arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.07702cs.CV
收藏

时间自我监控下的视听对比学习

Audio-Visual Contrastive Learning with Temporal Self-Supervision

Adobe Research(Adobe研究院);University of Surrey(萨里大学)

Simon Jenni, Alexander Black, John Collomosse

摘要:

我们提出了一个自监督学习的视频,学习表示的RGB帧和伴随的音频没有人的监督方法。与捕捉静态场景外观的图像相比,视频还包含声音和时间场景动态。为了利用视频固有的时间和听觉维度,我们的方法将时间自我监督扩展到视听环境,并将其与多模态对比目标相结合。作为时间的自我监督,我们提出回放速度和方向识别在这两种方式,并提出内和跨模态的时间排序任务。此外,我们设计了一种新的对比目标,其中通常的对补充额外的样本依赖的积极和消极的演变特征空间采样。在我们的模型中,我们将这种损失应用于视频片段之间以及视频与其时间上对应的音频片段之间。我们在广泛的消融实验中验证了我们的模型设计,并在转移实验中评估了UCF 101和HMBD 51上的动作识别和检索,ESC 50上的音频分类以及VGG-Sound上的鲁棒视频指纹识别的视频和音频表示,并获得了最先进的结果。

英文摘要:

We propose a self-supervised learning approach for videos that learns representations of both the RGB frames and the accompanying audio without human supervision. In contrast to images that capture the static scene appearance, videos also contain sound and temporal scene dynamics. To leverage the temporal and aural dimension inherent to videos, our method extends temporal self-supervision to the audio-visual setting and integrates it with multi-modal contrastive objectives. As temporal self-supervision, we pose playback speed and direction recognition in both modalities and propose intra- and inter-modal temporal ordering tasks. Furthermore, we design a novel contrastive objective in which the usual pairs are supplemented with additional sample-dependent positives and negatives sampled from the evolving feature space. In our model, we apply such losses among video clips and between videos and their temporally corresponding audio clips. We verify our model design in extensive ablation experiments and evaluate the video and audio representations in transfer experiments to action recognition and retrieval on UCF101 and HMBD51, audio classification on ESC50, and robust video fingerprinting on VGG-Sound, with state-of-the-art results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑