从fMRI大脑记录中重建自然视频非常具有挑战性，这两个主要原因是：（i）由于fMRI数据获取很困难，我们只有有限的监督样本，这还不足以覆盖自然视频的巨大空间； （ii）fMRI记录的时间分辨率远低于自然视频的帧速率。在本文中，我们提出了一种自我监督的自然电影重建方法。通过对编码编码自然视频的编码使用周期矛盾，我们可以：（i）利用培训视频的完整帧速率，而不仅仅限于与fMRI录音相对应的剪辑； （ii）利用受试者在fMRI机器内从未见过的大量外部自然视频。这些使适用的培训数据通过几个数量级增加，将自然视频先验引入解码网络以及时间连贯性。我们的方法大大优于竞争方法，因为这些方法仅在有限的监督数据上训练。我们进一步介绍了自然视频的新的简单暂时性先验，当将其进一步折叠到我们的fMRI解码器中时 - 允许我们在原始fMRI样本率的X8的较高框架速率（HFR）中重建视频。

高动态范围（HDR）视频提供比标准低动态范围（LDR）视频更具视觉上的体验。尽管HDR成像具有重要进展，但仍有一个具有挑战性的任务，可以使用传统的现成摄像头捕获高质量的HDR视频。现有方法完全依赖于在相邻的LDR序列之间使用致密光流来重建HDR帧。然而，当用嘈杂的框架应用于交替的曝光时，它们会导致颜色和暴露的曝光不一致。在本文中，我们提出了一种从LDR序列与交替曝光的LDR序列的HDR视频重建的端到端GAN框架。我们首先从Noisy LDR视频中提取清洁LDR帧，并具有在自我监督设置中培训的去噪网络的交替曝光。然后，我们将相邻的交流帧与参考帧对齐，然后在完全的对手设置中重建高质量的HDR帧。为了进一步提高所产生帧的鲁棒性和质量，我们在培训过程中将时间稳定性的正则化术语与成本函数的内容和风格的损耗一起融合。实验结果表明，我们的框架实现了最先进的性能，并通过现有方法生成视频的优质HDR帧。

We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be highly complex. Traditional optical-flow-based solutions often fail where flow estimation is challenging, while newer neural-network-based methods that hallucinate pixel values directly often produce blurry results. We combine the advantages of these two methods by training a deep network that learns to synthesize video frames by flowing pixel values from existing ones, which we call deep voxel flow. Our method requires no human supervision, and any video can be used as training data by dropping, and then learning to predict, existing frames. The technique is efficient, and can be applied at any video resolution. We demonstrate that our method produces results that both quantitatively and qualitatively improve upon the state-ofthe-art.

本文研究了从快照编码的LDR视频重建高动态范围（HDR）视频。构建HDR视频需要为每个帧恢复HDR值并保持连续帧之间的一致性。从单个图像捕获的HDR图像获取，也称为快照HDR成像，可以通过多种方式实现。例如，通过将光学元件引入相机的光学堆叠来实现可重新配置的快照HDR相机;通过将编码掩模放置在传感器前方的小支座距离处。可以使用深度学习方法从捕获的编码图像中恢复高质量的HDR图像。本研究利用3D-CNNS从编码LDR视频执行联合去脱模，去噪和HDR视频重建。我们通过引入考虑短期和长期一致性的时间损耗函数来执行更季度一致的HDR视频重建。获得的结果是有前途的，可以使用传统相机导致经济实惠的HDR视频捕获。

We propose a new self-supervised CNN pre-training technique based on a novel auxiliary task called odd-oneout learning. In this task, the machine is asked to identify the unrelated or odd element from a set of otherwise related elements. We apply this technique to self-supervised video representation learning where we sample subsequences from videos and ask the network to learn to predict the odd video subsequence. The odd video subsequence is sampled such that it has wrong temporal order of frames while the even ones have the correct temporal order. Therefore, to generate a odd-one-out question no manual annotation is required. Our learning machine is implemented as multi-stream convolutional neural network, which is learned end-to-end. Using odd-one-out networks, we learn temporal representations for videos that generalizes to other related tasks such as action recognition.On action classification, our method obtains 60.3% on the UCF101 dataset using only UCF101 data for training which is approximately 10% better than current stateof-the-art self-supervised learning methods. Similarly, on HMDB51 dataset we outperform self-supervised state-ofthe art methods by 12.7% on action classification task.

由于细粒度的视觉细节中的运动和丰富内容的大变化，视频是复杂的。从这些信息密集型媒体中抽象有用的信息需要详尽的计算资源。本文研究了一个两步的替代方案，首先将视频序列冷凝到信息“框架”，然后在合成帧上利用现成的图像识别系统。有效问题是如何定义“有用信息”，然后将其从视频序列蒸发到一个合成帧。本文介绍了一种新颖的信息帧综合（IFS）架构，其包含三个客观任务，即外观重建，视频分类，运动估计和两个常规方案，即对抗性学习，颜色一致性。每个任务都配备了一个能力的合成框，而每个常规器可以提高其视觉质量。利用这些，通过以端到端的方式共同学习帧合成，预期产生的帧封装了用于视频分析的所需的时空信息。广泛的实验是在大型动力学数据集上进行的。与基线方法相比，将视频序列映射到单个图像，IFS显示出优异的性能。更值得注意地，IFS始终如一地展示了基于图像的2D网络和基于剪辑的3D网络的显着改进，并且通过了具有较少计算成本的最先进方法实现了相当的性能。

来自单个运动模糊图像的视频重建是一个具有挑战性的问题，可以增强现有的相机的能力。最近，几种作品使用传统的成像和深度学习解决了这项任务。然而，由于方向模糊和噪声灵敏度，这种纯粹 - 数字方法本质上是有限的。一些作品提出使用非传统图像传感器解决这些限制，然而，这种传感器非常罕见和昂贵。为了使这些限制具有更简单的方法，我们提出了一种用于视频重建的混合光学 - 数字方法，其仅需要对现有光学系统的简单修改。在图像采集期间，在镜头孔径中使用学习的动态相位编码以对运动轨迹进行编码，该运动轨迹用作视频重建过程的先前信息。使用图像到视频卷积神经网络，所提出的计算相机以各种编码运动模糊图像的各种帧速率产生锐帧帧突发。与现有方法相比，我们使用模拟和现实世界的相机原型表现了优势和改进的性能。

We wish to automatically predict the "speediness" of moving objects in videos-whether they move faster, at, or slower than their "natural" speed. The core component in our approach is SpeedNet-a novel deep network trained to detect if a video is playing at normal rate, or if it is sped up. SpeedNet is trained on a large corpus of natural videos in a self-supervised manner, without requiring any manual annotations. We show how this single, binary classification network can be used to detect arbitrary rates of speediness of objects. We demonstrate prediction results by Speed-Net on a wide range of videos containing complex natural motions, and examine the visual cues it utilizes for making those predictions. Importantly, we show that through predicting the speed of videos, the model learns a powerful and meaningful space-time representation that goes beyond simple motion cues. We demonstrate how those learned features can boost the performance of self-supervised action recognition, and can be used for video retrieval. Furthermore, we also apply SpeedNet for generating time-varying, adaptive video speedups, which can allow viewers to watch videos faster, but with less of the jittery, unnatural motions typical to videos that are sped up uniformly.

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/.

视频通常将流和连续的视觉数据记录为离散的连续帧。由于存储成本对于高保真度的视频来说是昂贵的，因此大多数存储以相对较低的分辨率和帧速率存储。最新的时空视频超分辨率（STVSR）的工作是开发出来的，以将时间插值和空间超分辨率纳入统一框架。但是，其中大多数仅支持固定的上采样量表，这限制了其灵活性和应用。在这项工作中，我们没有遵循离散表示，我们提出了视频隐式神经表示（videoinr），并显示了其对STVSR的应用。学到的隐式神经表示可以解码为任意空间分辨率和帧速率的视频。我们表明，Videoinr在常见的上采样量表上使用最先进的STVSR方法实现了竞争性能，并且在连续和训练的分布量表上显着优于先前的作品。我们的项目页面位于http://zeyuan-chen.com/videoinr/。

无意的行动是罕见的事件，难以精确定义，并且高度依赖于动作的时间背景。在这项工作中，我们探讨了此类行动，并试图确定视频中的观点，这些动作从故意到无意中过渡。我们提出了一个多阶段框架，该框架利用了固有的偏见，例如运动速度，运动方向和为了识别无意的行动。为了通过自我监督的训练来增强表示，我们提出了时间转变，称为时间转变，称为无意义行动固有偏见（T2IBUA）的时间转变。多阶段方法对各个帧和完整剪辑的级别进行了时间信息。这些增强的表示表现出强烈的无意行动识别任务的表现。我们对我们的框架进行了广泛的消融研究，并报告结果对最先进的结果有了显着改善。

Given two consecutive frames, video interpolation aims at generating intermediate frame(s) to form both spatially and temporally coherent video sequences. While most existing methods focus on single-frame interpolation, we propose an end-to-end convolutional neural network for variable-length multi-frame video interpolation, where the motion interpretation and occlusion reasoning are jointly modeled. We start by computing bi-directional optical flow between the input images using a U-Net architecture. These flows are then linearly combined at each time step to approximate the intermediate bi-directional optical flows. These approximate flows, however, only work well in locally smooth regions and produce artifacts around motion boundaries. To address this shortcoming, we employ another U-Net to refine the approximated flow and also predict soft visibility maps. Finally, the two input images are warped and linearly fused to form each intermediate frame. By applying the visibility maps to the warped images before fusion, we exclude the contribution of occluded pixels to the interpolated intermediate frame to avoid artifacts. Since none of our learned network parameters are time-dependent, our approach is able to produce as many intermediate frames as needed. To train our network, we use 1,132 240-fps video clips, containing 300K individual video frames. Experimental results on several datasets, predicting different numbers of interpolated frames, demonstrate that our approach performs consistently better than existing methods.

随着脑成像技术和机器学习工具的出现，很多努力都致力于构建计算模型来捕获人脑中的视觉信息的编码。最具挑战性的大脑解码任务之一是通过功能磁共振成像（FMRI）测量的脑活动的感知自然图像的精确重建。在这项工作中，我们调查了来自FMRI的自然图像重建的最新学习方法。我们在架构设计，基准数据集和评估指标方面检查这些方法，并在标准化评估指标上呈现公平的性能评估。最后，我们讨论了现有研究的优势和局限，并提出了潜在的未来方向。

We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for learning visual representations from scratch. At training time, our model learns a feature map representation to be useful for performing cycle-consistent tracking. At test time, we use the acquired representation to find nearest neighbors across space and time. We demonstrate the generalizability of the representation -without finetuning -across a range of visual correspondence tasks, including video object segmentation, keypoint tracking, and optical flow. Our approach outperforms previous self-supervised methods and performs competitively with strongly supervised methods. 1

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。

本文介绍了一个名为DTVNet的新型端到端动态时间流逝视频生成框架，以从归一化运动向量上的单个景观图像生成多样化的延期视频。所提出的DTVNET由两个子模块组成：\ EMPH {光学流编码器}（OFE）和\ EMPH {动态视频生成器}（DVG）。 OFE将一系列光学流程图映射到编码所生成视频的运动信息的\ Emph {归一化运动向量}。 DVG包含来自运动矢量和单个景观图像的运动和内容流。此外，它包含一个编码器，用于学习共享内容特征和解码器，以构造具有相应运动的视频帧。具体地，\ EMPH {运动流}介绍多个\ EMPH {自适应实例归一化}（Adain）层，以集成用于控制对象运动的多级运动信息。在测试阶段，基于仅一个输入图像，可以产生具有相同内容但具有相同运动信息但各种运动信息的视频。此外，我们提出了一个高分辨率的景区时间流逝视频数据集，命名为快速天空时间，以评估不同的方法，可以被视为高质量景观图像和视频生成任务的新基准。我们进一步对天空延时，海滩和快速天空数据集进行实验。结果证明了我们对最先进的方法产生高质量和各种动态视频的方法的优越性。

我们研究允许人类用户探索，编辑和有效传输视频的视频特有的AutoEncoders。事先工作独立地研究了这些问题（以及子问题）并提出了不同的配方。在这项工作中，我们在特定视频的多个帧上培训一个简单的autoencoder（从划痕）。我们观察到：（1）由视频特定的autoencoder捕获该视频的空间和时间特性学习的潜在代码;（2）AutoEncoders可以将采样外输入投影到视频特定的歧管上。这两个属性允许我们使用一个学习的表示探索，编辑和有效地传输视频。对于例如，潜在代码的线性操作允许用户可视化视频的内容。关联视频和歧管投影的潜在代码使用户能够做出所需的编辑。内插潜码和歧管投影允许通过网络传输稀疏的低res帧。

We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. This representation is decoded using single or multiple decoder LSTMs to perform different tasks, such as reconstructing the input sequence, or predicting the future sequence. We experiment with two kinds of input sequences -patches of image pixels and high-level representations ("percepts") of video frames extracted using a pretrained convolutional net. We explore different design choices such as whether the decoder LSTMs should condition on the generated output. We analyze the outputs of the model qualitatively to see how well the model can extrapolate the learned video representation into the future and into the past. We try to visualize and interpret the learned features. We stress test the model by running it on longer time scales and on out-of-domain data. We further evaluate the representations by finetuning them for a supervised learning problemhuman action recognition on the UCF-101 and HMDB-51 datasets. We show that the representations help improve classification accuracy, especially when there are only a few training examples. Even models pretrained on unrelated datasets (300 hours of YouTube videos) can help action recognition performance.

We propose a self-supervised spatiotemporal learning technique which leverages the chronological order of videos. Our method can learn the spatiotemporal representation of the video by predicting the order of shuffled clips from the video. The category of the video is not required, which gives our technique the potential to take advantage of infinite unannotated videos. There exist related works which use frames, while compared to frames, clips are more consistent with the video dynamics. Clips can help to reduce the uncertainty of orders and are more appropriate to learn a video representation. The 3D convolutional neural networks are utilized to extract features for clips, and these features are processed to predict the actual order. The learned representations are evaluated via nearest neighbor retrieval experiments. We also use the learned networks as the pre-trained models and finetune them on the action recognition task. Three types of 3D convolutional neural networks are tested in experiments, and we gain large improvements compared to existing self-supervised methods.

由于水下环境复杂，水下鱼类分割以估计鱼体测量值仍然无法解决。依靠完全监督的分割模型需要收集每个像素标签，这很耗时且容易过度拟合。自我监督的学习方法可以帮助避免大型注释的培训数据集的要求，但是，在现实世界中，它们应该达到良好的细分质量。在本文中，我们介绍了一种基于变压器的方法，该方法使用自学意义重大的鱼类分割。我们提出的模型对视频进行了培训 - 没有任何注释，可以在野外现场拍摄的水下视频中进行鱼类分割。我们表明，当对一个数据集的一系列水下视频进行培训时，该建议的模型超过了以前的基于CNN的基于CNN和基于变压器的自我监督方法，并在两个未见的水下视频数据集中相对接近具有监督方法的性能。这表明了我们的模型的概括性以及它不需要预培训模型的事实。此外，我们表明，由于其密集的表示学习，我们的模型是计算效率的。我们提供定量和定性的结果，以证明我们的模型的重要功能。