Published on Wed Sep 16 2015

Group Membership Prediction

Ziming Zhang, Yuting Chen, Venkatesh Saligrama

The group membership prediction (GMP) problem involves predicting whether or not a collection of instances share a certain semantic property. We propose a novel probability model that decomposes group membership likelihood into a tensor product of data-independent parameters and data-dependent factors.

0
0
0
Abstract

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.

Mon Jan 12 2015
Computer Vision
Tri-Subject Kinship Verification: Understanding the Core of A Family
Computer vision can help answer such questions as whether a child in a photo belongs to given parents. The understanding of the child-parents relationship would have fundamental impact on the behavior of an artificial intelligence working in the human world.
0
0
0
Sun Jan 10 2021
Computer Vision
Automatic Face Understanding: Recognizing Families in Photos
We built the largest database for kinship recognition. The data were labeled using a novel clustering algorithm. Great savings in time and human input was had. Statistically, FIW shows enormous gains over its predecessors.
0
0
0
Sun May 24 2020
Machine Learning
Recognizing Families through Images with Pretrained Encoder
Kinship verification and kinship retrieval are emerging tasks in computer vision. We employ 3 methods, FaceNet, Siamese VGG-Face and StyleGAN2. We achieve the 9th standing for kinship verification in the Recognizing Family in The Wild 2020 competition.
0
0
0
Mon Nov 21 2016
Computer Vision
Kernel Cross-View Collaborative Representation based Classification for Person Re-Identification
Collaborative Representation based Classification (CRC) has been employed successfully to address the small-sample-size problem in computer vision. The original CRC formulation is not well-suited for person re-identification since it does not consider that probe and gallery samples are from different cameras.
0
0
0
Mon Jun 29 2020
Computer Vision
Survey on the Analysis and Modeling of Visual Kinship: A Decade in the Making
0
0
0
Fri Nov 27 2015
Computer Vision
Structured learning of metric ensembles with application to person re-identification
Matching individuals across non-overlapping camera networks is a fundamentally challenging problem. We propose two structured learning based approaches which explore the adaptive effects of visual features in recognizing persons in different benchmark data sets.
0
0
0