This page introduces current research projects of our lab. The old projects are here.
Adversarial Attack on Action Recognition

Adversarial Attack on Action RecognitionSkeleton-based action recognition models have r...
続きを読むDomain Adaptation by Adversarial Training

Domain Adaptation by Adversarial Training Unsupervised domain adaptation, which involve...
続きを読むAdversarial Attacks on Legged Robots

Adversarial Body Shape Search for Legged Robots We propose an evolutionary computation ...
続きを読むAdversarial Attacks in Frequency domain for robust image classifiler

Adversarial amplitude swap towards robust image classifiers The vulnerability of convol...
続きを読むZero-Shot Action Recognition

Zero-Shot Action Recognition Large datasets are often used to improve the accuracy of a...
続きを読むReinforcement Learning for Damaged Robot Control

Reinforcement Learning for Damaged Robot ControlIn reinforcement learning, for cost and ...
続きを読むDeep Models for Spatiotemporal forecasting

Deep Models for Spatiotemporal forecasting Recent approaches to time series forecasting...
続きを読むFirst-person activity recognition

First-Person Activity RecognitionWe have developed a system for first-person activity rec...
続きを読むGame-Theoretic Understanding of Misclassification in Deep Learning

Game-Theoretic Understanding of Misclassification in Deep Learning This study analyzes ...
続きを読む