Henry Yu

Tsinghua University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Ziwen Wang

Xi'an High Tech University

Hao Sun

Zhejiang University of Science and Technology

Aki Fujimura

Dassault Systèmes (United States)

Mike Meyer

Institute for Learning Innovation

Feng Xue

Beijing University of Posts and Telecommunications

Liu Jiang

Huzhou Central Hospital

Hao Sun

Southern Medical University

Ryan Pearman

Alabama College of Osteopathic Medicine

Haotian Zhang

Hong Kong Polytechnic University

David Olivares

Spectral Labs (United States)

Cooperative Institutions

Dassault Systèmes (United States)

Institute for Learning Innovation

VI Manufacturing (United States)

Spectral Labs (United States)

Stanford University

University of York

Space Micro (United States)

Northwestern Polytechnical University

Universidad de Zaragoza

Carnegie Mellon University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

An Invocation

Henry Yu

Abstract Let us start with a map. Unfold like a painted fan a mercator projection, a view from high above the earth encompassing the Pacific Ocean, with Asia on the left and the Americas on the right. The arc of the Pacific Rim sweeps from the blotch of Australia to Indonesia and Southeast Asia, up the coast of China past the Korean peninsula and Japan, around Alaska and down the West Coast of Canada and the United States, tailing off to the tip of South America. Imagine the map as a parchment through which to relive the past, a chart to trace the stories of people as they move about, leaving a trail of dotted lines that follow them from place to place. The story of these people is one of movement, and like a travel-worn atlas that shows the scrawled markings of roads taken and places seen, this map will show journeys and tell stories of how people came to see things previously unseen, how they tried to understand what they saw, and how they often kept going somewhere farther in order to understand what they had just seen. Place-names coalesce on this imaginary map, given meaning within and connected to the lives of our travelers. Guangdong Province in southern China, Japan, Hawaii, Seattle, San Francisco, Stockton, Los Angeles, Butte, Tule Lake, Iowa City, Nashville, and, on the extreme edge of our map, Chicago.

Peninsula

Centennial

10.1093/oso/9780195116601.003.0001

Cite

Citations (0)

MixModule: Mixed CNN Kernel Module for Medical Image Segmentation

arXiv (Cornell University) (2019)

Henry Yu Feng Xue Hao Sun Ziwen Wang

Convolutional neural networks (CNNs) have been successfully applied to medical image classification, segmentation, and related tasks. Among the many CNNs architectures, U-Net and its improved versions based are widely used and achieve state-of-the-art performance these years. These improved architectures focus on structural improvements and the size of the convolution kernel is generally fixed. In this paper, we propose a module that combines the benefits of multiple kernel sizes and we apply the proposed module to U-Net and its variants. We test our module on three segmentation benchmark datasets and experimental results show significant improvement.

Kernel (algebra)

Benchmark (surveying)

Convolution (computer science)

10.48550/arxiv.1910.08728

Cite

Citations (0)

Filtering approaches for real-time anti-aliasing

Jorge Jiménez Diego Gutiérrez Jason Yang Alexander Reshetov Pete Demoreuille

For more than a decade, supersample anti-aliasing (SSAA) and multisample anti-aliasing (MSAA) have been the gold-standard anti-aliasing solutions in games. However, these techniques are not well suited for deferred shading or fixed environments like the current generation of consoles. In recent years, industry and academia have been exploring alternative approaches, where anti-aliasing is performed as a post-processing step. The original, CPU-based morphological anti-aliasing (MLAA) method gave birth to an explosion of real-time anti-aliasing techniques that rival MSAA.

Aliasing

Anti-aliasing

Anti-aliasing filter

10.1145/2037636.2037642

Cite

Citations (45)

MixModule: Mixed CNN Kernel Module for Medical Image Segmentation

2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI) (2020)

Henry Yu Feng Xue Ziwen Wang Hao Sun

Kernel (algebra)

Benchmark (surveying)

Convolution (computer science)

10.1109/isbi45749.2020.9098498

Cite

Citations (9)

GetNet: Get Target Area for Image Pairing

Henry Yu Liu Jiang Hao Sun Ziwen Wang Haotian Zhang

Image pairing is an important research task in the field of computer vision. And finding image pairs containing objects of the same category is the basis of many tasks such as tracking and person re-identification, etc., and it is also the focus of our research. Existing traditional methods and deep learning-based methods have some degree of defects in speed or accuracy. In this paper, we made improvements on the Siamese network [1] and proposed GetNet. The proposed method GetNet combines STN [2] and Siamese network to get the target area first and then perform subsequent processing. Experiments show that our method achieves competitive results in speed and accuracy.

Identification

Tracking (education)

Basis (linear algebra)

10.1109/ivcnz48456.2019.8960995

Cite

Citations (2)

Integrating radiation transport models in a 3D Video Game to train nuclear detection techniques

James Winso John Rolando David Olivares Henry Yu Ronen Shaham

A novel technique has been developed under a Department of Homeland Security Small Business Innovative Research (SBIR) Program to exploit Video Games to dramatically improve the quality and availability of law enforcement and first responder training to locate and adjudicate nuclear sources. This training method is implemented in a software system which allows trainees to practice finding, identifying, and determining the threat level of radioactive sources in a 3D video game environment and returns results to a learning management system to enable tracking progress.

Video game

Adjudication

10.1109/igic.2011.6115136

Cite

Citations (0)

Making digital twins using the Deep Learning Kit (DLK)

Linyong Pang Suhas Pillai Thang Nguyen Mike Meyer Ajay Kumar Baranwal

Deep learning (DL) is one of the fastest-growing fields in artificial intelligence (AI). While still in its early stages of adoption, DL has already shown it has the potential to make significant changes to the lithography and photomask industries through the automation or optimization of equipment and processes. The key element required for application of DL techniques to any process is a large volume of data to adequately train the DL neural networks. The accuracy of the classification or prediction of any DL system is dependent on the depth and breadth of the training data to which it is exposed. For semiconductor manufacturing, finding adequate data – especially for corner cases – can be difficult and/or expensive. In this paper, we will present two digital twins that are themselves built from DL as a part of a DL Starter Kit. We will demonstrate the creation of DL-based digital twins for a mask scanning electron microscope (SEM) and for curvilinear inverse lithography technology (ILT).

Photomask

Optical proximity correction

10.1117/12.2538508

Cite

Citations (2)

Fast all-angle Mask 3D for ILT patterning

Ryan Pearman Mike Meyer J. Ungar Henry Yu Leo Pang

Typical ILT goes through a continuous tone mask to define a greyscale mask for the best process window, followed by a conversion into actual mask geometries, which are typically Manahttanized to be compatible with printing on existing mask writers. On mask, however, the features to be printed are not Manhattan, and we demonstrate that, by not taking into account the actual mask shapes, current Manhattan mask 3D (M3D) approximations using width, shape, and corner libraries, give rise to poor predictions for the final aerial image. Now that curvilinear ILT is possible to manufacture, we introduce a fully curvilinear mask 3D approximations, compatible with ILT masks, that predict the aerial image significantly better than before.

Aerial image

10.1117/12.2554856

Cite

Citations (6)

China’s policies on Chinese overseas: past and present

Routledge eBooks (2013)

Henry Yu

Until the late Qing period (1840s to 1911), the Chinese governments’ policies toward Chinese overseas were basically an aspect of their policies toward overseas trade. From the Qin to the Yuan dynasties (221 BC to 1368 AD), the Chinese governments had normally not interfered with private overseas trade. Some Chinese maritime merchants and sailors even settled down abroad. Because the number was very limited, they had been largely neglected by the Chinese governments. Based on China’s advanced handicraft industry and shipbuilding, higher navigation technology and abundant commodities for export, the Chinese merchants who replaced the Muslim merchants that were active between East Asia and the Indian Ocean, played a leading role in the East Asia maritime trade from the thirteenth century onwards. When the Chinese merchants spread all over the trading ports in East Asia, they established their trade bases, resulting in the emergence of permanent Chinese settlements. Toward the end of the fourteenth century, several large Chinese communities were formed in Java, Sumatra and other ports in Southeast Asia, each of which had several thousands of Chinese people (Zhuang 2001: 53-5).

10.4324/9780203100387-11

Cite

Citations (6)

Language of Discontent: Using the Stranger’s Perspective

Henry Yu

Abstract Sociology provided a language for Asian American scholars to examine and understand their experiences in the United States. More important, it supplied a seemingly neutral perspective from which they could analyze extremely disturbing events. The ability to acquire analytical distance from the social world allowed many of the Oriental intellectuals the freedom to remove themselves to a place where the concerns of their personal existence took on more abstract meanings. The detached outsider’s perspective of sociology, embodied in the outlook of the stranger, provided a means for intellectuals to extricate themselves from the entanglements of daily life. As it might be for a person who feels trapped in a small town, becoming an outsider could represent escape from the claustrophobic confinements of a life too well known.

10.1093/oso/9780195116601.003.0010

Cite

Citations (0)