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

We propose a new approach to Human Activity Evaluation (HAE) in long videosusing graph-based multi-task modeling. Previous works in activity evaluationeither directly compute a metric using a detected skeleton or use the sceneinformation to regress the activity score. These approaches are insufficientfor accurate activity assessment since they only compute an average score overa clip, and do not consider the correlation between the joints and bodydynamics. Moreover, they are highly scene-dependent which makes thegeneralizability of these methods questionable. We propose a novel multi-taskframework for HAE that utilizes a Graph Convolutional Network backbone to embedthe interconnections between human joints in the features. In this framework,we solve the Human Activity Segmentation (HAS) problem as an auxiliary task toimprove activity assessment. The HAS head is powered by an Encoder-DecoderTemporal Convolutional Network to semantically segment long videos intodistinct activity classes, whereas, HAE uses a Long-Short-Term-Memory-basedarchitecture. We evaluate our method on the UW-IOM and TUM Kitchen datasets anddiscuss the success and failure cases in these two datasets.

A Multi-Task Learning Approach for Human Activity Segmentation and Ergonomics Risk Assessment