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

Action recognition is currently one of the top-challenging research fields incomputer vision. Convolutional Neural Networks (CNNs) have significantlyboosted its performance but rely on fixed-size spatio-temporal windows ofanalysis, reducing CNNs temporal receptive fields. Among action recognitiondatasets, egocentric recorded sequences have become of important relevancewhile entailing an additional challenge: ego-motion is unavoidably transferredto these sequences. The proposed method aims to cope with it by estimating thisego-motion or camera motion. The estimation is used to temporally partitionvideo sequences into motion-compensated temporal \textit{chunks} showing theaction under stable backgrounds and allowing for a content-driven temporalsampling. A CNN trained in an end-to-end fashion is used to extract temporalfeatures from each \textit{chunk}, which are late fused. This process leads tothe extraction of features from the whole temporal range of an action,increasing the temporal receptive field of the network.

A Prospective Study on Sequence-Driven Temporal Sampling and Ego-Motion Compensation for Action Recognition in the EPIC-Kitchens Dataset