English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Isolating different types of motion in video data is a highly relevantproblem in video analysis. Applications can be found, for example, in dynamicmedical or biological imaging, where the analysis and further processing of thedynamics of interest is often complicated by additional, unwanted dynamics,such as motion of the measurement subject. In this work, it is empiricallyshown that a representation of video data via untrained generator networks,together with a specific technique for latent space disentanglement that usesminimal, one-dimensional information on some of the underlying dynamics, allowsto efficiently isolate different, highly non-linear motion types. Inparticular, such a representation allows to freeze any selection of motiontypes, and to obtain accurate independent representations of other dynamics ofinterest. Obtaining such a representation does not require any pre-training ona training data set, i.e., all parameters of the generator network are learneddirectly from a single video.

Latent-space disentanglement with untrained generator networks for the isolation of different motion types in video data