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

Spatiotemporal and motion features are two complementary and crucialinformation for video action recognition. Recent state-of-the-art methods adopta 3D CNN stream to learn spatiotemporal features and another flow stream tolearn motion features. In this work, we aim to efficiently encode these twofeatures in a unified 2D framework. To this end, we first propose an STM block,which contains a Channel-wise SpatioTemporal Module (CSTM) to present thespatiotemporal features and a Channel-wise Motion Module (CMM) to efficientlyencode motion features. We then replace original residual blocks in the ResNetarchitecture with STM blcoks to form a simple yet effective STM network byintroducing very limited extra computation cost. Extensive experimentsdemonstrate that the proposed STM network outperforms the state-of-the-artmethods on both temporal-related datasets (i.e., Something-Something v1 & v2and Jester) and scene-related datasets (i.e., Kinetics-400, UCF-101, andHMDB-51) with the help of encoding spatiotemporal and motion features together.

STM: SpatioTemporal and Motion Encoding for Action Recognition