视频识别是由端到端学习范式主导的 - 首先初始化具有预审预周化图像模型的视频识别模型,然后对视频进行端到端培训。这使视频网络能够受益于验证的图像模型。但是,这需要大量的计算和内存资源,以便在视频上进行填充以及直接使用预审计的图像功能的替代方案,而无需填充图像骨架会导致结果不足。幸运的是,在对比视力语言预训练(剪辑)方面的最新进展为视觉识别任务的新途径铺平了道路。这些模型在大型开放式图像文本对数据上进行了预测,以丰富的语义学习强大的视觉表示。在本文中,我们介绍了有效的视频学习(EVL) - 一种有效的框架,用于直接训练具有冷冻剪辑功能的高质量视频识别模型。具体来说,我们采用轻型变压器解码器并学习查询令牌,从剪辑图像编码器中动态收集帧级空间特征。此外,我们在每个解码器层中采用局部时间模块,以发现相邻帧及其注意力图的时间线索。我们表明,尽管有效地使用冷冻的骨干训练,但我们的模型在各种视频识别数据集上学习了高质量的视频表示。代码可在https://github.com/opengvlab/feld-video-rencognition上找到。
translated by 谷歌翻译
The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on image-level pretraining and adpation, which are limited for dynamic and complex video-level understanding tasks. To fill the gap, we present general video foundation models, InternVideo, by taking advantage of both generative and discriminative self-supervised video learning. Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications. Without bells and whistles, InternVideo achieves state-of-the-art performance on 39 video datasets from extensive tasks including video action recognition/detection, video-language alignment, and open-world video applications. Especially, our methods can obtain 91.1% and 77.2% top-1 accuracy on the challenging Kinetics-400 and Something-Something V2 benchmarks, respectively. All of these results effectively show the generality of our InternVideo for video understanding. The code will be released at https://github.com/OpenGVLab/InternVideo .
translated by 谷歌翻译
最近出现了有希望的表现,利用大型预训练的模型来实现各种感兴趣的下游任务。由于模型的规模不断增长,因此,在模型培训和存储方面,基于标准的完整任务适应策略的成本高昂。这导致了参数有效传输学习的新研究方向。但是,现有的尝试通常集中在预训练模型的相同模式(例如图像理解)的下游任务上。这会产生限制,因为在某些特定的方式(例如,视频理解)中,具有足够知识的强大预训练模型较少或不可用。在这项工作中,我们研究了这样一种新型的跨模式转移学习设置,即参数有效的图像到视频传输学习。为了解决此问题,我们为每个视频任务提出了一个新的时空适配器(ST-ADAPTER),以进行参数有效调整。凭借紧凑设计中的内置时空推理能力,ST-ADAPTER可以实现预训练的图像模型,而无需时间知识,以小(〜8%)的每任务参数成本来理解动态视频内容,以大约需要与以前的工作相比,更新参数少20倍。在视频动作识别任务上进行的广泛实验表明,我们的ST-ADAPTER可以匹配甚至优于强大的完整微调策略和最先进的视频模型,同时享受参数效率的优势。
translated by 谷歌翻译
对比性语言图像预测在学习网络尺度数据的视觉文本联合表示方面取得了巨大的成功,这表明了各种图像任务的显着“零射”概括能力。但是,如何有效地将这种新的语言图像预处理方法扩展到视频域仍然是一个开放的问题。在这项工作中,我们提出了一种简单而有效的方法,该方法将预验证的语言图像模型直接适应视频识别,而不是从头开始预处理新模型。更具体地说,为了捕获沿时间维度框架的远距离依赖性,我们提出了一种跨框架注意机制,该机制明确地跨帧交换信息。这样的模块是轻量级的,可以无缝地插入验证的语言图像模型中。此外,我们提出了一个特定于视频的提示方案,该方案利用视频内容信息生成歧视性文本提示。广泛的实验表明,我们的方法是有效的,可以推广到不同的视频识别方案。特别是,在完全监督的设置下,我们的方法在Kinectics-400上获得了最高1的精度为87.1%,而与SWIN-L和Vivit-H相比,使用量少12倍。在零拍摄的实验中,我们的方法超过了当前的最新方法 +7.6%和 +14.9%,而在两个流行协议下,TOP-1的准确性。在少数拍摄的情况下,当标记的数据非常有限时,我们的方法优于先前的最佳方法 +32.1%和 +23.1%。代码和型号可在https://aka.ms/x-clip上找到
translated by 谷歌翻译
通常需要在大型数据集上进行预训练的视频变压器,以在相对较小的数据集上实现首要性能。在本文中,我们表明视频蒙面的自动编码器(Videomae)是用于自我监督视频预训练(SSVP)的数据效率学习者。我们的启发受到了最近的ImageMae的启发,并提出了具有极高比例的定制视频管掩蔽。这种简单的设计使视频重建成为更具挑战性的自我判断任务,从而鼓励在此预训练过程中提取更有效的视频表示。我们在SSVP上获得了三个重要发现:(1)屏蔽比的比例极高(即90%至95%)仍然可以产生良好的视频性能。在时间上冗余的视频内容比图像更高的掩蔽率。 (2)视频在很小的数据集(即3K-4K视频)上取得了令人印象深刻的结果,而无需使用任何额外的数据。 (3)视频表明,数据质量比SSVP的数据数量更重要。在培训和目标数据集之间的域转移是一个重要问题。值得注意的是,我们与香草VIT的视频在动力学400上可以达到85.8%,在不使用任何额外数据的情况下,在HMDB51上的V2上有75.3%,UCF101的某些东西为75.3%,在UCF101上获得90.8%,HMDB51上的90.8%和61.1%。代码可从https://github.com/mcg-nju/videomae获得。
translated by 谷歌翻译
We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of framelevel patches. Our experimental study compares different self-attention schemes and suggests that "divided attention," where temporal attention and spatial attention are separately applied within each block, leads to the best video classification accuracy among the design choices considered. Despite the radically new design, TimeSformer achieves state-of-the-art results on several action recognition benchmarks, including the best reported accuracy on Kinetics-400 and Kinetics-600. Finally, compared to 3D convolutional networks, our model is faster to train, it can achieve dramatically higher test efficiency (at a small drop in accuracy), and it can also be applied to much longer video clips (over one minute long). Code and models are available at: https://github.com/ facebookresearch/TimeSformer.
translated by 谷歌翻译
我们呈现了基于纯变压器的视频分类模型,在图像分类中最近的近期成功进行了借鉴。我们的模型从输入视频中提取了时空令牌,然后由一系列变压器层编码。为了处理视频中遇到的令牌的长序列,我们提出了我们模型的几种有效的变体,它们将输入的空间和时间维构建。虽然已知基于变换器的模型只有在可用的大型训练数据集时才有效,但我们展示了我们如何在训练期间有效地规范模型,并利用预先训练的图像模型能够在相对小的数据集上训练。我们进行彻底的消融研究,并在包括动力学400和600,史诗厨房,东西的多个视频分类基准上实现最先进的结果,其中 - 基于深度3D卷积网络的现有方法表现出优先的方法。为了促进进一步的研究,我们在https://github.com/google-research/scenic/tree/main/scenic/projects/vivit发布代码
translated by 谷歌翻译
本文研究了视频变压器的BERT预借鉴。考虑到近期图像变形金刚的伯爵预借鉴成功,这是一个简单但值得学习的延伸。我们介绍了Decouples将视频表示学习学习的BEVT进入空间代表学习和时间动态学习。特别地,BEVT首先在图像数据上执行屏蔽图像建模,然后在视频数据上与屏蔽视频建模联合进行屏蔽图像建模。这种设计具有两个观察的动机:1)在图像数据集上学习的变压器提供了体面的空间前沿,可以缓解视频变压器的学习,这通常是从划痕训练的计算密集型的时间。 2)鉴别的线索,即空间和时间信息,需要在不同的视频中进行正确的预测,由于阶级的阶级和阶级际变化而不同。我们对三个具有挑战性的视频基准进行了广泛的实验,其中BEVT达到了非常有前途的结果。在动力学400上,哪些识别主要依赖于歧视性空间表示,BEVT达到了强大的监督基线的可比结果。在某种东西 - V2和潜水48上,其中包含依靠时间动态的视频,BEVT优于所有替代基准,分别实现了70.6%和86.7%的最新性能。
translated by 谷歌翻译
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。
translated by 谷歌翻译
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.
translated by 谷歌翻译
We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10× more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https: //github.com/facebookresearch/SlowFast.
translated by 谷歌翻译
This work explores an efficient approach to establish a foundational video-text model for tasks including open-vocabulary video classification, text-to-video retrieval, video captioning and video question-answering. We present VideoCoCa that reuses a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules (for example, cross-frame attention layer or perceiver resampler) and finetune the modified architecture on video-text data, we surprisingly find that the generative attentional pooling and contrastive attentional pooling layers in the image-text CoCa design are instantly adaptable to ``flattened frame embeddings'', yielding a strong zero-shot transfer baseline for many video-text tasks. Specifically, the frozen image encoder of a pretrained image-text CoCa takes each video frame as inputs and generates \(N\) token embeddings per frame for totally \(T\) video frames. We flatten \(N \times T\) token embeddings as a long sequence of frozen video representation and apply CoCa's generative attentional pooling and contrastive attentional pooling on top. All model weights including pooling layers are directly loaded from an image-text CoCa pretrained model. Without any video or video-text data, VideoCoCa's zero-shot transfer baseline already achieves state-of-the-art results on zero-shot video classification on Kinetics 400/600/700, UCF101, HMDB51, and Charades, as well as zero-shot text-to-video retrieval on MSR-VTT and ActivityNet Captions. We also explore lightweight finetuning on top of VideoCoCa, and achieve strong results on video question-answering (iVQA, MSRVTT-QA, MSVD-QA) and video captioning (MSR-VTT, ActivityNet, Youcook2). Our approach establishes a simple and effective video-text baseline for future research.
translated by 谷歌翻译
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.
translated by 谷歌翻译
视频理解需要在多种时空分辨率下推理 - 从短的细粒度动作到更长的持续时间。虽然变压器架构最近提出了最先进的,但它们没有明确建模不同的时空分辨率。为此,我们为视频识别(MTV)提供了多视图变压器。我们的模型由单独的编码器组成,表示输入视频的不同视图,以横向连接,以跨视图熔断信息。我们对我们的模型提供了彻底的消融研究,并表明MTV在一系列模型尺寸范围内的准确性和计算成本方面始终如一地表现优于单视对应力。此外,我们在五个标准数据集上实现最先进的结果,并通过大规模预制来进一步提高。我们将释放代码和备用检查点。
translated by 谷歌翻译
我们呈现蒙版特征预测(MaskFeat),用于自我监督的视频模型的预训练。我们的方法首先随机地掩盖输入序列的一部分,然后预测蒙面区域的特征。我们研究五种不同类型的功能,找到面向导向渐变(HOG)的直方图,手工制作的特征描述符,在性能和效率方面尤其良好。我们观察到猪中的局部对比标准化对于良好的结果至关重要,这与使用HOG进行视觉识别的早期工作符合。我们的方法可以学习丰富的视觉知识和基于大规模的变压器的模型。在不使用额外的模型重量或监督的情况下,在未标记视频上预先培训的MaskFeat在动力学-400上使用MVIT-L达到86.7%的前所未有的结果,在动力学-600,88.3%上,88.3%,在动力学-700,88.8地图上SSV2上的75.0%。 MaskFeat进一步推广到图像输入,其可以被解释为具有单个帧的视频,并在想象中获得竞争结果。
translated by 谷歌翻译
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。
translated by 谷歌翻译
探索大规模预处理的基础模型对计算机视觉具有重大兴趣,因为这些模型可以快速转移到许多下游任务中。本文介绍了对比字幕(COCA),这是一种极简主义的设计,旨在为图像文本编码器编码器基础模型预算与对比度损失和字幕损失,从而从剪辑和诸如simvlm之类的生成方法之类的对比方法中包含模型能力。与所有解码器层都参与编码器输出的标准编码器 - 模块变压器相反,可口可乐省略了解码器层的上半部分的交叉注意,以编码单峰文本表示,并串联到剩余的解码器层,这些解码器与图像编码器相交的解码器层多模式图像文本表示。除了对多模态解码器输出的字幕损失外,我们还应用了单峰图像和文本嵌入之间的对比损失,该输出可以预测文本令牌自动加压。通过共享相同的计算图,可以用最小的开销有效地计算两个培训目标。可口可乐是端到端和从头开始的网络尺度alt-text数据和带注释的图像,通过将所有标签视为文本,无缝地统一自然语言监督以进行表示。从经验上讲,可口可乐通过零拍传输或在广泛的下游任务上进行零摄像转移或最少的特定任务适应,跨越视觉识别(Imagenet,Kinetics-400/600/700,瞬间, ),交叉模式检索(MSCOCO,FLICKR30K,MSR-VTT),多模式理解(VQA,SNLI-VE,NLVR2)和图像字幕(MSCOCO,NOCAPS)。值得注意的是,在Imagenet分类方面,COCA获得了86.3%的TOP-1准确性,带有冷冻编码器和学习的分类头90.6%,以及带有填充编码器的Imagenet上的新最先进的91.0%Top-1 Top-1精度。
translated by 谷歌翻译
The last several years have witnessed remarkable progress in video-and-language (VidL) understanding. However, most modern VidL approaches use complex and specialized model architectures and sophisticated pretraining protocols, making the reproducibility, analysis and comparisons of these frameworks difficult. Hence, instead of proposing yet another new VidL model, this paper conducts a thorough empirical study demystifying the most important factors in the VidL model design. Among the factors that we investigate are (i) the spatiotemporal architecture design, (ii) the multimodal fusion schemes, (iii) the pretraining objectives, (iv) the choice of pretraining data, (v) pretraining and finetuning protocols, and (vi) dataset and model scaling. Our empirical study reveals that the most important design factors include: temporal modeling, video-to-text multimodal fusion, masked modeling objectives, and joint training on images and videos. Using these empirical insights, we then develop a step-by-step recipe, dubbed VindLU, for effective VidL pretraining. Our final model trained using our recipe achieves comparable or better than state-of-the-art results on several VidL tasks without relying on external CLIP pretraining. In particular, on the text-to-video retrieval task, our approach obtains 61.2% on DiDeMo, and 55.0% on ActivityNet, outperforming current SOTA by 7.8% and 6.1% respectively. Furthermore, our model also obtains state-of-the-art video question-answering results on ActivityNet-QA, MSRVTT-QA, MSRVTT-MC and TVQA. Our code and pretrained models are publicly available at: https://github.com/klauscc/VindLU.
translated by 谷歌翻译
We present a simple approach which can turn a ViT encoder into an efficient video model, which can seamlessly work with both image and video inputs. By sparsely sampling the inputs, the model is able to do training and inference from both inputs. The model is easily scalable and can be adapted to large-scale pre-trained ViTs without requiring full finetuning. The model achieves SOTA results and the code will be open-sourced.
translated by 谷歌翻译
从任务不足的预训练的深层模型中转移知识以进行下游任务是计算机视觉研究中的一个重要主题。随着计算能力的增长,我们现在拥有大规模的模型体系结构和数据量的开源视觉语言预培训模型。在这项研究中,我们专注于转移视力分类任务的知识。传统方法随机初始化线性分类器头进行视觉分类,但是它们将文本编码器的用法留为未发现的下游视觉识别任务。在本文中,我们修改了线性分类器的角色,并用对象类别的嵌入式语言表示替换分类器。这些语言表示是从视觉语言预训练模型的文本编码器初始化的,以进一步利用其良好的语言模型参数。实证研究表明,我们的方法提高了视频分类的性能和训练速度,模型的变化微不足道。特别是,我们的范式在动力学400上实现了87.3%的最新准确性。
translated by 谷歌翻译