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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

With the widespread of user-generated Internet videos, emotion recognition inthose videos attracts increasing research efforts. However, most existing worksare based on framelevel visual features and/or audio features, which might failto model the temporal information, e.g. characteristics accumulated along time.In order to capture video temporal information, in this paper, we propose toanalyse features in frequency domain transformed by discrete Fourier transform(DFT features). Frame-level features are firstly extract by a pre-trained deepconvolutional neural network (CNN). Then, time domain features are transferredand interpolated into DFT features. CNN and DFT features are further encodedand fused for emotion classification. By this way, static image featuresextracted from a pre-trained deep CNN and temporal information represented byDFT features are jointly considered for video emotion recognition. Experimentalresults demonstrate that combining DFT features can effectively capturetemporal information and therefore improve emotion recognition performance. Ourapproach has achieved a state-of-the-art performance on the largest videoemotion dataset (VideoEmotion-8 dataset), improving accuracy from 51.1% to62.6%.

Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos