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

Based on the progress of image recognition, video recognition has beenextensively studied recently. However, most of the existing methods are focusedon short-term but not long-term video recognition, called contextual videorecognition. To address contextual video recognition, we use convolutionalrecurrent neural networks (ConvRNNs) having a rich spatio-temporal informationprocessing capability, but ConvRNNs requires extensive computation that slowsdown training. In this paper, inspired by the normalization and detrendingmethods, we propose adaptive detrending (AD) for temporal normalization inorder to accelerate the training of ConvRNNs, especially for convolutionalgated recurrent unit (ConvGRU). AD removes internal covariate shift within asequence of each neuron in recurrent neural networks (RNNs) by subtracting atrend. In the experiments for contextual recognition on ConvGRU, the resultsshow that (1) ConvGRU clearly outperforms the feed-forward neural networks, (2)AD consistently offers a significant training acceleration and generalizationimprovement, and (3) AD is further improved by collaborating with the existingnormalization methods.

Adaptive Detrending to Accelerate Convolutional Gated Recurrent Unit Training for Contextual Video Recognition