APES: Audiovisual Person Search in Untrimmed Video

TL;DR

This paper introduces APES, the largest untrimmed audiovisual person search dataset with dense face and speech annotations, and demonstrates that combining audio and visual cues improves person recognition in videos.

Contribution

The paper presents the APES dataset with dense audiovisual annotations and establishes a baseline for audiovisual person search, advancing research in untrimmed video retrieval.

Findings

Audiovisual cues improve person identification accuracy.

APES dataset contains over 1.9K identities and 36 hours of video.

Baseline results demonstrate the effectiveness of audiovisual integration.

Abstract

Humans are arguably one of the most important subjects in video streams, many real-world applications such as video summarization or video editing workflows often require the automatic search and retrieval of a person of interest. Despite tremendous efforts in the person reidentification and retrieval domains, few works have developed audiovisual search strategies. In this paper, we present the Audiovisual Person Search dataset (APES), a new dataset composed of untrimmed videos whose audio (voices) and visual (faces) streams are densely annotated. APES contains over 1.9K identities labeled along 36 hours of video, making it the largest dataset available for untrimmed audiovisual person search. A key property of APES is that it includes dense temporal annotations that link faces to speech segments of the same identity. To showcase the potential of our new dataset, we propose an audiovisual baseline and benchmark for person retrieval. Our study shows that modeling audiovisual cues benefits the recognition of people's identities. To enable reproducibility and promote future research, the dataset annotations and baseline code are available at: https://github.com/fuankarion/audiovisual-person-search