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

Temporal action segmentation is a task to classify each frame in the videowith an action label. However, it is quite expensive to annotate every frame ina large corpus of videos to construct a comprehensive supervised trainingdataset. Thus in this work we propose an unsupervised method, namely SSCAP,that operates on a corpus of unlabeled videos and predicts a likely set oftemporal segments across the videos. SSCAP leverages Self-Supervised learningto extract distinguishable features and then applies a novel Co-occurrenceAction Parsing algorithm to not only capture the correlation among sub-actionsunderlying the structure of activities, but also estimate the temporal path ofthe sub-actions in an accurate and general way. We evaluate on both classicdatasets (Breakfast, 50Salads) and the emerging fine-grained action dataset(FineGym) with more complex activity structures and similar sub-actions.Results show that SSCAP achieves state-of-the-art performance on all datasetsand can even outperform some weakly-supervised approaches, demonstrating itseffectiveness and generalizability.

SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation