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

In recent years, few-shot action recognition has attracted increasingattention. It generally adopts the paradigm of meta-learning. In this field,overcoming the overlapping distribution of classes and outliers is still achallenging problem based on limited samples. We believe the combination ofMulti-modal and Multi-view can improve this issue depending on informationcomplementarity. Therefore, we propose a method of Multi-view Distillationbased on Multi-modal Fusion. Firstly, a Probability Prompt Selector for thequery is constructed to generate probability prompt embedding based on thecomparison score between the prompt embeddings of the support and the visualembedding of the query. Secondly, we establish a Multi-view. In each view, wefuse the prompt embedding as consistent information with visual and the globalor local temporal context to overcome the overlapping distribution of classesand outliers. Thirdly, we perform the distance fusion for the Multi-view andthe mutual distillation of matching ability from one to another, enabling themodel to be more robust to the distribution bias. Our code is available at theURL: \url{https://github.com/cofly2014/MDMF}.

Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-$\mathrm{M^2}$DF)