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

Human behavior is a continuous stochastic spatio-temporal process which isgoverned by semantic actions and affordances as well as latent factors.Therefore, video-based human activity modeling is concerned with a number oftasks such as inferring current and future semantic labels, predicting futurecontinuous observations as well as imagining possible future label and featuresequences. In this paper we present a semi-supervised probabilistic deep latentvariable model that can represent both discrete labels and continuousobservations as well as latent dynamics over time. This allows the model tosolve several tasks at once without explicit fine-tuning. We focus here on thetasks of action classification, detection, prediction and anticipation as wellas motion prediction and synthesis based on 3D human activity data recordedwith Kinect. We further extend the model to capture hierarchical labelstructure and to model the dependencies between multiple entities, such as ahuman and objects. Our experiments demonstrate that our principled approach tohuman activity modeling can be used to detect current and anticipate futuresemantic labels and to predict and synthesize future label and featuresequences. When comparing our model to state-of-the-art approaches, which arespecifically designed for e.g. action classification, we find that ourprobabilistic formulation outperforms or is comparable to these task specificmodels.

A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling