Families In Wild Multimedia: A Multimodal Database for Recognizing Kinship

TL;DR

This paper introduces FIW MM, a multimodal kinship dataset with videos, audio, and captions, demonstrating significant performance improvements in kinship recognition and enabling more realistic, multi-faceted research in the field.

Contribution

It extends the existing FIW dataset with multimedia data and provides a new multi-task benchmark for kinship recognition, developed with minimal human effort.

Findings

Significant performance improvements with added modalities

First publicly available multimodal kinship dataset

Enhanced potential for real-world kinship recognition systems

Abstract

Kinship, a soft biometric detectable in media, is fundamental for a myriad of use-cases. Despite the difficulty of detecting kinship, annual data challenges using still-images have consistently improved performances and attracted new researchers. Now, systems reach performance levels unforeseeable a decade ago, closing in on performances acceptable to deploy in practice. Like other biometric tasks, we expect systems can receive help from other modalities. We hypothesize that adding modalities to FIW, which has only still-images, will improve performance. Thus, to narrow the gap between research and reality and enhance the power of kinship recognition systems, we extend FIW with multimedia (MM) data (i.e., video, audio, and text captions). Specifically, we introduce the first publicly available multi-task MM kinship dataset. To build FIW MM, we developed machinery to automatically collect, annotate, and prepare the data, requiring minimal human input and no financial cost. The proposed MM corpus allows the problem statements to be more realistic template-based protocols. We show significant improvements in all benchmarks with the added modalities. The results highlight edge cases to inspire future research with different areas of improvement. FIW MM supplies the data needed to increase the potential of automated systems to detect kinship in MM. It also allows experts from diverse fields to collaborate in novel ways.