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

Long Short-Term Memory (LSTM) is a prominent recurrent neural network forextracting dependencies from sequential data such as time-series and multi-viewdata, having achieved impressive results for different visual recognitiontasks. A conventional LSTM network can learn a model to posteriorly extractinformation from one input sequence. However, if two or more dependentsequences of data are simultaneously acquired, the conventional LSTM networksmay only process those sequences consecutively, not taking benefit of theinformation carried out by their mutual dependencies. In this context, thispaper proposes two novel LSTM cell architectures that are able to jointly learnfrom multiple sequences simultaneously acquired, targeting to create richer andmore effective models for recognition tasks. The efficacy of the novel LSTMcell architectures is assessed by integrating them into deep learning-basedmethods for face recognition with multi-view, light field images. The new cellarchitectures jointly learn the scene horizontal and vertical parallaxesavailable in a light field image, to capture richer spatio-angular informationfrom both directions. A comprehensive evaluation, with the IST-EURECOM LFFDdataset using three challenging evaluation protocols, shows the advantage ofusing the novel LSTM cell architectures for face recognition over thestate-of-the-art light field-based methods. These results highlight the addedvalue of the novel cell architectures when learning from correlated inputsequences.

Long Short-Term Memory with Gate and State Level Fusion for Light Field-Based Face Recognition