我们呈现了一个用于学习视听表示的自我监督的框架。在我们的框架中引入了一种小说概念，其中除了学习模态和标准的“同步的”跨模型关系之外，riscross也会学习“异步”的跨模式关系。我们展示通过放松音频和视觉模态之间的时间同步性，网络了解强劲的时间不变的表示。我们的实验表明，音频和视觉方式的强大增强，可放松交叉模态时间同步优化性能。要预先绘制我们提出的框架，我们使用具有不同大小，动力学，动力学-400和augioset的不同数据集。学习的表示是在许多下游任务中评估的，即行动识别，声音分类和检索。 Crisscross显示了动作识别的最先进的性能（UCF101和HMDB51）和声音分类（ESC50）。将公开可用的代码和预赠品模型。

We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled video clips. XKD is trained with two pseudo tasks. First, masked data reconstruction is performed to learn modality-specific representations. Next, self-supervised cross-modal knowledge distillation is performed between the two modalities through teacher-student setups to learn complementary information. To identify the most effective information to transfer and also to tackle the domain gap between audio and visual modalities which could hinder knowledge transfer, we introduce a domain alignment strategy for effective cross-modal distillation. Lastly, to develop a general-purpose solution capable of handling both audio and visual streams, a modality-agnostic variant of our proposed framework is introduced, which uses the same backbone for both audio and visual modalities. Our proposed cross-modal knowledge distillation improves linear evaluation top-1 accuracy of video action classification by 8.4% on UCF101, 8.1% on HMDB51, 13.8% on Kinetics-Sound, and 14.2% on Kinetics400. Additionally, our modality-agnostic variant shows promising results in developing a general-purpose network capable of handling different data streams. The code is released on the project website.

Visual and audio modalities are highly correlated, yet they contain different information. Their strong correlation makes it possible to predict the semantics of one from the other with good accuracy. Their intrinsic differences make cross-modal prediction a potentially more rewarding pretext task for self-supervised learning of video and audio representations compared to within-modality learning. Based on this intuition, we propose Cross-Modal Deep Clustering (XDC), a novel selfsupervised method that leverages unsupervised clustering in one modality (e.g., audio) as a supervisory signal for the other modality (e.g., video). This cross-modal supervision helps XDC utilize the semantic correlation and the differences between the two modalities. Our experiments show that XDC outperforms single-modality clustering and other multi-modal variants. XDC achieves state-of-the-art accuracy among self-supervised methods on multiple video and audio benchmarks. Most importantly, our video model pretrained on large-scale unlabeled data significantly outperforms the same model pretrained with full-supervision on ImageNet and Kinetics for action recognition on HMDB51 and UCF101. To the best of our knowledge, XDC is the first self-supervised learning method that outperforms large-scale fully-supervised pretraining for action recognition on the same architecture.

自我监督的方法已通过端到端监督学习的图像分类显着缩小了差距。但是，在人类动作视频的情况下，外观和运动都是变化的重要因素，因此该差距仍然很大。这样做的关键原因之一是，采样对类似的视频剪辑，这是许多自我监督的对比学习方法所需的步骤，目前是保守的，以避免误报。一个典型的假设是，类似剪辑仅在单个视频中暂时关闭，从而导致运动相似性的示例不足。为了减轻这种情况，我们提出了SLIC，这是一种基于聚类的自我监督的对比度学习方法，用于人类动作视频。我们的关键贡献是，我们通过使用迭代聚类来分组类似的视频实例来改善传统的视频内积极采样。这使我们的方法能够利用集群分配中的伪标签来取样更艰难的阳性和负面因素。在UCF101上，SLIC的表现优于最先进的视频检索基线 +15.4％，而直接转移到HMDB51时，SLIC检索基线的率高为15.4％， +5.7％。通过用于动作分类的端到端登录，SLIC在UCF101上获得了83.2％的TOP-1准确性（+0.8％），而HMDB51（+1.6％）上的fric fineTuns in top-1 finetuning。在动力学预处理后，SLIC还与最先进的行动分类竞争。

There is a natural correlation between the visual and auditive elements of a video. In this work we leverage this connection to learn general and effective models for both audio and video analysis from self-supervised temporal synchronization. We demonstrate that a calibrated curriculum learning scheme, a careful choice of negative examples, and the use of a contrastive loss are critical ingredients to obtain powerful multi-sensory representations from models optimized to discern temporal synchronization of audio-video pairs. Without further finetuning, the resulting audio features achieve performance superior or comparable to the state-of-the-art on established audio classification benchmarks (DCASE2014 and ESC-50). At the same time, our visual subnet provides a very effective initialization to improve the accuracy of video-based action recognition models: compared to learning from scratch, our self-supervised pretraining yields a remarkable gain of +19.9% in action recognition accuracy on UCF101 and a boost of +17.7% on HMDB51.

尽管视频自我监督的学习模型最近取得了成功，但关于它们的概括能力仍然有很多了解。在本文中，我们研究了敏感的视频自我监督学习对当前常规基准的方式以及方法是否超出规范评估设置的概括。我们在敏感性的四个不同因素上做到这一点：域，样本，动作和任务。我们的研究包括7个视频数据集，9种自学方法和6种视频理解任务的500多个实验，揭示了视频自我监督学习中的当前基准测试不是沿这些敏感性因素的概括指标。此外，我们发现自我监督的方法在香草的监督前训练后落后，尤其是当域移动较大并且可用下游样品的量很低时。从我们的分析中，我们将严重的基准测试（实验的一个子集）提炼出来，并讨论其对评估现有和未来自我监督视频学习方法获得的表示的普遍性的意义。

Videos are a rich source of multi-modal supervision. In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. To this end, we introduce the notion of a multimodal versatile network -a network that can ingest multiple modalities and whose representations enable downstream tasks in multiple modalities. In particular, we explore how best to combine the modalities, such that fine-grained representations of the visual and audio modalities can be maintained, whilst also integrating text into a common embedding. Driven by versatility, we also introduce a novel process of deflation, so that the networks can be effortlessly applied to the visual data in the form of video or a static image. We demonstrate how such networks trained on large collections of unlabelled video data can be applied on video, video-text, image and audio tasks. Equipped with these representations, we obtain state-of-the-art performance on multiple challenging benchmarks including UCF101, HMDB51, Kinetics600, Audioset and ESC-50 when compared to previous self-supervised work. Our models are publicly available [1, 2, 3]. * Equal contribution. † Work done during an internship at DeepMind. 34th Conference on Neural Information Processing Systems (NeurIPS 2020),

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips from the same short video are pulled together in the embedding space, while clips from different videos are pushed away. We study what makes for good data augmentations for video self-supervised learning and find that both spatial and temporal information are crucial. We carefully design data augmentations involving spatial and temporal cues. Concretely, we propose a temporally consistent spatial augmentation method to impose strong spatial augmentations on each frame of the video while maintaining the temporal consistency across frames. We also propose a sampling-based temporal augmentation method to avoid overly enforcing invariance on clips that are distant in time. On Kinetics-600, a linear classifier trained on the representations learned by CVRL achieves 70.4% top-1 accuracy with a 3D-ResNet-50 (R3D-50) backbone, outperforming ImageNet supervised pre-training by 15.7% and SimCLR unsupervised pre-training by 18.8% using the same inflated R3D-50. The performance of CVRL can be further improved to 72.9% with a larger R3D-152 (2× filters) backbone, significantly closing the gap between unsupervised and supervised video representation learning. Our code and models will be available at https://github.com/tensorflow/models/tree/master/official/.

我们提出了一种自制算法，以从以自我为中心的视频数据中学习表示形式。最近，已经做出了重大努力，以捕捉人类在日常活动中与自己的环境进行互动。结果，已经出现了几个大型的以相互作用的多模式数据的自我为中心的数据集。但是，来自视频的学习表征可能具有挑战性。首先，鉴于长期连续视频的未经保育性质，学习有效表示需要专注于互动的时间。其次，日常活动的视觉表示应对环境状态的变化敏感。但是，当前成功的多模式学习框架鼓励随着时间的推移表示代表。为了应对这些挑战，我们利用音频信号来确定有利于更好学习的可能相互作用的时刻。我们还提出了一个新颖的自我监督目标，该目标从相互作用引起的听觉状态变化中学习。我们在两个大规模的中心数据集（Epic-Kitchens-100和最近发布的EGO4D）上广泛验证了这些贡献，并显示了几个下游任务的改进，包括行动识别，长期行动预期和对象状态变化分类。

通过自学学习的视觉表示是一项极具挑战性的任务，因为网络需要在没有监督提供的主动指导的情况下筛选出相关模式。这是通过大量数据增强，大规模数据集和过量量的计算来实现的。视频自我监督学习（SSL）面临着额外的挑战：视频数据集通常不如图像数据集那么大，计算是一个数量级，并且优化器所必须通过的伪造模式数量乘以几倍。因此，直接从视频数据中学习自我监督的表示可能会导致次优性能。为了解决这个问题，我们建议在视频表示学习框架中利用一个以自我或语言监督为基础的强大模型，并在不依赖视频标记的数据的情况下学习强大的空间和时间信息。为此，我们修改了典型的基于视频的SSL设计和目标，以鼓励视频编码器\ textit {subsume}基于图像模型的语义内容，该模型在通用域上训练。所提出的算法被证明可以更有效地学习（即在较小的时期和较小的批次中），并在单模式SSL方法中对标准下游任务进行了新的最新性能。

我们介绍了一种对比视频表示方法，它使用课程学习在对比度培训中施加动态抽样策略。更具体地说，Concur以易于正面样本（在时间上和语义上相似的剪辑上）开始对比度训练，并且随着训练的进行，它会有效地提高时间跨度，从而有效地采样了硬质阳性（时间为时间和语义上不同）。为了学习更好的上下文感知表示形式，我们还提出了一个辅助任务，以预测积极剪辑之间的时间距离。我们对两个流行的动作识别数据集进行了广泛的实验，即UCF101和HMDB51，我们提出的方法在两项视频动作识别和视频检索的基准任务上实现了最新的性能。我们通过使用R（2+1）D和C3D编码器以及对Kinetics-400和Kinetics-200200数据集的R（2+1）D和C3D编码器以及预训练的影响来探讨编码器骨架和预训练策略的影响。此外，一项详细的消融研究显示了我们提出的方法的每个组成部分的有效性。

我们提出了MACLR，这是一种新颖的方法，可显式执行从视觉和运动方式中学习的跨模式自我监督的视频表示。与以前的视频表示学习方法相比，主要关注学习运动线索的研究方法是隐含的RGB输入，MACLR丰富了RGB视频片段的标准对比度学习目标，具有运动途径和视觉途径之间的跨模式学习目标。我们表明，使用我们的MACLR方法学到的表示形式更多地关注前景运动区域，因此可以更好地推广到下游任务。为了证明这一点，我们在五个数据集上评估了MACLR，以进行动作识别和动作检测，并在所有数据集上展示最先进的自我监督性能。此外，我们表明MACLR表示可以像在UCF101和HMDB51行动识别的全面监督下所学的表示一样有效，甚至超过了对Vidsitu和SSV2的行动识别的监督表示，以及对AVA的动作检测。

The objective of this paper is visual-only self-supervised video representation learning. We make the following contributions: (i) we investigate the benefit of adding semantic-class positives to instance-based Info Noise Contrastive Estimation (In-foNCE) training, showing that this form of supervised contrastive learning leads to a clear improvement in performance; (ii) we propose a novel self-supervised co-training scheme to improve the popular infoNCE loss, exploiting the complementary information from different views, RGB streams and optical flow, of the same data source by using one view to obtain positive class samples for the other; (iii) we thoroughly evaluate the quality of the learnt representation on two different downstream tasks: action recognition and video retrieval. In both cases, the proposed approach demonstrates state-of-the-art or comparable performance with other self-supervised approaches, whilst being significantly more efficient to train, i.e. requiring far less training data to achieve similar performance.

We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and inter-modal contrastive learning with masking, and (3) self-training by reconstructing joint audio-video contextualized features learned from the first two objectives. Pre-training with MAViL not only enables the model to perform well in audio-visual classification and retrieval tasks but also improves representations of each modality in isolation, without using information from the other modality for fine-tuning or inference. Empirically, MAViL sets a new state-of-the-art on AudioSet (53.1 mAP) and VGGSound (67.1% accuracy). For the first time, a self-supervised audio-visual model outperforms ones that use external supervision on these benchmarks. Code will be available soon.

视频自我监督的学习是一项挑战的任务，这需要模型的显着表达力量来利用丰富的空间时间知识，并从大量未标记的视频产生有效的监督信号。但是，现有方法未能提高未标记视频的时间多样性，并以明确的方式忽略精心建模的多尺度时间依赖性。为了克服这些限制，我们利用视频中的多尺度时间依赖性，并提出了一个名为时间对比图学习（TCGL）的新型视频自我监督学习框架，该框架共同模拟了片段间和片段间的时间依赖性用混合图对比学习策略学习的时间表示学习。具体地，首先引入空间 - 时间知识发现（STKD）模块以基于离散余弦变换的频域分析从视频中提取运动增强的空间时间表。为了显式模拟未标记视频的多尺度时间依赖性，我们的TCGL将关于帧和片段命令的先前知识集成到图形结构中，即片段/间隙间时间对比图（TCG）。然后，特定的对比学习模块旨在最大化不同图形视图中节点之间的协议。为了为未标记的视频生成监控信号，我们介绍了一种自适应片段订购预测（ASOP）模块，它利用视频片段之间的关系知识来学习全局上下文表示并自适应地重新校准通道明智的功能。实验结果表明我们的TCGL在大规模行动识别和视频检索基准上的最先进方法中的优势。

最近，自我监督的表示学习（SSRL）在计算机视觉，语音，自然语言处理（NLP）以及最近的其他类型的模式（包括传感器的时间序列）中引起了很多关注。自我监督学习的普及是由传统模型通常需要大量通知数据进行培训的事实所驱动的。获取带注释的数据可能是一个困难且昂贵的过程。已经引入了自我监督的方法，以通过使用从原始数据自由获得的监督信号对模型进行判别预训练来提高训练数据的效率。与现有的对SSRL的评论不同，该评论旨在以单一模式为重点介绍CV或NLP领域的方法，我们旨在为时间数据提供对多模式自我监督学习方法的首次全面审查。为此，我们1）提供现有SSRL方法的全面分类，2）通过定义SSRL框架的关键组件来引入通用管道，3）根据其目标功能，网络架构和潜在应用程序，潜在的应用程序，潜在的应用程序，比较现有模型， 4）查看每个类别和各种方式中的现有多模式技术。最后，我们提出了现有的弱点和未来的机会。我们认为，我们的工作对使用多模式和/或时间数据的域中SSRL的要求有了一个观点

The remarkable success of deep learning in various domains relies on the availability of large-scale annotated datasets. However, obtaining annotations is expensive and requires great effort, which is especially challenging for videos. Moreover, the use of human-generated annotations leads to models with biased learning and poor domain generalization and robustness. As an alternative, self-supervised learning provides a way for representation learning which does not require annotations and has shown promise in both image and video domains. Different from the image domain, learning video representations are more challenging due to the temporal dimension, bringing in motion and other environmental dynamics. This also provides opportunities for video-exclusive ideas that advance self-supervised learning in the video and multimodal domain. In this survey, we provide a review of existing approaches on self-supervised learning focusing on the video domain. We summarize these methods into four different categories based on their learning objectives: 1) pretext tasks, 2) generative learning, 3) contrastive learning, and 4) cross-modal agreement. We further introduce the commonly used datasets, downstream evaluation tasks, insights into the limitations of existing works, and the potential future directions in this area.

我们使用无卷积的变压器架构提出了一种从未标记数据学习多式式表示的框架。具体而言，我们的视频音频文本变压器（Vatt）将原始信号作为输入提取，提取丰富的多式化表示，以使各种下游任务受益。我们使用多模式对比损失从头划线训练Vatt端到端，并通过视频动作识别，音频事件分类，图像分类和文本到视频检索的下游任务评估其性能。此外，我们通过共享三种方式之间的重量来研究模型 - 无话的单骨架变压器。我们表明，无卷积VATT优于下游任务中的最先进的Convnet架构。特别是，Vatt的视觉变压器在动力学-400上实现82.1％的高精度82.1％，在动力学-600，72.7％的动力学-700上的72.7％，以及时间的时间，新的记录，在避免受监督的预训练时，新的记录。通过从头划伤训练相同的变压器，转移到图像分类导致图像分类导致78.7％的ImageNet精度为64.7％，尽管视频和图像之间的域间差距，我们的模型概括了我们的模型。 Vatt的音雅音频变压器还通过在没有任何监督的预训练的情况下在Audioset上实现39.4％的地图来设置基于波形的音频事件识别的新记录。 Vatt的源代码是公开的。

我们提出了一个简单而有效的自我监督框架，用于视听表示学习，以将声源定位在视频中。为了了解什么使能够学习有用的表示形式，我们系统地研究了数据增强的效果，并揭示（1）数据增强的组成起着关键作用，{\ em I.E.}〜明确鼓励音频表征是不变的各种转换〜（{\ em转换不变性}）; （2）强制执行几何一致性基本上提高了学会表示的质量，{\ em，即}〜所检测到的声源应遵循在输入视频帧〜（{\ em em transive equivarianciance}）上应用的相同转换。广泛的实验表明，我们的模型在两个声音定位基准上的先前方法（即Flickr-soundnet和vgg-sounds）都显着优于先前的方法。此外，我们还评估了音频检索和跨模式检索任务。在这两种情况下，我们的自我监管模型都表现出了出色的检索性能，甚至在音频检索中具有监督方法竞争。这揭示了所提出的框架学会了强大的多模式表示，这些表示有益于声音定位和对进一步应用的概括。 \ textIt {所有代码都将可用}。

我们提出了一个新的基准数据集，即Sapsucker Woods 60（SSW60），用于推进视听细颗粒分类的研究。尽管我们的社区在图像上的细粒度视觉分类方面取得了长足的进步，但音频和视频细颗粒分类的对应物相对尚未探索。为了鼓励在这个领域的进步，我们已经仔细构建了SSW60数据集，以使研究人员能够以三种不同的方式对相同的类别进行分类：图像，音频和视频。该数据集涵盖了60种鸟类，由现有数据集以及全新的专家策划音频和视频数据集组成。我们通过使用最先进的变压器方法进行了彻底基准的视听分类性能和模态融合实验。我们的发现表明，视听融合方法的性能要比仅使用基于图像或音频的方法来进行视频分类任务要好。我们还提出了有趣的模态转移实验，这是由SSW60的独特构造所涵盖的三种不同模态所实现的。我们希望SSW60数据集和伴随的基线在这个迷人的地区进行研究。