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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recently, few-shot action recognition has significantly progressed bylearning the feature discriminability and designing suitable comparisonmethods. Still, there are the following restrictions. (a) Previous works aremainly based on visual mono-modal. Although some multi-modal works use labelsas supplementary to construct prototypes of support videos, they can not usethis information for query videos. The labels are not used efficiently. (b)Most of the works ignore the motion feature of video, although the motionfeatures are essential for distinguishing. We proposed a Consistency Prototypeand Motion Compensation Network(CLIP-CP$M^2$C) to address these issues.Firstly, we use the CLIP for multi-modal few-shot action recognition with thetext-image comparison for domain adaption. Secondly, in order to make theamount of information between the prototype and the query more similar, wepropose a novel method to compensate for the text(prompt) information of queryvideos when text(prompt) does not exist, which depends on a Consistency Loss.Thirdly, we use the differential features of the adjacent frames in twodirections as the motion features, which explicitly embeds the network withmotion dynamics. We also apply the Consistency Loss to the motion features.Extensive experiments on standard benchmark datasets demonstrate that theproposed method can compete with state-of-the-art results. Our code isavailable at the URL: https://github.com/xxx/xxx.git.

Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CP$\mathbf{M^2}$C)