English

Audio-Visual Event Localization in Unconstrained Videos

Computer Vision and Pattern Recognition 2018-03-26 v1

Abstract

In this paper, we introduce a novel problem of audio-visual event localization in unconstrained videos. We define an audio-visual event as an event that is both visible and audible in a video segment. We collect an Audio-Visual Event(AVE) dataset to systemically investigate three temporal localization tasks: supervised and weakly-supervised audio-visual event localization, and cross-modality localization. We develop an audio-guided visual attention mechanism to explore audio-visual correlations, propose a dual multimodal residual network (DMRN) to fuse information over the two modalities, and introduce an audio-visual distance learning network to handle the cross-modality localization. Our experiments support the following findings: joint modeling of auditory and visual modalities outperforms independent modeling, the learned attention can capture semantics of sounding objects, temporal alignment is important for audio-visual fusion, the proposed DMRN is effective in fusing audio-visual features, and strong correlations between the two modalities enable cross-modality localization.

Keywords

Cite

@article{arxiv.1803.08842,
  title  = {Audio-Visual Event Localization in Unconstrained Videos},
  author = {Yapeng Tian and Jing Shi and Bochen Li and Zhiyao Duan and Chenliang Xu},
  journal= {arXiv preprint arXiv:1803.08842},
  year   = {2018}
}

Comments

23 pages, 7 figures

R2 v1 2026-06-23T01:03:10.864Z