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

Estimation of pain intensity from facial expressions captured in videos hasan immense potential for health care applications. Given the challenges relatedto subjective variations of facial expressions, and operational captureconditions, the accuracy of state-of-the-art DL models for recognizing facialexpressions may decline. Domain adaptation has been widely explored toalleviate the problem of domain shifts that typically occur between video datacaptured across various source and target domains. Moreover, given thelaborious task of collecting and annotating videos, and subjective bias due toambiguity among adjacent intensity levels, weakly-supervised learning isgaining attention in such applications. State-of-the-art WSL models aretypically formulated as regression problems, and do not leverage the ordinalrelationship among pain intensity levels, nor temporal coherence of multipleconsecutive frames. This paper introduces a new DL model for weakly-supervisedDA with ordinal regression that can be adapted using target domain videos withcoarse labels provided on a periodic basis. The WSDA-OR model enforces ordinalrelationships among intensity levels assigned to target sequences, andassociates multiple relevant frames to sequence-level labels. In particular, itlearns discriminant and domain-invariant feature representations by integratingmultiple instance learning with deep adversarial DA, where soft Gaussian labelsare used to efficiently represent the weak ordinal sequence-level labels fromtarget domain. The proposed approach was validated using RECOLA video datasetas fully-labeled source domain data, and UNBC-McMaster shoulder pain videodataset as weakly-labeled target domain data. We have also validated WSDA-OR onBIOVID and Fatigue datasets for sequence level estimation.

Deep Domain Adaptation for Ordinal Regression of Pain Intensity Estimation Using Weakly-Labelled Videos