7 citations · 28 across the 12 of their papers we have counts for
12 papers
Exploiting Frequency Spectrum of Adversarial Images for General Robustness
Chun Yang Tan, Kazuhiko Kawamoto, Hiroshi Kera
In recent years, there has been growing concern over the vulnerability of convolutional neural networks (CNNs) to image perturbations. However, achieving general robustness against…
Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition
Nariki Tanaka, Hiroshi Kera, Kazuhiko Kawamoto
Using Fourier analysis, we explore the robustness and vulnerability of graph convolutional neural networks (GCNs) for skeleton-based action recognition. We adopt a joint Fourier tr…
Improving Zero-Shot Action Recognition using Human Instruction with Text Description
Nan Wu, Hiroshi Kera, Kazuhiko Kawamoto
Zero-shot action recognition, which recognizes actions in videos without having received any training examples, is gaining wide attention considering it can save labor costs and tr…
Spatiotemporal forecasting of vertical track alignment with exogenous factors
Katsuya Kosukegawa, Yasukuni Mori, Hiroki Suyari +1
To ensure the safety of railroad operations, it is important to monitor and forecast track geometry irregularities. A higher safety requires forecasting with higher spatiotemporal…
Game-Theoretic Understanding of Misclassification
Kosuke Sumiyasu, Kazuhiko Kawamoto, Hiroshi Kera
This paper analyzes various types of image misclassification from a game-theoretic view. Particularly, we consider the misclassification of clean, adversarial, and corrupted images…
Adversarial Body Shape Search for Legged Robots
Takaaki Azakami, Hiroshi Kera, Kazuhiko Kawamoto
We propose an evolutionary computation method for an adversarial attack on the length and thickness of parts of legged robots by deep reinforcement learning. This attack changes th…
Adversarial joint attacks on legged robots
Takuto Otomo, Hiroshi Kera, Kazuhiko Kawamoto
We address adversarial attacks on the actuators at the joints of legged robots trained by deep reinforcement learning. The vulnerability to the joint attacks can significantly impa…
Adversarial amplitude swap towards robust image classifiers
Chun Yang Tan, Kazuhiko Kawamoto, Hiroshi Kera
The vulnerability of convolutional neural networks (CNNs) to image perturbations such as common corruptions and adversarial perturbations has recently been investigated from the pe…
Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control
Wataru Okamoto, Hiroshi Kera, Kazuhiko Kawamoto
This study is aimed at addressing the problem of fault tolerance of quadruped robots to actuator failure, which is critical for robots operating in remote or extreme environments.…
Conditional MoCoGAN for Zero-Shot Video Generation
Shun Kimura, Kazuhiko Kawamoto
We propose a conditional generative adversarial network (GAN) model for zero-shot video generation. In this study, we have explored zero-shot conditional generation setting. In oth…
Adversarial Bone Length Attack on Action Recognition
Nariki Tanaka, Hiroshi Kera, Kazuhiko Kawamoto
Skeleton-based action recognition models have recently been shown to be vulnerable to adversarial attacks. Compared to adversarial attacks on images, perturbations to skeletons are…
Adversarially Trained Object Detector for Unsupervised Domain Adaptation
Kazuma Fujii, Hiroshi Kera, Kazuhiko Kawamoto
Unsupervised domain adaptation, which involves transferring knowledge from a label-rich source domain to an unlabeled target domain, can be used to substantially reduce annotation…