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

Video Recognition has drawn great research interest and great progress hasbeen made. A suitable frame sampling strategy can improve the accuracy andefficiency of recognition. However, mainstream solutions generally adopthand-crafted frame sampling strategies for recognition. It could degrade theperformance, especially in untrimmed videos, due to the variation offrame-level saliency. To this end, we concentrate on improving untrimmed videoclassification via developing a learning-based frame sampling strategy. Weintuitively formulate the frame sampling procedure as multiple parallel Markovdecision processes, each of which aims at picking out a frame/clip by graduallyadjusting an initial sampling. Then we propose to solve the problems withmulti-agent reinforcement learning (MARL). Our MARL framework is composed of anovel RNN-based context-aware observation network which jointly models contextinformation among nearby agents and historical states of a specific agent, apolicy network which generates the probability distribution over a predefinedaction space at each step and a classification network for reward calculationas well as final recognition. Extensive experimental results show that ourMARL-based scheme remarkably outperforms hand-crafted strategies with various2D and 3D baseline methods. Our single RGB model achieves a comparableperformance of ActivityNet v1.3 champion submission with multi-modalmulti-model fusion and new state-of-the-art results on YouTube Birds andYouTube Cars.

Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition