arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.08237cs.CV
收藏

LoCoNet:用于主动说话人检测的长短上下文网络

LoCoNet: Long-Short Context Network for Active Speaker Detection

Indiana University(印第安纳大学);UNC Chapel Hill(北卡罗来纳大学教堂山分校)

Xizi Wang, Feng Cheng, Gedas Bertasius, David Crandall

AI总结:

LoCoNet 通过自注意力建模长期说话人内部上下文、卷积块建模短期说话人之间上下文,在多个 ASD 数据集上取得最先进性能。

摘要:

主动说话人检测(ASD)旨在识别视频每一帧中谁在说话。ASD 从两种上下文中的音频和视觉信息进行推理:长期说话人内部上下文和短期说话人之间上下文。长期说话人内部上下文建模同一说话人的时间依赖关系,而短期说话人之间上下文建模同一场景中说话人之间的交互。这两种上下文相互补充,有助于推断主动说话人。受这些观察启发,我们提出了 LoCoNet,一种简单而有效的长短上下文网络,用于建模长期说话人内部上下文和短期说话人之间上下文。我们使用自注意力来建模长期说话人内部上下文,因为它在建模长距离依赖方面非常有效,并使用捕获局部模式的卷积块来建模短期说话人之间上下文。大量实验表明,LoCoNet 在多个数据集上取得了最先进的性能,在 AVA-ActiveSpeaker 上达到 95.2%(+1.1%)的 mAP,在 Columbia 数据集上达到 68.1%(+22%),在 Talkies 数据集上达到 97.2%(+2.8%),在 Ego4D 数据集上达到 59.7%(+8.0%)。此外,在存在多个说话人或主动说话人的面部远小于同一场景中其他面部的挑战性情况下,LoCoNet 在 AVA-ActiveSpeaker 数据集上比先前最先进的方法高出 3.4%。代码将在 https://github.com/SJTUwxz/LoCoNet_ASD 发布。

英文摘要:

Active Speaker Detection (ASD) aims to identify who is speaking in each frame of a video. ASD reasons from audio and visual information from two contexts: long-term intra-speaker context and short-term inter-speaker context. Long-term intra-speaker context models the temporal dependencies of the same speaker, while short-term inter-speaker context models the interactions of speakers in the same scene. These two contexts are complementary to each other and can help infer the active speaker. Motivated by these observations, we propose LoCoNet, a simple yet effective Long-Short Context Network that models the long-term intra-speaker context and short-term inter-speaker context. We use self-attention to model long-term intra-speaker context due to its effectiveness in modeling long-range dependencies, and convolutional blocks that capture local patterns to model short-term inter-speaker context. Extensive experiments show that LoCoNet achieves state-of-the-art performance on multiple datasets, achieving an mAP of 95.2%(+1.1%) on AVA-ActiveSpeaker, 68.1%(+22%) on Columbia dataset, 97.2%(+2.8%) on Talkies dataset and 59.7%(+8.0%) on Ego4D dataset. Moreover, in challenging cases where multiple speakers are present, or face of active speaker is much smaller than other faces in the same scene, LoCoNet outperforms previous state-of-the-art methods by 3.4% on the AVA-ActiveSpeaker dataset. The code will be released at https://github.com/SJTUwxz/LoCoNet_ASD.

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。

↑