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

Zero-shot action recognition, which recognizes actions in videos withouthaving received any training examples, is gaining wide attention considering itcan save labor costs and training time. Nevertheless, the performance ofzero-shot learning is still unsatisfactory, which limits its practicalapplication. To solve this problem, this study proposes a framework to improvezero-shot action recognition using human instructions with text descriptions.The proposed framework manually describes video contents, which incurs somelabor costs; in many situations, the labor costs are worth it. We manuallyannotate text features for each action, which can be a word, phrase, orsentence. Then by computing the matching degrees between the video and all textfeatures, we can predict the class of the video. Furthermore, the proposedmodel can also be combined with other models to improve its accuracy. Inaddition, our model can be continuously optimized to improve the accuracy byrepeating human instructions. The results with UCF101 and HMDB51 showed thatour model achieved the best accuracy and improved the accuracies of othermodels.

Improving Zero-Shot Action Recognition using Human Instruction with Text Description