Group Membership Prediction
This work addresses visual recognition tasks like kinship verification and person re-identification, which are important for applications in security and social analysis, but it appears incremental as it builds on existing group prediction frameworks.
The paper tackles the group membership prediction problem, such as kinship verification and person re-identification, by proposing a novel probability model with latent view-specific and view-shared variables, and reports that it significantly outperforms state-of-the-art methods on most benchmark datasets.
The group membership prediction (GMP) problem involves predicting whether or not a collection of instances share a certain semantic property. For instance, in kinship verification given a collection of images, the goal is to predict whether or not they share a {\it familial} relationship. In this context we propose a novel probability model and introduce latent {\em view-specific} and {\em view-shared} random variables to jointly account for the view-specific appearance and cross-view similarities among data instances. Our model posits that data from each view is independent conditioned on the shared variables. This postulate leads to a parametric probability model that decomposes group membership likelihood into a tensor product of data-independent parameters and data-dependent factors. We propose learning the data-independent parameters in a discriminative way with bilinear classifiers, and test our prediction algorithm on challenging visual recognition tasks such as multi-camera person re-identification and kinship verification. On most benchmark datasets, our method can significantly outperform the current state-of-the-art.