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/

Zendy Plus

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

Zendy Tools

Zendy Open

Analysis of human interaction is one important research topic of human motionanalysis. It has been studied either using first person vision (FPV) or thirdperson vision (TPV). However, the joint learning of both types of vision has sofar attracted little attention. One of the reasons is the lack of suitabledatasets that cover both FPV and TPV. In addition, existing benchmark datasetsof either FPV or TPV have several limitations, including the limited number ofsamples, participant subjects, interaction categories, and modalities. In thiswork, we contribute a large-scale human interaction dataset, namely, FT-HIDdataset. FT-HID contains pair-aligned samples of first person and third personvisions. The dataset was collected from 109 distinct subjects and has more than90K samples for three modalities. The dataset has been validated by usingseveral existing action recognition methods. In addition, we introduce a novelmulti-view interaction mechanism for skeleton sequences, and a joint learningmulti-stream framework for first person and third person visions. Both methodsyield promising results on the FT-HID dataset. It is expected that theintroduction of this vision-aligned large-scale dataset will promote thedevelopment of both FPV and TPV, and their joint learning techniques for humanaction analysis. The dataset and code are available at\href{https://github.com/ENDLICHERE/FT-HID}{here}.

FT-HID: A Large Scale RGB-D Dataset for First and Third Person Human Interaction Analysis