2,503 Hits in 2.1 sec

追悼 田中正俊先生
The late Dr. TANAKA Masatoshi

2003 Shigaku zasshi  
doi:10.24471/shigaku.112.1_112 fatcat:qjsa24gqh5dr5olnavr45qxv7q

Nonperturbative Aspects in N-fold Supersymmetry [article]

Toshiaki Tanaka, Masatoshi Sato
2002 arXiv   pre-print
Through a nonperturbative analysis on a sextic triple-well potential, we reveal novel aspects of the dynamical property of the system in connection with N-fold supersymmetry and quasi-solvability.
arXiv:hep-th/0211064v1 fatcat:ijr6io7hqvg6xctzlzxs3ntm4a

Gradient-Based Low-Light Image Enhancement [article]

Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi
2018 arXiv   pre-print
A low-light image enhancement is a highly demanded image processing technique, especially for consumer digital cameras and cameras on mobile phones. In this paper, a gradient-based low-light image enhancement algorithm is proposed. The key is to enhance the gradients of dark region, because the gradients are more sensitive for human visual system than absolute values. In addition, we involve the intensity-range constraints for the image integration. By using the intensity-range constraints, we
more » ... an integrate the output image with enhanced gradients preserving the given gradient information while enforcing the intensity range of the output image within a certain intensity range. Experiments demonstrate that the proposed gradient-based low-light image enhancement can effectively enhance the low-light images.
arXiv:1809.09297v1 fatcat:q6i52dhiabbxzdcbzo2xl5t3bm

Human Segmentation with Dynamic LiDAR Data [article]

Tao Zhong, Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi
2020 arXiv   pre-print
Consecutive LiDAR scans compose dynamic 3D sequences, which contain more abundant information than a single frame. Similar to the development history of image and video perception, dynamic 3D sequence perception starts to come into sight after inspiring research on static 3D data perception. This work proposes a spatio-temporal neural network for human segmentation with the dynamic LiDAR point clouds. It takes a sequence of depth images as input. It has a two-branch structure, i.e., the spatial
more » ... segmentation branch and the temporal velocity estimation branch. The velocity estimation branch is designed to capture motion cues from the input sequence and then propagates them to the other branch. So that the segmentation branch segments humans according to both spatial and temporal features. These two branches are jointly learned on a generated dynamic point cloud dataset for human recognition. Our works fill in the blank of dynamic point cloud perception with the spherical representation of point cloud and achieves high accuracy. The experiments indicate that the introduction of temporal feature benefits the segmentation of dynamic point cloud.
arXiv:2010.08092v1 fatcat:ujght6tf2fhdfppzh53vbsexwi

Improving Transparency of Deep Neural Inference Process [article]

Hiroshi Kuwajima, Masayuki Tanaka, Masatoshi Okutomi
2019 arXiv   pre-print
Deep learning techniques are rapidly advanced recently, and becoming a necessity component for widespread systems. However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must exhibit high transparency. In this paper, to address this black-box limitation, we develop a simple analysis method which consists of 1) structural feature analysis: lists of the features contributing to inference process, 2) linguistic feature analysis: lists
more » ... the natural language labels describing the visual attributes for each feature contributing to inference process, and 3) consistency analysis: measuring consistency among input data, inference (label), and the result of our structural and linguistic feature analysis. Our analysis is simplified to reflect the actual inference process for high transparency, whereas it does not include any additional black-box mechanisms such as LSTM for highly human readable results. We conduct experiments and discuss the results of our analysis qualitatively and quantitatively, and come to believe that our work improves the transparency of neural networks. Evaluated through 12,800 human tasks, 75% workers answer that input data and result of our feature analysis are consistent, and 70% workers answer that inference (label) and result of our feature analysis are consistent. In addition to the evaluation of the proposed analysis, we find that our analysis also provide suggestions, or possible next actions such as expanding neural network complexity or collecting training data to improve a neural network.
arXiv:1903.05501v1 fatcat:lwenegrjnnghtjpdymtii2gx6i

Majorana multipole response of topological superconductors [article]

Shingo Kobayashi, Ai Yamakage, Yukio Tanaka, Masatoshi Sato
2018 arXiv   pre-print
Tanaka, T. Yokoyama, A. V. Balatsky, and N. Nagaosa, Phys. Rev. B 79, 060505 (2009). [79] S. Tamura, S. Kobayashi, L. Bo, and Y. Tanaka, Phys. Rev. B 95, 104511 (2017). S1.  ...  Tanaka, Y. Mizuno, T. Yokoyama, K. Yada, and M. Sato, Phys. Rev. Lett. 105, 097002 (2010). [67] K. Yada, M. Sato, Y. Tanaka, and T. Yokoyama, Phys. Rev. B 83, 064505 (2011). [68] P. M. R. Brydon, A.  ... 
arXiv:1812.01857v1 fatcat:pupewbo6zfgevbocqp72mqcnui

Photonic Crystal Fibers

Masatoshi TANAKA
2012 The Review of Laser Engineering  
doi:10.2184/lsj.40.6_428 fatcat:mygegsh2xbc5ndmghr2jsbmpee

Classifying degraded images over various levels of degradation [article]

Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi
2020 arXiv   pre-print
Classification for degraded images having various levels of degradation is very important in practical applications. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The results demonstrate that the proposed network can classify degraded images over various levels of degradation well. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images.
arXiv:2006.08145v1 fatcat:ov2hzjv7rfgn3czxdckaoodiqm

Geometric Data Augmentation Based on Feature Map Ensemble [article]

Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi
2021 arXiv   pre-print
Deep convolutional networks have become the mainstream in computer vision applications. Although CNNs have been successful in many computer vision tasks, it is not free from drawbacks. The performance of CNN is dramatically degraded by geometric transformation, such as large rotations. In this paper, we propose a novel CNN architecture that can improve the robustness against geometric transformations without modifying the existing backbones of their CNNs. The key is to enclose the existing
more » ... one with a geometric transformation (and the corresponding reverse transformation) and a feature map ensemble. The proposed method can inherit the strengths of existing CNNs that have been presented so far. Furthermore, the proposed method can be employed in combination with state-of-the-art data augmentation algorithms to improve their performance. We demonstrate the effectiveness of the proposed method using standard datasets such as CIFAR, CUB-200, and Mnist-rot-12k.
arXiv:2107.10524v1 fatcat:hpwmbb33bbbh5lmwdiviycpa5q

Influence of Local Vibration on Finger Functions of Forest Workers

Masatoshi TANAKA, Kazutoshi NAKAMURA, Kisaburo SATO, Kazuko TANAKA
1997 Industrial Health  
M TANAKA et al.  ... 
doi:10.2486/indhealth.35.337 pmid:9248216 fatcat:vckhcctmszgczisvig7zmgynqy

麻痺肢の機能的電気刺激 : 表面電極法について

Keiji KOMAI, Akihiro TOMINAGA, Jiro KAWAMURA, Masatoshi MATSUYA, Nobuyoshi FUKUI, Masatoshi TANAKA, Kazuyoshi NISHIHARA
1986 Biomechanisms  
:ltf";f'/.ttsoueftUtftli・ FUNCTIONAL NEUROMUSCULAR STIMULATION THROUGH SURFACE ELECTRODES Keiji KOMAI', Akihiro TOMINAGA', Jiro KAWAMURA'*, Masatoshi MATSUYA"", Nobuyoshi FUKUI'", Masatoshi TANAKA"' and  ... 
doi:10.3951/biomechanisms.8.155 fatcat:23kif7mmdbejbkmb5loog42crq

Non-blind Image Restoration Based on Convolutional Neural Network [article]

Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi
2018 arXiv   pre-print
Blind image restoration processors based on convolutional neural network (CNN) are intensively researched because of their high performance. However, they are too sensitive to the perturbation of the degradation model. They easily fail to restore the image whose degradation model is slightly different from the trained degradation model. In this paper, we propose a non-blind CNN-based image restoration processor, aiming to be robust against a perturbation of the degradation model compared to the
more » ... blind restoration processor. Experimental comparisons demonstrate that the proposed non-blind CNN-based image restoration processor can robustly restore images compared to existing blind CNN-based image restoration processors.
arXiv:1809.03757v1 fatcat:zr4phlfkrnefvmj75iwakwdgc4

Stability Integrals for Linear Multipole Configurations

Masatoshi TANAKA, Sanae TAMURA
1968 Kakuyūgō kenkyū  
doi:10.1585/jspf1958.21.202 fatcat:o5q2alvppncyjisr42ghbffy5a

Expansion of Gas from Fast Acting Valve

Masatoshi Tanaka
1963 Kakuyūgō kenkyū  
doi:10.1585/jspf1958.10.158 fatcat:crtitibqv5dg7hmoopkck2h7nu

Local skin thermal responses to heat radiation

Masatoshi TANAKA
1985 Sangyo Igaku  
doi:10.1539/joh1959.27.90 fatcat:j4j7iudaqfhx7hhf3cpaxqgwy4
« Previous Showing results 1 — 15 out of 2,503 results