Selection of Optimal Salient Time Steps by Non-negative Tucker Tensor Decomposition

Simple item page
dc.contributor.authorPulido, Jesusen_US
dc.contributor.authorPatchett, Johnen_US
dc.contributor.authorBhattarai, Manishen_US
dc.contributor.authorAlexandrov, Boianen_US
dc.contributor.authorAhrens, Jamesen_US
dc.contributor.editorAgus, Marco and Garth, Christoph and Kerren, Andreasen_US
dc.date.accessioned2021-06-12T11:03:25Z
dc.date.available2021-06-12T11:03:25Z
dc.date.issued2021
dc.description.abstractChoosing salient time steps from spatio-temporal data is useful for summarizing the sequence and developing visualizations for animations prior to committing time and resources to their production on an entire time series. Animations can be developed more quickly with visualization choices that work best for a small set of the important salient timesteps. Here we introduce a new unsupervised learning method for finding such salient timesteps. The volumetric data is represented by a 4-dimensional non-negative tensor, X(t; x; y; z).The presence of latent (not directly observable) structure in this tensor allows a unique representation and compression of the data. To extract the latent time-features we utilize non-negative Tucker tensor decomposition. We then map these time-features to their maximal values to identify the salient time steps. We demonstrate that this choice of time steps allows a good representation of the time series as a whole.en_US
dc.description.sectionheadersScientific Visualization
dc.description.seriesinformationEuroVis 2021 - Short Papers
dc.identifier.doi10.2312/evs.20211055
dc.identifier.isbn978-3-03868-143-4
dc.identifier.pages55-59
dc.identifier.urihttps://doi.org/10.2312/evs.20211055
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/evs20211055
dc.publisherThe Eurographics Associationen_US
dc.subjectHuman
dc.subjectcentered computing
dc.subjectVisualization design and evaluation methods
dc.titleSelection of Optimal Salient Time Steps by Non-negative Tucker Tensor Decompositionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
055-059.pdf
Size:
2.2 MB
Format:
Adobe Portable Document Format
Download
Collections
EuroVisShort2021