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 this report, the method for the iqiyi submission to the task ofActivityNet 2019 Kinetics-700 challenge is described. Three models are involvedin the model ensemble stage: TSN, HG-NL and StNet. We propose the hierarchicalgroup-wise non-local (HG-NL) module for frame-level features aggregation forvideo classification. The standard non-local (NL) module is effective inaggregating frame-level features on the task of video classification butpresents low parameters efficiency and high computational cost. The HG-NLmethod involves a hierarchical group-wise structure and generates multipleattention maps to enhance performance. Basing on this hierarchical group-wisestructure, the proposed method has competitive accuracy, fewer parameters andsmaller computational cost than the standard NL. For the task of ActivityNet2019 Kinetics-700 challenge, after model ensemble, we finally obtain anaveraged top-1 and top-5 error percentage 28.444% on the test set.

iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention