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

Tiny Actions Challenge focuses on understanding human activities inreal-world surveillance. Basically, there are two main difficulties foractivity recognition in this scenario. First, human activities are oftenrecorded at a distance, and appear in a small resolution without muchdiscriminative clue. Second, these activities are naturally distributed in along-tailed way. It is hard to alleviate data bias for such heavy categoryimbalance. To tackle these problems, we propose a comprehensive recognitionsolution in this paper. First, we train video backbones with data balance, inorder to alleviate overfitting in the challenge benchmark. Second, we design adual-resolution distillation framework, which can effectively guidelow-resolution action recognition by super-resolution knowledge. Finally, weapply model en-semble with post-processing, which can further boostper-formance on the long-tailed categories. Our solution ranks Top-1 on theleaderboard.

Low-Resolution Action Recognition for Tiny Actions Challenge