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

Explaining concepts by contrasting examples is an efficient and convenientway of giving insights into the reasons behind a classification decision. Thisis of particular interest in decision-critical domains, such as medicaldiagnostics. One particular challenging use case is to distinguish facialexpressions of pain and other states, such as disgust, due to high similarityof manifestation. In this paper, we present an approach for generatingcontrastive explanations to explain facial expressions of pain and disgustshown in video sequences. We implement and compare two approaches forcontrastive explanation generation. The first approach explains a specific paininstance in contrast to the most similar disgust instance(s) based on theoccurrence of facial expressions (attributes). The second approach takes intoaccount which temporal relations hold between intervals of facial expressionswithin a sequence (relations). The input to our explanation generation approachis the output of an interpretable rule-based classifier for pain and disgust.Weutilize two different similarity metrics to determine near misses and farmisses as contrasting instances. Our results show that near miss explanationsare shorter than far miss explanations, independent from the applied similaritymetric. The outcome of our evaluation indicates that pain and disgust can bedistinguished with the help of temporal relations. We currently planexperiments to evaluate how the explanations help in teaching concepts and howthey could be enhanced by further modalities and interaction.

Explaining with Attribute-based and Relational Near Misses: An Interpretable Approach to Distinguishing Facial Expressions of Pain and Disgust