Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation attention mechanism is proposed to reduce the complexity of standard Transformers. Then, a full autoregressive model, a partial autoregressive model and a non-autoregressive model are developed based on the new efficient Transformer. The partial autoregressive model has a similar performance with the full autoregressive model but a faster inference speed. The non-autoregressive model not only achieves a faster inference speed but also mitigates the quality degradation problem of the autoregressive counterparts, but it requires additional parameters and loss function for learning. Given the same attention mechanism, we conducted a comprehensive study to compare the proposed three video prediction variants. Experiments show that the proposed video prediction models are competitive with more complex state-of-the-art convolutional-LSTM based models. The source code is available at https://github.com/XiYe20/VPTR.

Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities (e.g., images, videos, text and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. We then cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering, visual reasoning, and visual grounding), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution, image enhancement, and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works. We hope this effort will ignite further interest in the community to solve current challenges towards the application of transformer models in computer vision.

视觉变压器正在成为解决计算机视觉问题的强大工具。最近的技术还证明了超出图像域之外的变压器来解决许多与视频相关的任务的功效。其中，由于其广泛的应用，人类的行动识别是从研究界受到特别关注。本文提供了对动作识别的视觉变压器技术的首次全面调查。我们朝着这个方向分析并总结了现有文献和新兴文献，同时突出了适应变形金刚以进行动作识别的流行趋势。由于其专业应用，我们将这些方法统称为``动作变压器''。我们的文献综述根据其架构，方式和预期目标为动作变压器提供了适当的分类法。在动作变压器的背景下，我们探讨了编码时空数据，降低维度降低，框架贴片和时空立方体构造以及各种表示方法的技术。我们还研究了变压器层中时空注意的优化，以处理更长的序列，通常通过减少单个注意操作中的令牌数量。此外，我们还研究了不同的网络学习策略，例如自我监督和零局学习，以及它们对基于变压器的行动识别的相关损失。这项调查还总结了在具有动作变压器重要基准的评估度量评分方面取得的进步。最后，它提供了有关该研究方向的挑战，前景和未来途径的讨论。

The mainstream of the existing approaches for video prediction builds up their models based on a Single-In-Single-Out (SISO) architecture, which takes the current frame as input to predict the next frame in a recursive manner. This way often leads to severe performance degradation when they try to extrapolate a longer period of future, thus limiting the practical use of the prediction model. Alternatively, a Multi-In-Multi-Out (MIMO) architecture that outputs all the future frames at one shot naturally breaks the recursive manner and therefore prevents error accumulation. However, only a few MIMO models for video prediction are proposed and they only achieve inferior performance due to the date. The real strength of the MIMO model in this area is not well noticed and is largely under-explored. Motivated by that, we conduct a comprehensive investigation in this paper to thoroughly exploit how far a simple MIMO architecture can go. Surprisingly, our empirical studies reveal that a simple MIMO model can outperform the state-of-the-art work with a large margin much more than expected, especially in dealing with longterm error accumulation. After exploring a number of ways and designs, we propose a new MIMO architecture based on extending the pure Transformer with local spatio-temporal blocks and a new multi-output decoder, namely MIMO-VP, to establish a new standard in video prediction. We evaluate our model in four highly competitive benchmarks (Moving MNIST, Human3.6M, Weather, KITTI). Extensive experiments show that our model wins 1st place on all the benchmarks with remarkable performance gains and surpasses the best SISO model in all aspects including efficiency, quantity, and quality. We believe our model can serve as a new baseline to facilitate the future research of video prediction tasks. The code will be released.

Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced with the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey we analyze main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled as input-level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and capture long-term temporal dynamics. In addition we provide an overview of different training regimes and explore effective self-supervised learning strategies for video. Finally, we conduct a performance comparison on the most common benchmark for Video Transformers (i.e., action classification), finding them to outperform 3D ConvNets even with less computational complexity.

变压器是一种基于关注的编码器解码器架构，彻底改变了自然语言处理领域。灵感来自这一重大成就，最近在将变形式架构调整到计算机视觉（CV）领域的一些开创性作品，这已经证明了他们对各种简历任务的有效性。依靠竞争力的建模能力，与现代卷积神经网络相比在本文中，我们已经为三百不同的视觉变压器进行了全面的审查，用于三个基本的CV任务（分类，检测和分割），提出了根据其动机，结构和使用情况组织这些方法的分类。 。由于培训设置和面向任务的差异，我们还在不同的配置上进行了评估了这些方法，以便于易于和直观的比较而不是各种基准。此外，我们已经揭示了一系列必不可少的，但可能使变压器能够从众多架构中脱颖而出，例如松弛的高级语义嵌入，以弥合视觉和顺序变压器之间的差距。最后，提出了三个未来的未来研究方向进行进一步投资。

用于深度卷积神经网络的视频插值的现有方法，因此遭受其内在限制，例如内部局限性核心权重和受限制的接收领域。为了解决这些问题，我们提出了一种基于变换器的视频插值框架，允许内容感知聚合权重，并考虑具有自我关注操作的远程依赖性。为避免全球自我关注的高计算成本，我们将当地注意的概念引入视频插值并将其扩展到空间域。此外，我们提出了一个节省时间的分离策略，以节省内存使用，这也提高了性能。此外，我们开发了一种多尺度帧合成方案，以充分实现变压器的潜力。广泛的实验证明了所提出的模型对最先进的方法来说，定量和定性地在各种基准数据集上进行定量和定性。

基于变压器的方法最近在基于2D图像的视力任务上取得了巨大进步。但是，对于基于3D视频的任务，例如动作识别，直接将时空变压器应用于视频数据将带来沉重的计算和记忆负担，因为斑块的数量大大增加以及自我注意计算的二次复杂性。如何对视频数据的3D自我注意力进行有效地建模，这对于变压器来说是一个巨大的挑战。在本文中，我们提出了一种时间贴片移动（TPS）方法，用于在变压器中有效的3D自发明建模，以进行基于视频的动作识别。 TPS在时间尺寸中以特定的镶嵌图模式移动斑块的一部分，从而将香草的空间自我发项操作转换为时空的一部分，几乎没有额外的成本。结果，我们可以使用几乎相同的计算和记忆成本来计算3D自我注意力。 TPS是一个插件模块，可以插入现有的2D变压器模型中，以增强时空特征学习。提出的方法可以通过最先进的V1和V1，潜水-48和Kinetics400实现竞争性能，同时在计算和内存成本方面效率更高。 TPS的源代码可在https://github.com/martinxm/tps上找到。

从CNN，RNN到VIT，我们见证了视频预测中的显着进步，结合了辅助输入，精心设计的神经体系结构和复杂的培训策略。我们钦佩这些进步，但对必要性感到困惑：是否有一种可以表现得很好的简单方法？本文提出了SIMVP，这是一个简单的视频预测模型，完全建立在CNN上，并以端到端的方式受到MSE损失的训练。在不引入任何其他技巧和复杂策略的情况下，我们可以在五个基准数据集上实现最先进的性能。通过扩展实验，我们证明了SIMVP在现实世界数据集上具有强大的概括和可扩展性。培训成本的显着降低使扩展到复杂方案变得更加容易。我们认为SIMVP可以作为刺激视频预测进一步发展的坚实基线。该代码可在\ href {https://github.com/gaozhangyang/simvp-simpler-yet-better-video-prediction} {github}中获得。

speed among all existing VIS models, and achieves the best result among methods using single model on the YouTube-VIS dataset. For the first time, we demonstrate a much simpler and faster video instance segmentation framework built upon Transformers, achieving competitive accuracy. We hope that VisTR can motivate future research for more video understanding tasks.

时尚预测学习是给定一系列历史框架的未来框架。传统算法主要基于经常性的神经网络（RNN）。然而，由于经常性结构的序列性，RNN遭受了重大计算负担，例如由于经常性结构的序列性而达到时间和长的背部传播过程。最近，还以编码器 - 解码器或普通编码器的形式研究了基于变压器的方法，但是编码器 - 解码器形式需要过于深的网络，并且普通编码器缺乏短期依赖性。为了解决这些问题，我们提出了一种名为3D时间卷积变压器（TCTN）的算法，其中采用具有时间卷积层的基于变压器的编码器来捕获短期和长期依赖性。由于变压器的并行机理，我们所提出的算法与基于RNN的方法相比，易于实施和培训得多。为了验证我们的算法，我们对移动和kth数据集进行实验，并表明TCTN在性能和训练速度下表现出最先进的（SOTA）方法。

Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, the first end-to-end video object detection system based on spatial-temporal Transformer architectures. The first goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow model, relation networks. Besides, benefited from the object query design in DETR, our method does not need complicated post-processing methods such as Seq-NMS. In particular, we present a temporal Transformer to aggregate both the spatial object queries and the feature memories of each frame. Our temporal transformer consists of two components: Temporal Query Encoder (TQE) to fuse object queries, and Temporal Deformable Transformer Decoder (TDTD) to obtain current frame detection results. These designs boost the strong baseline deformable DETR by a significant margin (2 %-4 % mAP) on the ImageNet VID dataset. TransVOD yields comparable performances on the benchmark of ImageNet VID. Then, we present two improved versions of TransVOD including TransVOD++ and TransVOD Lite. The former fuses object-level information into object query via dynamic convolution while the latter models the entire video clips as the output to speed up the inference time. We give detailed analysis of all three models in the experiment part. In particular, our proposed TransVOD++ sets a new state-of-the-art record in terms of accuracy on ImageNet VID with 90.0 % mAP. Our proposed TransVOD Lite also achieves the best speed and accuracy trade-off with 83.7 % mAP while running at around 30 FPS on a single V100 GPU device. Code and models will be available for further research.

在这项工作中，我们呈现SEQFormer，这是一个令人沮丧的视频实例分段模型。 SEQFormer遵循Vision变换器的原理，该方法模型视频帧之间的实例关系。然而，我们观察到一个独立的实例查询足以捕获视频中的时间序列，但应该独立地使用每个帧进行注意力机制。为此，SEQFormer在每个帧中定位一个实例，并聚合时间信息以学习视频级实例的强大表示，其用于动态地预测每个帧上的掩模序列。实例跟踪自然地实现而不进行跟踪分支或后处理。在YouTube-VIS数据集上，SEQFormer使用Reset-50个骨干和49.0 AP实现47.4个AP，其中Reset-101骨干，没有响铃和吹口哨。此类成果分别显着超过了以前的最先进的性能4.6和4.4。此外，与最近提出的Swin变压器集成，SEQFormer可以实现59.3的高得多。我们希望SEQFormer可能是一个强大的基线，促进了视频实例分段中的未来研究，同时使用更强大，准确，整洁的模型来实现该字段。代码和预先训练的型号在https://github.com/wjf5203/seqformer上公开使用。

最近，变形金刚在空间范围内的学习和推断方面很受欢迎。但是，他们的性能依赖于存储并将注意力应用于视频中每个帧的功能张量。因此，随着视频的长度的增长，它们的空间和时间复杂性会线性增加，这对于长视频而言可能非常昂贵。我们提出了一种新颖的视觉记忆网络架构，用于空间范围的学习和推理问题。我们在内存网络中维护了固定的内存插槽，并提出了基于Gumbel-SoftMax的算法，以学习一种自适应策略以更新此内存。最后，该体系结构在视频对象细分（VOS）和视频预测问题上进行了基准测试。我们证明，我们的内存体系结构可实现最新的结果，在视频预测上优于基于变压器的方法和其他最新方法，同时保持恒定的内存能力与序列长度无关。

Autonomous systems not only need to understand their current environment, but should also be able to predict future actions conditioned on past states, for instance based on captured camera frames. However, existing models mainly focus on forecasting future video frames for short time-horizons, hence being of limited use for long-term action planning. We propose Multi-Scale Hierarchical Prediction (MSPred), a novel video prediction model able to simultaneously forecast future possible outcomes of different levels of granularity at different spatio-temporal scales. By combining spatial and temporal downsampling, MSPred efficiently predicts abstract representations such as human poses or locations over long time horizons, while still maintaining a competitive performance for video frame prediction. In our experiments, we demonstrate that MSPred accurately predicts future video frames as well as high-level representations (e.g. keypoints or semantics) on bin-picking and action recognition datasets, while consistently outperforming popular approaches for future frame prediction. Furthermore, we ablate different modules and design choices in MSPred, experimentally validating that combining features of different spatial and temporal granularity leads to a superior performance. Code and models to reproduce our experiments can be found in https://github.com/AIS-Bonn/MSPred.

创建视频是为了表达情感，交换信息和分享经验。视频合成很长时间以来一直吸引了研究人员。尽管视觉合成的进步驱动了迅速的进展，但大多数现有研究都集中在提高框架的质量和之间的过渡上，而在生成更长的视频方面几乎没有取得进展。在本文中，我们提出了一种基于3D-VQGAN和Transformers的方法，以生成具有数千帧的视频。我们的评估表明，我们的模型在16架视频剪辑中培训了来自UCF-101，Sky TimeLapse和Taichi-HD数据集等标准基准测试片段，可以生成多样化，连贯和高质量的长视频。我们还展示了我们通过将时间信息与文本和音频结合在一起来生成有意义的长视频的方法的条件扩展。可以在https://songweige.github.io/projects/tats/index.html上找到视频和代码。

最近，与常规像素的隐性表示相比，视频的图像隐式神经表示，其有希望的结果和迅速的速度因其有希望的结果和迅速的速度而受欢迎。但是，网络结构内的冗余参数在扩大理想性能时会导致大型模型大小。这种现象的关键原因是神经的耦合公式，该公式直接从框架索引输入中输出视频帧的空间和时间信息。在本文中，我们提出了E-NERV，它通过将图像的隐式神经代表分解为单独的空间和时间上下文来显着加快神经的速度。在这种新公式的指导下，我们的模型大大降低了冗余模型参数，同时保留表示能力。我们从实验上发现，我们的方法可以通过更少的参数改善性能，从而使收敛的速度更快地提高了$ 8 \ times $。代码可在https://github.com/kyleleey/e-nerv上找到。

变压器最近展示了改进视觉跟踪算法的明显潜力。尽管如此，基于变压器的跟踪器主要使用变压器熔断并增强由卷积神经网络（CNNS）产生的功能。相比之下，在本文中，我们提出了一个完全基于注意力的变压器跟踪算法，Swin-Cranstormer Tracker（SwintRack）。 SwintRack使用变压器进行特征提取和特征融合，允许目标对象和搜索区域之间的完全交互进行跟踪。为了进一步提高性能，我们调查了全面的不同策略，用于特征融合，位置编码和培训损失。所有这些努力都使SwintRack成为一个简单但坚实的基线。在我们的彻底实验中，SwintRack在leasot上设置了一个新的记录，在4.6 \％的情况下超过4.6 \％，同时仍然以45 fps运行。此外，它达到了最先进的表演，0.483 Suc，0.832 Suc和0.694 Ao，其他具有挑战性的leasot _ {ext} $，trackingnet和got-10k。我们的实施和培训型号可在HTTPS://github.com/litinglin/swintrack获得。

我们提出了块茎：一种简单的时空视频动作检测解决方案。与依赖于离线演员检测器或手工设计的演员位置假设的现有方法不同，我们建议通过同时执行动作定位和识别从单个表示来直接检测视频中的动作微管。块茎学习一组管芯查询，并利用微调模块来模拟视频剪辑的动态时空性质，其有效地加强了与在时空空间中的演员位置假设相比的模型容量。对于包含过渡状态或场景变更的视频，我们提出了一种上下文意识的分类头来利用短期和长期上下文来加强行动分类，以及用于检测精确的时间动作程度的动作开关回归头。块茎直接产生具有可变长度的动作管，甚至对长视频剪辑保持良好的结果。块茎在常用的动作检测数据集AVA，UCF101-24和JHMDB51-21上优于先前的最先进。

尽管来自视频的3D人类姿势估算的巨大进展，但是充分利用冗余2D姿势序列来学习用于生成一个3D姿势的代表表示的开放问题。为此，我们提出了一种改进的基于变压器的架构，称为冲压变压器，简单地有效地将长期的2D联合位置升高到单个3D姿势。具体地，采用Vanilla变压器编码器（VTE）来模拟2D姿势序列的远程依赖性。为了减少序列的冗余，vte的前馈网络中的完全连接的层被冲击卷积替换，以逐步缩小序列长度并从本地上下文聚合信息。修改的VTE称为STRIVEIVERCHER ENCODER（STE），其构建在VTE的输出时。 STE不仅有效地将远程信息聚集到分层全球和本地时尚的单载体表示，而且显着降低了计算成本。此外，全序列和单个目标帧尺度都设计了全序，分别适用于VTE和ST的输出。该方案与单个目标帧监督结合施加额外的时间平滑度约束，因此有助于产生更平滑和更准确的3D姿势。所提出的轮廓变压器在两个具有挑战性的基准数据集，Human3.6M和HumanVa-I中进行评估，并通过更少的参数实现最先进的结果。代码和模型可用于\ url {https://github.com/vegetebird/stridedtransformer-pose3d}。