Zobrazeno 1 - 10
of 288
pro vyhledávání: '"Han-Wei Shen"'
Publikováno v:
Visual Informatics, Vol 5, Iss 2, Pp 1-12 (2021)
Neural attention-based encoders, which effectively attend sentence tokens to their associated context without being restricted by long-term distance or dependency, have demonstrated outstanding performance in embedding sentences into meaningful repre
Externí odkaz:
https://doaj.org/article/ef06bf5e058843979f6d434803acb2f7
Publikováno v:
Visual Informatics, Vol 4, Iss 2, Pp 99-108 (2020)
Generating compact and effective numerical representations of data is a fundamental step for many machine learning tasks. Traditionally, handcrafted features are used but as deep learning starts to show its potential, using deep learning models to ex
Externí odkaz:
https://doaj.org/article/fa7be2edd69f403ca408199c410ba92e
Publikováno v:
Visual Informatics, Vol 4, Iss 2, Pp 132-141 (2020)
Convolutional neural networks are one of the most important and widely used constructs in natural language processing and AI in general. In many applications, they have achieved state-of-the-art performance, with training time faster than the other a
Externí odkaz:
https://doaj.org/article/48e4657a0a674d9880dcfa16fe8b5e89
Publikováno v:
Visual Informatics, Vol 4, Iss 2, Pp 109-121 (2020)
We propose a deep learning approach to collectively compare two or multiple ensembles, each of which is a collection of simulation outputs. The purpose of collective comparison is to help scientists understand differences between simulation models by
Externí odkaz:
https://doaj.org/article/ec8458a6f71d4f18a6a55aa11ec3d530
Autor:
Kwan-Liu Ma, Han-Wei Shen
Publikováno v:
Visual Informatics, Vol 4, Iss 2, Pp 71- (2020)
Externí odkaz:
https://doaj.org/article/b55499bd9dcf44b1a3b475f4730182bd
Autor:
Chaoli Wang, Han-Wei Shen
Publikováno v:
Entropy, Vol 13, Iss 1, Pp 254-273 (2011)
In recent years, there is an emerging direction that leverages information theory to solve many challenging problems in scientific data analysis and visualization. In this article, we review the key concepts in information theory, discuss how the pri
Externí odkaz:
https://doaj.org/article/7943f5d03c394dd8ad14332d42cf4784
Publikováno v:
Entropy, Vol 20, Iss 7, p 540 (2018)
Uncertainty of scalar values in an ensemble dataset is often represented by the collection of their corresponding isocontours. Various techniques such as contour-boxplot, contour variability plot, glyphs and probabilistic marching-cubes have been pro
Externí odkaz:
https://doaj.org/article/4febeb8439644c63aad41b297fd61c64
Publikováno v:
Journal of Fluid Science and Technology, Vol 3, Iss 4, Pp 563-575 (2008)
In this paper, we present a volume rendering framework for visualizing 3D flow fields. We introduce the concept of coherence field which evaluates the representativeness of a given streamline set for the underlying 3D vector field. Visualization of t
Externí odkaz:
https://doaj.org/article/d6c0e91278b741468d106e8523affd92
Publikováno v:
Data Science Journal, Vol 3, Pp 153-162 (2006)
Novel visualization methods are presented for spatial probability density function data. These are spatial datasets, where each pixel is a random variable, and has multiple samples which are the results of experiments on that random variable. We use
Externí odkaz:
https://doaj.org/article/04c8b9d2026d4b1184d992f280781e9c
Autor:
Haoyu Li, Han-Wei Shen
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. 29:3354-3367
Feature related particle data analysis plays an important role in many scientific applications such as fluid simulations, cosmology simulations and molecular dynamics. Compared to conventional methods that use hand-crafted feature descriptors, some r