Society for Neuroscience 2016 Annual Meeting (SfN)
San Diego, US, November, 2016
Date, H., Kawasaki, K., Ozay, M., Hongo, T., Hasegawa, I., Okatani, T.
[poster] 

Correspondence between the representations of convolutional neural networks and the activities in inferior temporal cortex measured by electrocorticography
Neuroscience 2016: The 39th Annual Meeting of the Japan Neuroscience Society (JNS)
Yokohama, Japan, July, 2016
Date, H., Kawasaki, K., Ozay, M., Hongo, T., Hasegawa, I., Okatani, T.
[poster] 

Learning Deep Representations of Objects and Materials for Material Recognition
Vision Sciences Society Annual Meeting (VSS)
Florida, US, May, 2016
Liu, X., Ozay, Y., Zhang, Y., Okatani, T.
[link, poster]