Influence of Heterogamy by Religion on Risk of Marital Dissolution: A Cohort Study of 20,000 Couples

Heterogamous marriages, in which partners have dissimilar attributes (e.g. by socio-economic status or ethnicity), are often at elevated risk of dissolution. We investigated the influences of heterogamy by religion and area of residence on risk of marital dissolution in Northern Ireland, a country with a history of conflict and residential segregation along Catholic–Protestant lines. We expected Catholic–Protestant marriages to have elevated risks of dissolution, especially in areas with high concentrations of a single religious group where opposition to intermarriage was expected to be high. We estimated risks of marital dissolution from 2001 to 2011 for 19,791 couples drawn from the Northern Ireland Longitudinal Study (a record linkage study), adjusting for a range of compositional and contextual factors using multilevel logistic regression. Dissolution risk decreased with increasing age and higher socio-economic status. Catholic–Protestant marriages were rare (5.9 % of the sample) and were at increased risk of dissolution relative to homogamous marriages. We found no association between local population composition and dissolution risk for Catholic–Protestant couples, indicating that partner and household characteristics may have a greater influence on dissolution risk than the wider community.

Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance.