Kashu Yamazaki

Kashu Yamazaki
University of Arkansas | U of A · Department of Computer Science and Computer Engineering

Bachelor of Engineering

About

20
Publications
3,004
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
64
Citations
Additional affiliations
June 2021 - June 2021
Google Inc.
Position
  • Research Assistant
August 2017 - December 2018
University of Arkansas
Position
  • Research Assistant
Description
  • Conducting drill component of Statics (MEEG 2003) class. Covered topics including: equilibrium and resultants of force systems in a plane and in space; analysis of structures, friction, centroids, moments of inertia, and virtual work method.
Education
August 2016 - December 2020
University of Arkansas
Field of study
  • Mechanical Engineering

Publications

Publications (20)
Preprint
Full-text available
In recent years, deep neural networks have achieved state-of-the-art performance in a variety of recognition and segmentation tasks in medical imaging including brain tumor segmentation. We investigate that segmenting a brain tumor is facing to the imbalanced data problem where the number of pixels belonging to the background class (non tumor pixel...
Preprint
Full-text available
Medical image segmentation has played an important role in medical analysis and widely developed for many clinical applications. Deep learning-based approaches have achieved high performance in semantic segmentation but they are limited to pixel-wise setting and imbalanced classes data problem. In this paper, we tackle those limitations by developi...
Conference Paper
Full-text available
Deep Convolutional Neural Networks (CNNs) i.e. Residual Networks (ResNets) have been used successfully for many computer vision tasks, but are difficult to scale to 3D volumetric medical data. Memory is increasingly often the bottleneck when training 3D Convolutional Neural Networks (CNNs). Recently, invertible neural networks have been applied to...
Preprint
Full-text available
In this paper, we leverage the human perceiving process, that involves vision and language interaction, to generate a coherent paragraph description of untrimmed videos. We propose vision-language (VL) features consisting of two modalities, i.e., (i) vision modality to capture global visual content of the entire scene and (ii) language modality to...
Article
Full-text available
The past decade has witnessed the great success of deep neural networks in various domains. However, deep neural networks are very resource-intensive in terms of energy consumption, data requirements, and high computational costs. With the recent increasing need for the autonomy of machines in the real world, e.g., self-driving vehicles, drones, an...
Article
Full-text available
Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the remarkable successes of deep reinforcement learning in various domains including finance, medicine, healthcare, video games, robotics, and computer vision. In this work, we pr...
Preprint
Full-text available
Deep learning methods have been successful in solving tasks in machine learning and have made breakthroughs in many sectors owing to their ability to automatically extract features from unstructured data. However, their performance relies on manual trial-and-error processes for selecting an appropriate network architecture, hyperparameters for trai...
Preprint
Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important role in many tasks of video analysis and understanding. Despite the great achievement in TAPG, most existing works ignore the human perception of interaction between agents and the surrounding...
Preprint
Humans typically perceive the establishment of an action in a video through the interaction between an actor and the surrounding environment. An action only starts when the main actor in the video begins to interact with the environment, while it ends when the main actor stops the interaction. Despite the great progress in temporal action proposal...
Article
Full-text available
Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important role in many tasks of video analysis and understanding. Despite the great achievement in TAPG, most existing works ignore the human perception of interaction between agents and the surrounding...
Preprint
Full-text available
Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the remarkable successes of deep reinforcement learning in various domains including finance, medicine, healthcare, video games, robotics, and computer vision. In this work, we pr...
Article
Full-text available
Medical image segmentation is one of the most challenging tasks in medical image analysis and widely developed for many clinical applications. While deep learning-based approaches have achieved impressive performance in semantic segmentation, they are limited to pixel-wise settings with imbalanced-class data problems and weak boundary object segmen...
Preprint
Full-text available
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of existing approaches are unable to follow the human cognitive process of understanding the video context due to lack of attention mechanism to express the concept of an action or an...
Conference Paper
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of the existing approaches are unable to follow the human cognitive process of understanding the video context due to a lack of attention mechanism to express the concept of an action...
Preprint
Deep Convolutional Neural Networks (CNNs) i.e. Residual Networks (ResNets) have been used successfully for many computer vision tasks, but are difficult to scale to 3D volumetric medical data. Memory is increasingly often the bottleneck when training 3D Convolutional Neural Networks (CNNs). Recently, invertible neural networks have been applied to...
Article
Photodynamic therapy (PDT) has received increased attention over the past decades with the potential to non-invasively treat cancer via light exposure. Due to the limited light penetration depth (typically less than 1 cm), the PDT optical fiber typically needs to be placed close to the cancerous region to ensure the treatment outcome. In this paper...
Article
Full-text available
The article justifies the need to use independent power supply sources in the Arctic regions. It gives arguments in favour of using wind-driven power plants as autonomous power sources. It describes the problems of operating wind energy equipment in the arctic climate. As a solution of the above operational problems, it is proposed to use an emerge...
Conference Paper
Currently, photodynamic therapy (PDT) of primary tumors in peritoneal organs is limited by the lack of specificity of photosensitizers (PSs) and availability of appropriate laparoscopy for accurate and dexterous PDT optical fiber deployment. Invasive procedures are often required in the conventional approach, leads to significant side effects such...

Network

Cited By