Abstract
Audio-visual person recognition (AVPR) has received extensive attention. However, most datasets used for AVPR research so far are collected in constrained environments, and thus cannot reflect the true performance of AVPR systems in real-world scenarios. To meet the request for research on AVPR in unconstrained conditions, this paper presents a multi-genre AVPR dataset collected `in the wild', named CN-Celeb-AV. This dataset contains more than 420k video segments from 1,136 persons from public media. In particular, we put more emphasis on two real-world complexities: (1) data in multiple genres; (2) segments with partial information. A comprehensive study was conducted to compare CN-Celeb-AV with two popular public AVPR benchmark datasets, and the results demonstrated that CN-Celeb-AV is more in line with real-world scenarios and can be regarded as a new benchmark dataset for AVPR research. The dataset also involves a development set that can be used to boost the performance of AVPR systems in real-life situations. The dataset is free for researchers and can be downloaded from this http URL.
Abstract (translated)
听觉视觉个人识别(AVPR)已经受到了广泛的关注。然而,目前用于AVPR研究的大多数数据集都是在限制环境下收集的,因此无法反映现实世界中AVPR系统的真实表现。为了满足对在没有限制条件下研究AVPR的要求,本文介绍了一个多体裁AVPR数据集,名为CN-Celeb-AV,该数据集是从公共媒体中收集的超过420,000个视频片段,涉及1,136名公众。特别强调的是两个现实世界的复杂性:(1)多个体裁的数据;(2)部分信息的视频片段。进行了一项全面的研究,以比较CN-Celeb-AV与两个流行的公共AVPR基准数据集,结果表明,CN-Celeb-AV更接近现实世界场景,可以被视为AVPR研究的新基准数据集。数据集还包括一个开发集,可用于提高AVPR系统在现实世界场景中的性能。数据集是免费向公众开放的,可以从这个httpURL下载。
URL
https://arxiv.org/abs/2305.16049