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

Learning invariant representations from images is one of the hardestchallenges facing computer vision. Spatial pooling is widely used to createinvariance to spatial shifting, but it is restricted to convolutional models.In this paper, we propose a novel pooling method that can learn soft clusteringof features from image sequences. It is trained to improve the temporalcoherence of features, while keeping the information loss at minimum. Ourmethod does not use spatial information, so it can be used withnon-convolutional models too. Experiments on images extracted from naturalvideos showed that our method can cluster similar features together. Whentrained by convolutional features, auto-pooling outperformed traditionalspatial pooling on an image classification task, even though it does not usethe spatial topology of features.

Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences