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

We introduce caption-guided face recognition (CGFR) as a new framework toimprove the performance of commercial-off-the-shelf (COTS) face recognition(FR) systems. In contrast to combining soft biometrics (eg., facial marks,gender, and age) with face images, in this work, we use facial descriptionsprovided by face examiners as a piece of auxiliary information. However, due tothe heterogeneity of the modalities, improving the performance by directlyfusing the textual and facial features is very challenging, as both lie indifferent embedding spaces. In this paper, we propose a contextual featureaggregation module (CFAM) that addresses this issue by effectively exploitingthe fine-grained word-region interaction and global image-caption association.Specifically, CFAM adopts a self-attention and a cross-attention scheme forimproving the intra-modality and inter-modality relationship between the imageand textual features, respectively. Additionally, we design a textual featurerefinement module (TFRM) that refines the textual features of the pre-trainedBERT encoder by updating the contextual embeddings. This module enhances thediscriminative power of textual features with a cross-modal projection loss andrealigns the word and caption embeddings with visual features by incorporatinga visual-semantic alignment loss. We implemented the proposed CGFR framework ontwo face recognition models (ArcFace and AdaFace) and evaluated its performanceon the Multi-Modal CelebA-HQ dataset. Our framework significantly improves theperformance of ArcFace in both 1:1 verification and 1:N identificationprotocol.

Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation