iQIYI-VID: A Large Dataset for Multi-modal Person Identification

TL;DR

This paper introduces iQIYI-VID, the largest multi-modal video dataset for person identification, and demonstrates how multi-modal feature fusion improves identification accuracy in challenging real-world scenarios.

Contribution

The paper presents a large-scale, high-quality multi-modal dataset for person identification and proposes a novel Multi-modal Attention module for better feature fusion.

Findings

State-of-the-art models perform poorly in wild conditions

Multi-modal feature fusion improves identification accuracy

Dataset release promotes further research in the field

Abstract

Person identification in the wild is very challenging due to great variation in poses, face quality, clothes, makeup and so on. Traditional research, such as face recognition, person re-identification, and speaker recognition, often focuses on a single modal of information, which is inadequate to handle all the situations in practice. Multi-modal person identification is a more promising way that we can jointly utilize face, head, body, audio features, and so on. In this paper, we introduce iQIYI-VID, the largest video dataset for multi-modal person identification. It is composed of 600K video clips of 5,000 celebrities. These video clips are extracted from 400K hours of online videos of various types, ranging from movies, variety shows, TV series, to news broadcasting. All video clips pass through a careful human annotation process, and the error rate of labels is lower than 0.2\%. We evaluated the state-of-art models of face recognition, person re-identification, and speaker recognition on the iQIYI-VID dataset. Experimental results show that these models are still far from being perfect for the task of person identification in the wild. We proposed a Multi-modal Attention module to fuse multi-modal features that can improve person identification considerably. We have released the dataset online to promote multi-modal person identification research.