Takio Kurita

Professor

Hiroshima University

Japan

Research Interests

Explore related searches

Professors in Japan Professors in Artificial Intelligence Artificial Intelligence professors in Japan

Contact this professor

ORCID

Google Scholar

About

Takio Kurita is a Professor at Hiroshima University in Japan. His research focuses on areas such as machine learning applications, anomaly detection, and object detection methodologies, as evidenced by his recent publications. Notable works include advancements in convolutional autoencoders and techniques for handling noisy labels in data sets. He contributes significantly to the field of machine learning with practical applications in material development and biomedical image analysis.

Takio Kurita

Research Interests

Explore related searches

Contact this professor

About

Articles (19)

A Practical Application of Machine Learning for the Development of Metallole-Based Fluorescent Materials

Direction-aware convolutional autoencoder based on positional encoding for one-dimensional anomaly detection

Improved Head and Data Augmentation to Reduce Artifacts at Grid Boundaries in Object Detection

Nonlinear dimensionality reduction with q-Gaussian distribution

Attention-effective multiple instance learning on weakly stem cell colony segmentation

An Object Detection Method Using Probability Maps for Instance Segmentation to Mask Background

Convolutional autoencoder based on latent subspace projection for anomaly detection

Data Expansion Approach with Attention Mechanism for Learning with Noisy Labels

Deep Neural Network Models for Colon Cancer Screening

Correction to: Extensive framework based on novel convolutional and variational autoencoder based on maximization of mutual information for anomaly detection

Consistency Regularization on Clean Samples for Learning with Noisy Labels

Regularizer based on Euler characteristic for retinal blood vessel segmentation

Autoencoder framework based on orthogonal projection constraints improves anomalies detection

Extensive framework based on novel convolutional and variational autoencoder based on maximization of mutual information for anomaly detection

Mixture of experts with convolutional and variational autoencoders for anomaly detection

Author Correction: Deep learning enables automated localization of the metastatic lymph node for thyroid cancer on 131I post-ablation whole-body planar scans

Completion of missing labels for multi-label annotation by a unified graph laplacian regularization

Correlation Net: Spatiotemporal multimodal deep learning for action recognition

Deep learning enables automated localization of the metastatic lymph node for thyroid cancer on <sup>131</sup>I post-ablation whole-body planar scans

Collaborators (6)

Joji Ohshita

Balu Alagar Venmathi Maran

Yohei Adachi

Ran Dong

Yusuke Kanematsu

Muthu Subash Kavitha

How do I reach out?

Meet Kite AI