利用在大规模图像文本对中预先训练的视觉和语言模型（VLM）成为开放式视觉识别的有希望的范式。在这项工作中，我们通过利用视频中自然存在的运动和音频来扩展这种范式。我们提出\ textbf {mov}，这是\ textbf {m} ult-imodal \ textbf {o} pen- \ textbf {v} ocabulary视频分类的简单而有效的方法。在MOV中，我们直接使用具有最小修改的预训练VLM的视觉编码器来编码视频，光流和音频频谱图。我们设计一种跨模式融合机制来汇总免费的多模式信息。 Kinetics-700和VGGSOUND的实验表明，引入流量或音频模态会带来预先训练的VLM和现有方法的大量性能增长。具体而言，MOV极大地提高了基础类别的准确性，而在新颖的课程上则更好地概括了。 MOV在UCF和HMDB零摄像视频分类基准上实现了最新结果，从而极大地超过了基于VLMS的传统零摄像方法和最新方法。代码和模型将发布。

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain. In this pursuit, new parametric modules are added to learn temporal information and inter-frame relationships which require meticulous design efforts. Furthermore, when the resulting models are learned on videos, they tend to overfit on the given task distribution and lack in generalization aspect. This begs the following question: How to effectively transfer image-level CLIP representations to videos? In this work, we show that a simple Video Fine-tuned CLIP (ViFi-CLIP) baseline is generally sufficient to bridge the domain gap from images to videos. Our qualitative analysis illustrates that the frame-level processing from CLIP image-encoder followed by feature pooling and similarity matching with corresponding text embeddings helps in implicitly modeling the temporal cues within ViFi-CLIP. Such fine-tuning helps the model to focus on scene dynamics, moving objects and inter-object relationships. For low-data regimes where full fine-tuning is not viable, we propose a `bridge and prompt' approach that first uses fine-tuning to bridge the domain gap and then learns prompts on language and vision side to adapt CLIP representations. We extensively evaluate this simple yet strong baseline on zero-shot, base-to-novel generalization, few-shot and fully supervised settings across five video benchmarks. Our code is available at https://github.com/muzairkhattak/ViFi-CLIP.

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。

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。

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

Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-attention, our model forces information between different modalities to pass through a small number of bottleneck latents, requiring the model to collate and condense the most relevant information in each modality and only share what is necessary. We find that such a strategy improves fusion performance, at the same time reducing computational cost. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks including Audioset, Epic-Kitchens and VGGSound. All code and models will be released.

现有的时间动作检测（TAD）方法依赖于大型培训数据，包括细分级注释，仅限于在推理期间单独识别先前看到的课程。为每类兴趣收集和注释一个大型培训集是昂贵的，因此无法计算。零射TAD（ZS-TAD）通过启用预训练的模型来识别任何看不见的动作类别来解决这一障碍。同时，ZS-TAD的调查大大降低，ZS-Tad也更具挑战性。受零摄像图像分类的成功的启发，我们旨在解决更复杂的TAD任务。一种直观的方法是将现成的建议探测器与剪辑样式分类集成。但是，由于顺序定位（例如，提案生成）和分类设计，它很容易进行定位误差传播。为了克服这个问题，在本文中，我们通过视觉提示（陈旧）提出了一种新型的零射击时间动作检测模型。这种新颖的设计通过破坏介于两者之间的错误传播途径来有效地消除了定位和分类之间的依赖性。我们进一步介绍了分类和定位之间的相互作用机制，以改善优化。对标准ZS-TAD视频基准测试的广泛实验表明，我们的陈旧的表现明显优于最先进的替代方案。此外，我们的模型还与最近的强大竞争对手相比，在受到监督的TAD上还能产生卓越的成果。 Stale的Pytorch实现可从https://github.com/sauradip/stale获得。

Vision-language models (VLMs) that are pre-trained on large-scale image-text pairs have demonstrated impressive transferability on a wide range of visual tasks. Transferring knowledge from such powerful pre-trained VLMs is emerging as a promising direction for building effective video recognition models. However, the current exploration is still limited. In our opinion, the greatest charm of pre-trained vision-language models is to build a bridge between visual and textual domains. In this paper, we present a novel framework called BIKE which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We propose a Video Attribute Association mechanism which leverages the Video-to-Text knowledge to generate textual auxiliary attributes to complement video recognition. ii) We also present a Temporal Concept Spotting mechanism which uses the Text-to-Video expertise to capture temporal saliency in a parameter-free manner to yield enhanced video representation. The extensive studies on popular video datasets (ie, Kinetics-400 & 600, UCF-101, HMDB-51 and ActivityNet) show that our method achieves state-of-the-art performance in most recognition scenarios, eg, general, zero-shot, and few-shot video recognition. To the best of our knowledge, our best model achieves a state-of-the-art accuracy of 88.4% on challenging Kinetics-400 with the released CLIP pre-trained model.

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/.

We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-text embedding learned contrastively with these additional auto-generated narrations outperforms the previous state-of-the-art on multiple first-person and third-person video tasks, both in zero-shot and finetuned setups. Most notably, LaViLa obtains an absolute gain of 10.1% on EGTEA classification and 5.9% Epic-Kitchens-100 multi-instance retrieval benchmarks. Furthermore, LaViLa trained with only half the narrations from the Ego4D dataset outperforms baseline models trained on the full set, and shows positive scaling behavior on increasing pre-training data and model size.

Few-shot (FS) and zero-shot (ZS) learning are two different approaches for scaling temporal action detection (TAD) to new classes. The former adapts a pretrained vision model to a new task represented by as few as a single video per class, whilst the latter requires no training examples by exploiting a semantic description of the new class. In this work, we introduce a new multi-modality few-shot (MMFS) TAD problem, which can be considered as a marriage of FS-TAD and ZS-TAD by leveraging few-shot support videos and new class names jointly. To tackle this problem, we further introduce a novel MUlti-modality PromPt mETa-learning (MUPPET) method. This is enabled by efficiently bridging pretrained vision and language models whilst maximally reusing already learned capacity. Concretely, we construct multi-modal prompts by mapping support videos into the textual token space of a vision-language model using a meta-learned adapter-equipped visual semantics tokenizer. To tackle large intra-class variation, we further design a query feature regulation scheme. Extensive experiments on ActivityNetv1.3 and THUMOS14 demonstrate that our MUPPET outperforms state-of-the-art alternative methods, often by a large margin. We also show that our MUPPET can be easily extended to tackle the few-shot object detection problem and again achieves the state-of-the-art performance on MS-COCO dataset. The code will be available in https://github.com/sauradip/MUPPET

随着大型预训练的Vison语言模型（如剪辑）的出现，可以通过及时调整来调整可转让表示形式。及时调整试图从存储在预训练的视觉模型的图像和文本编码器中的常识中探索有益信息，以探索下游任务。最近提出的名为“上下文优化”（COP）的方法将一组可学习的向量从语言侧引入文本提示符，而单独调整文本提示符则不会影响图像编码器的计算视觉特征，从而导致了次级优势。在本文中，我们通过学习文本提示并同时为文本和图像编码器提供双重模式提示调整范式。此外，为了使视觉提示更多地集中在目标视觉概念上，我们提出了类感知的视觉及时调整（CAVPT），该调整是通过在模板提示和视觉类别令牌嵌入的语言描述之间进行交叉注意来动态生成的。我们的方法提供了一种新的范式来调整大型预训练的视觉模型，并在8个数据集上进行了广泛的实验结果，证明了该方法的有效性。我们的代码在补充材料中可用。

Video recognition in an open and dynamic world is quite challenging, as we need to handle different settings such as close-set, long-tail, few-shot and open-set. By leveraging semantic knowledge from noisy text descriptions crawled from the Internet, we focus on the general video recognition (GVR) problem of solving different recognition tasks within a unified framework. The core contribution of this paper is twofold. First, we build a comprehensive video recognition benchmark of Kinetics-GVR, including four sub-task datasets to cover the mentioned settings. To facilitate the research of GVR, we propose to utilize external textual knowledge from the Internet and provide multi-source text descriptions for all action classes. Second, inspired by the flexibility of language representation, we present a unified visual-linguistic framework (VLG) to solve the problem of GVR by an effective two-stage training paradigm. Our VLG is first pre-trained on video and language datasets to learn a shared feature space, and then devises a flexible bi-modal attention head to collaborate high-level semantic concepts under different settings. Extensive results show that our VLG obtains the state-of-the-art performance under four settings. The superior performance demonstrates the effectiveness and generalization ability of our proposed framework. We hope our work makes a step towards the general video recognition and could serve as a baseline for future research. The code and models will be available at https://github.com/MCG-NJU/VLG.

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.

自动视觉解对我们多样化和开放的世界需要计算机视觉模型，以概括为特定任务的最小定制，类似于人类视力。计算机视觉基础型号培训，培训多样化，大型数据集，可以适应各种下游任务，对该任务来解决现实世界计算机视觉应用而言至关重要。虽然现有的视觉基础模型如剪辑，对齐和吴道2.0主要集中在映射图像和文本表示到跨模型共享表示，我们介绍了一台新的计算机视觉基础模型，佛罗伦萨，扩大粗糙的表示（现场）到精细（对象），从静态（图像）到动态（视频），以及从RGB到多个模态（标题，深度）。通过从Web级图像文本数据中纳入通用视觉语言表示，我们的佛罗伦萨模型可以很容易地适应各种计算机视觉任务，例如分类，检索，对象检测，VQA，图像标题，视频检索和动作识别。此外，佛罗伦萨在许多类型的转移学习中表现出出色的表现：全面采样的微调，线性探测，几次射击传输和用于新颖图像和物体的零拍摄传输。所有这些属性对于我们的视觉基础模型至关重要，以提供通用视觉任务。佛罗伦萨实现了新的最先进的导致44个代表性基准，例如Imagenet-1K零射击分类，最高1精度为83.74，最高5个精度为97.18，62.4地图上的Coco微调， 80.36在VQA上，动力学-600上的87.8。

来自视频数据的多模态学习最近看过，因为它允许在没有人为注释的情况下培训语义有意义的嵌入，从而使得零射击检索和分类等任务。在这项工作中，我们提出了一种多模态，模态无政府主义融合变压器方法，它学会在多个模态之间交换信息，例如视频，音频和文本，并将它们集成到加入的多模态表示中，以获取聚合的嵌入多模态时间信息。我们建议培训系统的组合丢失，单个模态以及成对的方式，明确地留出任何附加组件，如位置或模态编码。在测试时间时，产生的模型可以处理和融合任意数量的输入模态。此外，变压器的隐式属性允许处理不同长度的输入。为了评估所提出的方法，我们在大规模HOWASET上培训模型，并评估四个具有挑战性的基准数据集上产生的嵌入空间获得最先进的视频检索和零射击视频动作定位。

视觉世界自然地展现了一个长尾的开放类分布，这对现代视觉系统带来了巨大挑战。现有方法可以执行类重新平衡策略或直接改进网络模块以解决问题。然而，他们仍然用有限一套预定义标签训练模型，限制了他们的监督信息并限制了他们对新颖实例的可转移性。新途径上的大型对比视觉普瑞宁普雷宁闪光灯的最新进展，可视识别。利用开放词汇监督，预先染色的对比视觉语言模型学习强大的多模式表示，这是对处理数据缺陷和看不见的概念。通过计算视觉和文本输入之间的语义相似性，可视识别被转换为vision语言匹配问题。灵感来自于此，我们提出了民谣，利用了对比尾识别的对比视觉模型。我们首先通过对特定的长尾目标数据集进行对比学习继续预先预留视觉语言骨干。之后，我们冻结了骨干，进一步采用了额外的适配器层，以增强通过重新采样策略构建的平衡训练样本上的尾级课程的表示。已经在三个流行的长尾识别基准测试中进行了广泛的实验。因此，我们简单有效的方法设定了新的最先进的表演，优于具有大边距的竞争基础。代码在https://github.com/gaopengcuhk/ballad发布。

本文介绍了一种基于纯变压器的方法，称为视频动作识别的多模态视频变压器（MM-VIT）。与仅利用解码的RGB帧的其他方案不同，MM-VIT专门在压缩视频域中进行操作，并利用所有容易获得的模式，即I帧，运动向量，残差和音频波形。为了处理从多种方式提取的大量时空令牌，我们开发了几种可扩展的模型变体，它们将自我关注分解在空间，时间和模态尺寸上。此外，为了进一步探索丰富的模态互动及其效果，我们开发并比较了可以无缝集成到变压器构建块中的三种不同的交叉模态注意力机制。关于三个公共行动识别基准的广泛实验（UCF-101，某事-V2，Kinetics-600）证明了MM-VIT以效率和准确性的最先进的视频变压器，并且表现更好或同样地表现出对于具有计算重型光学流的最先进的CNN对应物。

Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing approaches usually consider learning prompt vectors for each task independently from scratch, thereby failing to exploit the rich shareable knowledge across different vision-language tasks. In this paper, we propose multitask vision-language prompt tuning (MVLPT), which incorporates cross-task knowledge into prompt tuning for vision-language models. Specifically, (i) we demonstrate the effectiveness of learning a single transferable prompt from multiple source tasks to initialize the prompt for each target task; (ii) we show many target tasks can benefit each other from sharing prompt vectors and thus can be jointly learned via multitask prompt tuning. We benchmark the proposed MVLPT using three representative prompt tuning methods, namely text prompt tuning, visual prompt tuning, and the unified vision-language prompt tuning. Results in 20 vision tasks demonstrate that the proposed approach outperforms all single-task baseline prompt tuning methods, setting the new state-of-the-art on the few-shot ELEVATER benchmarks and cross-task generalization benchmarks. To understand where the cross-task knowledge is most effective, we also conduct a large-scale study on task transferability with 20 vision tasks in 400 combinations for each prompt tuning method. It shows that the most performant MVLPT for each prompt tuning method prefers different task combinations and many tasks can benefit each other, depending on their visual similarity and label similarity. Code is available at https://github.com/sIncerass/MVLPT.

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。