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

This paper describes our solution for the video recognition task ofActivityNet Kinetics challenge that ranked the 1st place. Most of existingstate-of-the-art video recognition approaches are in favor of an end-to-endpipeline. One exception is the framework of DevNet. The merit of DevNet is thatthey first use the video data to learn a network (i.e. fine-tuning or trainingfrom scratch). Instead of directly using the end-to-end classification scores(e.g. softmax scores), they extract the features from the learned network andthen fed them into the off-the-shelf machine learning models to conduct videoclassification. However, the effectiveness of this line work has long-term beenignored and underestimated. In this submission, we extensively use thisstrategy. Particularly, we investigate four temporal modeling approaches usingthe learned features: Multi-group Shifting Attention Network, Temporal XceptionNetwork, Multi-stream sequence Model and Fast-Forward Sequence Model.Experiment results on the challenging Kinetics dataset demonstrate that ourproposed temporal modeling approaches can significantly improve existingapproaches in the large-scale video recognition tasks. Most remarkably, ourbest single Multi-group Shifting Attention Network can achieve 77.7% in term oftop-1 accuracy and 93.2% in term of top-5 accuracy on the validation set.

Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification