T
Teng-Yok Lee
Researcher at Mitsubishi Electric Research Laboratories
Publications - 57
Citations - 1627
Teng-Yok Lee is an academic researcher from Mitsubishi Electric Research Laboratories. The author has contributed to research in topics: Visualization & Data visualization. The author has an hindex of 18, co-authored 55 publications receiving 1318 citations. Previous affiliations of Teng-Yok Lee include Ohio State University & Mitsubishi Electric.
Papers
More filters
Proceedings ArticleDOI
Attention-Based Multimodal Fusion for Video Description
Chiori Hori,Takaaki Hori,Teng-Yok Lee,Ziming Zhang,Bret Harsham,John R. Hershey,Tim K. Marks,Kazuhiko Sumi +7 more
TL;DR: In this article, a multimodal attention model was proposed to fuse audio features in addition to the image and motion features for each word in the output description, which achieved state-of-the-art performance on YouTube2Text and MSR-VTT.
Journal ArticleDOI
An Information-Theoretic Framework for Flow Visualization
TL;DR: An information-theoretic framework for flow visualization with a special focus on streamline generation is presented, and it is shown that the framework can effectively visualize 2D and 3D flow data.
Proceedings ArticleDOI
Deep Active Learning for Civil Infrastructure Defect Detection and Classification
TL;DR: Deep Active Learning for Civil Infrastructure Defect Detection and Classification Chen Feng, Ming-Yu Liu, Chieh-Chi Kao, and Teng-Yok Lee1, 201 Broadway, Cambridge, Massachusetts 02139, and ABSTRACT Automatic detection and classification of defects in infrastructure surface images can largely boost its maintenance efficiency.
Proceedings ArticleDOI
A Study of Parallel Particle Tracing for Steady-State and Time-Varying Flow Fields
Tom Peterka,Robert Ross,Boonthanome Nouanesengsy,Teng-Yok Lee,Han-Wei Shen,Wesley Kendall,Jian Huang +6 more
TL;DR: This paper scales parallel particle tracing for visualizing steady and unsteady flow fields well beyond previously published results, and configures the 4D domain decomposition into spatial and temporal blocks that combine in-core and out-of-core execution in a flexible way that favors faster run time or smaller memory.
Journal ArticleDOI
Visualization and Exploration of Temporal Trend Relationships in Multivariate Time-Varying Data
Teng-Yok Lee,Han-Wei Shen +1 more
TL;DR: A new algorithm to explore and visualize multivariate time-varying data sets and design novel user interfaces to explore the trend relationships, to visualize their temporal characteristics, and to display their spatial distributions is presented.