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

Fine-grained action segmentation and recognition is an important yetchallenging task. Given a long, untrimmed sequence of kinematic data, the taskis to classify the action at each time frame and segment the time series intothe correct sequence of actions. In this paper, we propose a novel frameworkthat combines a temporal Conditional Random Field (CRF) model with a powerfulframe-level representation based on discriminative sparse coding. We introducean end-to-end algorithm for jointly learning the weights of the CRF model,which include action classification and action transition costs, as well as anovercomplete dictionary of mid-level action primitives. This results in a CRFmodel that is driven by sparse coding features obtained using a discriminativedictionary that is shared among different actions and adapted to the task ofstructured output learning. We evaluate our method on three surgical tasksusing kinematic data from the JIGSAWS dataset, as well as on a food preparationtask using accelerometer data from the 50 Salads dataset. Our results show thatthe proposed method performs on par or better than state-of-the-art methods.

End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding