Filters








165,622 Hits in 5.1 sec

Predicting Visual Importance Across Graphic Design Types [article]

Camilo Fosco, Vincent Casser, Amish Kumar Bedi, Peter O'Donovan, Aaron Hertzmann, Zoya Bylinskii
2020 arXiv   pre-print
This paper introduces a Unified Model of Saliency and Importance (UMSI), which learns to predict visual importance in input graphic designs, and saliency in natural images, along with a new dataset and  ...  We demonstrate two new design interfaces that use importance prediction, including a tool for adjusting the relative importance of design elements, and a tool for reflowing designs to new aspect ratios  ...  , and importance prediction on visualizations [6] and posters [6, 28] .  ... 
arXiv:2008.02912v1 fatcat:q3nvjo673fhuhhjzmnfd56goka

Learning Visual Importance for Graphic Designs and Data Visualizations

Zoya Bylinskii, Nam Wook Kim, Peter O'Donovan, Sami Alsheikh, Spandan Madan, Hanspeter Pfister, Fredo Durand, Bryan Russell, Aaron Hertzmann
2017 Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology - UIST '17  
We present automated models that predict the relative importance of different elements in data visualizations and graphic designs.  ...  Knowing where people look and click on visual designs can provide clues about how the designs are perceived, and where the most important or relevant content lies.  ...  This paper presents a new importance prediction method for graphic designs and data visualizations.  ... 
doi:10.1145/3126594.3126653 dblp:conf/uist/BylinskiiKOAMPD17 fatcat:zxxaqb23njfnlfmr2v2naoixgi

Understanding Mobile GUI: from Pixel-Words to Screen-Sentences [article]

Jingwen Fu, Xiaoyi Zhang, Yuwang Wang, Wenjun Zeng, Sam Yang, Grayson Hilliard
2022 arXiv   pre-print
In analogy to the individual Words, we define the Pixel-Words as atomic visual components (text and graphic components), which are visually consistent and semantically clear across screenshots of a large  ...  The effectiveness of PW2SS is further verified in the GUI understanding tasks including relation prediction, clickability prediction, screen retrieval, and app type classification.  ...  In analogy to NLP, the "word" of a screen should be: 1) atomic visual components carrying clear semantic meaning. 2) visually consistent across different UIs.  ... 
arXiv:2105.11941v2 fatcat:4bzzlwihtvetlduooutje54fim

BubbleView

Nam Wook Kim, Zoya Bylinskii, Michelle A. Borkin, Krzysztof Z. Gajos, Aude Oliva, Fredo Durand, Hanspeter Pfister
2017 ACM Transactions on Computer-Human Interaction  
Across 10 experiments with 28 different parameter combinations, we evaluated BubbleView on a variety of image types: information visualizations, natural images, static webpages, and graphic designs, and  ...  BubbleView is designed to collect clicks on static images, and works best for defined tasks such as describing the content of an information visualization or measuring image importance.  ...  important in graphic designs.  ... 
doi:10.1145/3131275 fatcat:pcmdv6oourbf7ipjiimp6tdkiq

Visualizing Rule Sets: Exploration and Validation of a Design Space [article]

Jun Yuan, Oded Nov, Enrico Bertini
2021 arXiv   pre-print
The paper presents an initial design space for visualizing rule sets and a user study exploring their impact.  ...  In this paper, we explore the idea of designing alternative representations of rules, focusing on a number of visual factors we believe have a positive impact on rule readability and understanding.  ...  Task 1: Prediction Estimation. We provide the performance of Task 1 across visual conditions in Figure 6 .  ... 
arXiv:2103.01022v2 fatcat:cqjroqxucvamxltalfggh2hcve

Visual Model Validation via Inline Replication [article]

David Gotz, Brandon A. Price, Annie T. Chen
2016 arXiv   pre-print
In this way, visualizations often serve as visual predictive models despite the fact that they are typically designed to present historical views of the data.  ...  This "visual predictive model" approach, however, can lead to invalid inferences.  ...  By graphically depicting the repeatability of a particular measure across multiple folds, IR provides users with important and easy-to-interpret cues as to the variability of a given measure.  ... 
arXiv:1605.08749v1 fatcat:rz4tvv2du5hd3fazii5r2ujije

VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository [article]

Kevin Hu and Neil Gaikwad and Michiel Bakker and Madelon Hulsebos and Emanuel Zgraggen and César Hidalgo and Tim Kraska and Guoliang Li and Arvind Satyanarayan and Çağatay Demiralp
2019 arXiv   pre-print
Researchers currently rely on ad hoc datasets to train automated visualization tools and evaluate the effectiveness of visualization designs.  ...  To contend with running such studies at scale, we demonstrate how a metric of perceptual effectiveness can be learned from experimental results, and show its predictive power across test datasets.  ...  performance (i.e. error rate and response time) across data distributions (D), visualization designs (V), and task types (T).  ... 
arXiv:1905.04616v1 fatcat:d46eqdu55fbv7ely5u7h3jhmnu

Graphs as aids to knowledge construction: Signaling techniques for guiding the process of graph comprehension

Priti Shah, Mary Hegarty, Richard E. Mayer
1999 Journal of Educational Psychology  
In Experiments 2 and 3, the researchers isolated one important factor that affects viewers' interpretation (i.e., the perceptual organization of the information in graphs).  ...  If relevant quantitative information is perceptually grouped to form visual chunks (because relevant data points are either connected in line graphs or close together in bar graphs), then viewers describe  ...  & Kirsch, 1991 ,1992 , which typically predict an interaction of type of task and type of document.  ... 
doi:10.1037//0022-0663.91.4.690 fatcat:ugysj723zbdhdiwxbbtllfthl4

Graphs as aids to knowledge construction: Signaling techniques for guiding the process of graph comprehension

Priti Shah, Richard E. Mayer, Mary Hegarty
1999 Journal of Educational Psychology  
In Experiments 2 and 3, the researchers isolated one important factor that affects viewers' interpretation (i.e., the perceptual organization of the information in graphs).  ...  If relevant quantitative information is perceptually grouped to form visual chunks (because relevant data points are either connected in line graphs or close together in bar graphs), then viewers describe  ...  & Kirsch, 1991 ,1992 , which typically predict an interaction of type of task and type of document.  ... 
doi:10.1037/0022-0663.91.4.690 fatcat:5bkirp2cizgpfnagmnox5o5xyi

A two visual systems approach to understanding voice and gestural interaction

Barry A. Po, Brian D. Fisher, Kellogg S. Booth
2005 Virtual Reality  
It is important to consider the physiological and behavioral mechanisms that allow users to physically interact with virtual environments.  ...  interaction: (1) voice-based input, (2) pointing with a visual cursor, (3) pointing without a visual cursor, and (4) pointing with a timelagged visual cursor.  ...  We can use the two visual systems model to predict how target selection through voice or gestural pointing can be influenced by the presence or absence of two types of graphical elements: visible cursors  ... 
doi:10.1007/s10055-005-0156-2 fatcat:ngjp2jl3qre4tc7xjpthmtc6ra

What characterizes personalities of graphic designs?

Nanxuan Zhao, Ying Cao, Rynson W. H. Lau
2018 ACM Transactions on Graphics  
Our personality scoring network automatically learns a visual representation that captures the semantics necessary to predict graphic design personality.  ...  With our personality scoring network, we systematically and quantitatively investigate how various design factors (e.g., color, font, and layout) affect design personality across different scales (from  ...  Bylinskii et al. [2017] developed fully convolutional networks to predict the importance maps of both graphic designs and data visualizations.  ... 
doi:10.1145/3197517.3201355 fatcat:c47loa6wfjbz3dx47ez5uxnqqm

An Exploration And Validation of Visual Factors in Understanding Classification Rule Sets [article]

Jun Yuan, Oded Nov, Enrico Bertini
2021 arXiv   pre-print
In this paper, we explore the idea of designing alternative representations of rules, focusing on a number of visual factors we believe have a positive impact on rule readability and understanding.  ...  Surprisingly, to date there has been limited work on exploring visual alternatives for presenting rules.  ...  Task 1: Prediction Estimation We provide the performance of Task 1 across visual conditions in Figure 3 . Accuracy across all conditions is very similar and very close to 100%.  ... 
arXiv:2109.09160v1 fatcat:x2ekoxcjdvarhivcnaycalq4cy

User-centered virtual environment design for virtual rehabilitation

Cali M Fidopiastis, Albert A Rizzo, Jannick P Rolland
2010 Journal of NeuroEngineering and Rehabilitation  
Benchmarks were obtained using a novel vision test capable of measuring a user's stereoacuity while wearing different types of head-worn displays.  ...  Current human-computer interaction designs focus on usability without benchmarking technology within a user-inthe-loop design cycle.  ...  Information such as display type, field-of-view (FOV), interpupillary eye distance (IPD) range, and resolution are important parameters of the HWD that determine the users' visual performance.  ... 
doi:10.1186/1743-0003-7-11 pmid:20170519 pmcid:PMC2837672 fatcat:lk52wclxhbgkldw7ez24gnt7iy

Sockeye: A 3D Environment for Comparative Genomics

S. B. Montgomery
2004 Genome Research  
We have developed a Java-based application called Sockeye that uses three-dimensional (3D) graphics technology to facilitate the visualization of annotation and conservation across multiple sequences.  ...  Ensembl-derived and imported sequences can be analyzed by using a suite of multiple and pair-wise alignment algorithms.  ...  The use of 3D in any type of data visualization and analysis application has advantages and disadvantages. 3D data visualization has been successfully used for engineering design and for geological and  ... 
doi:10.1101/gr.1890304 pmid:15123592 pmcid:PMC479126 fatcat:r4jnd5w7fveoxe55hwa5g42bz4

WholeCellViz: data visualization for whole-cell models

Ruby Lee, Jonathan R Karr, Markus W Covert
2013 BMC Bioinformatics  
Furthermore, WholeCellViz enables researchers to compare predictions within and across simulations by allowing users to simultaneously display multiple visualizations.  ...  These visualizations help researchers analyze model predictions by displaying predictions in their biological context.  ...  Acknowledgements We thank Elsa Birch, Derek Macklin, Jane Maynard, Nick Ruggero, and Jayodita Sanghvi for helpful discussions on data analysis and visualization.  ... 
doi:10.1186/1471-2105-14-253 pmid:23964998 pmcid:PMC3765349 fatcat:ms2ldguy5vd6vfylu6y5ixy4gm
« Previous Showing results 1 — 15 out of 165,622 results