时间动作定位中的大多数现代方法将此问题分为两个部分:(i)短期特征提取和(ii)远程时间边界定位。由于处理长期未修剪的视频引起的GPU内存成本很高,因此许多方法通过冷冻骨干或使用小型空间视频分辨率来牺牲短期功能提取器的代表力。由于最近的视频变压器模型,其中许多具有二次记忆复杂性,这个问题变得更糟。为了解决这些问题,我们提出了TallFormer,这是一种具有长期内存的记忆效率和端到端的可训练时间动作定位变压器。我们的长期记忆机制消除了在每个训练迭代期间处理数百个冗余视频帧的需求,从而大大减少了GPU的记忆消耗和训练时间。这些效率节省使我们(i)可以使用功能强大的视频变压器提取器,而无需冷冻主链或减少空间视频分辨率,而(ii)也保持了远距离的时间边界定位能力。只有RGB框架作为输入,没有外部动作识别分类器,TallFormer的表现优于先前的最先前的边距,在Thumos14上获得了59.1%的平均地图,而ActivityNet-1.3的平均地图为35.6%。该代码可公开:https://github.com/klauscc/tallformer。
translated by 谷歌翻译
时间动作本地化在视频分析中起着重要作用,该视频分析旨在将动作定位和分类在未修剪视频中。先前的方法通常可以预测单个时间尺度的特征空间上的动作。但是,低级量表的时间特征缺乏足够的语义来进行动作分类,而高级尺度则无法提供动作边界的丰富细节。为了解决这个问题,我们建议预测多个颞尺度特征空间的动作。具体而言,我们使用不同尺度的精致特征金字塔将语义从高级尺度传递到低级尺度。此外,为了建立整个视频的长时间尺度,我们使用时空变压器编码器来捕获视频帧的远程依赖性。然后,具有远距离依赖性的精制特征被送入分类器以进行粗糙的动作预测。最后,为了进一步提高预测准确性,我们建议使用框架级别的自我注意模块来完善每个动作实例的分类和边界。广泛的实验表明,所提出的方法可以超越Thumos14数据集上的最先进方法,并在ActivityNet1.3数据集上实现可比性的性能。与A2NET(tip20,avg \ {0.3:0.7 \}),sub-action(csvt2022,avg \ {0.1:0.5 \})和afsd(cvpr21,avg \ {0.3:0.7 \}) ,提出的方法分别可以提高12.6 \%,17.4 \%和2.2 \%
translated by 谷歌翻译
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without hitting the computation or memory bottlenecks. In this paper, we propose a new strategy to overcome this challenge. Instead of trying to process more frames at once like most existing methods, we propose to process videos in an online fashion and cache "memory" at each iteration. Through the memory, the model can reference prior context for long-term modeling, with only a marginal cost. Based on this idea, we build MeMViT, a Memory-augmented Multiscale Vision Transformer, that has a temporal support 30x longer than existing models with only 4.5% more compute; traditional methods need >3,000% more compute to do the same. On a wide range of settings, the increased temporal support enabled by MeMViT brings large gains in recognition accuracy consistently. MeMViT obtains state-of-the-art results on the AVA, EPIC-Kitchens-100 action classification, and action anticipation datasets. Code and models are available at https://github.com/facebookresearch/memvit.
translated by 谷歌翻译
Temporal action detection (TAD) is extensively studied in the video understanding community by generally following the object detection pipeline in images. However, complex designs are not uncommon in TAD, such as two-stream feature extraction, multi-stage training, complex temporal modeling, and global context fusion. In this paper, we do not aim to introduce any novel technique for TAD. Instead, we study a simple, straightforward, yet must-known baseline given the current status of complex design and low detection efficiency in TAD. In our simple baseline (termed BasicTAD), we decompose the TAD pipeline into several essential components: data sampling, backbone design, neck construction, and detection head. We extensively investigate the existing techniques in each component for this baseline, and more importantly, perform end-to-end training over the entire pipeline thanks to the simplicity of design. As a result, this simple BasicTAD yields an astounding and real-time RGB-Only baseline very close to the state-of-the-art methods with two-stream inputs. In addition, we further improve the BasicTAD by preserving more temporal and spatial information in network representation (termed as PlusTAD). Empirical results demonstrate that our PlusTAD is very efficient and significantly outperforms the previous methods on the datasets of THUMOS14 and FineAction. Meanwhile, we also perform in-depth visualization and error analysis on our proposed method and try to provide more insights on the TAD problem. Our approach can serve as a strong baseline for future TAD research. The code and model will be released at https://github.com/MCG-NJU/BasicTAD.
translated by 谷歌翻译
Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train directly from video frames with extremely low GPU memory consumption. Our main idea is to minimize and balance the heavy computation among features and gradients in each training iteration. We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder. To further alleviate the computational redundancy in training, we propose to dynamically sample only a small subset of proposals during training. Moreover, various sampling strategies and ratios are studied for both the encoder and detector. ETAD achieves state-of-the-art performance on TAD benchmarks with remarkable efficiency. On ActivityNet-1.3, training ETAD in 18 hours can reach 38.25% average mAP with only 1.3 GB memory consumption per video under end-to-end training. Our code will be publicly released.
translated by 谷歌翻译
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。
translated by 谷歌翻译
To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank-supportive information extracted over the entire span of a video-to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades. Code is available online. 1 1 https://github.com/facebookresearch/ video-long-term-feature-banks Input clip (4 seconds) Target frame
translated by 谷歌翻译
大多数现代视频识别模型旨在在短视频剪辑上运行(例如,长度为5-10)。因此,将此类模型应用于长时间的电影理解任务是一项挑战,通常需要复杂的长期时间推理。最近引入的视频变形金刚通过使用远程时间自我注意来部分解决此问题。但是,由于自我注意力的二次成本,这种模型通常是昂贵且不切实际的。取而代之的是,我们提出了Vis4mer,这是一种有效的远程视频模型,结合了自我注意力的优势和最近引入的结构化状态空间序列(S4)层。我们的模型使用标准的变压器编码器进行短距离时空特征提取,以及多尺度的时间S4解码器,用于随后的远程时间推理。通过逐步减少每个解码器层处的时空特征分辨率和通道维度,Vis4mer在视频中学习了复杂的长期时空依赖性。此外,比相应的基于纯的自我注意力的模型,Vis4mer的价格更快为$ 2.63 \ times $ $,$ 8 \ times $ $ GPU内存。此外,Vis4mer实现最先进的结果,在长期视频理解(LVU)基准中,$ 9 $ 9 $长的电影视频分类任务中的$ 6 $。此外,我们表明我们的方法成功地将其推广到其他领域,从而在早餐和硬币程序活动数据集中取得了竞争成果。该代码可在以下网址公开获取:https://github.com/md-mohaiminul/vis4mer。
translated by 谷歌翻译
动作检测的任务旨在在每个动作实例中同时推论动作类别和终点的本地化。尽管Vision Transformers推动了视频理解的最新进展,但由于在长时间的视频剪辑中,设计有效的架构以进行动作检测是不平凡的。为此,我们提出了一个有效的层次时空时空金字塔变压器(STPT)进行动作检测,这是基于以下事实:变压器中早期的自我注意力层仍然集中在局部模式上。具体而言,我们建议在早期阶段使用本地窗口注意来编码丰富的局部时空时空表示,同时应用全局注意模块以捕获后期的长期时空依赖性。通过这种方式,我们的STPT可以用冗余的大大减少来编码区域和依赖性,从而在准确性和效率之间进行有希望的权衡。例如,仅使用RGB输入,提议的STPT在Thumos14上获得了53.6%的地图,超过10%的I3D+AFSD RGB模型超过10%,并且对使用其他流量的额外流动功能的表现较少,该流量具有31%的GFLOPS ,它是一个有效,有效的端到端变压器框架,用于操作检测。
translated by 谷歌翻译
我们介绍了在视频中发现时间精确,细粒度事件的任务(检测到时间事件的精确时刻)。精确的斑点需要模型在全球范围内对全日制动作规模进行推理,并在本地识别微妙的框架外观和运动差异,以识别这些动作过程中事件的识别。令人惊讶的是,我们发现,最高的绩效解决方案可用于先前的视频理解任务,例如操作检测和细分,不能同时满足这两个要求。作为响应,我们提出了E2E点,这是一种紧凑的端到端模型,在精确的发现任务上表现良好,可以在单个GPU上快速培训。我们证明,E2E点的表现明显优于最近根据视频动作检测,细分和将文献发现到精确的发现任务的基线。最后,我们为几个细粒度的运动动作数据集贡献了新的注释和分裂,以使这些数据集适用于未来的精确发现工作。
translated by 谷歌翻译
时间动作检测(TAD)旨在确定未修剪视频中每个动作实例的语义标签和边界。先前的方法通过复杂的管道来解决此任务。在本文中,我们提出了一个具有简单集的预测管道的端到端时间动作检测变压器(TADTR)。给定一组名为“动作查询”的可学习嵌入,Tadtr可以从每个查询的视频中自适应提取时间上下文,并直接预测动作实例。为了适应TAD的变压器,我们提出了三个改进,以提高其所在地意识。核心是一个时间可变形的注意模块,在视频中有选择地参加一组稀疏的密钥片段。片段的完善机制和动作回归头旨在完善预测实例的边界和信心。 TADTR需要比以前的检测器更低的计算成本,同时保留了出色的性能。作为一个独立的检测器,它在Thumos14(56.7%地图)和HACS段(32.09%地图)上实现了最先进的性能。结合一个额外的动作分类器,它在ActivityNet-1.3上获得了36.75%的地图。我们的代码可在\ url {https://github.com/xlliu7/tadtr}上获得。
translated by 谷歌翻译
时间动作本地化(TAL)是识别视频中一组动作的任务,该任务涉及将开始和终点定位并对每个操作实例进行分类。现有方法通过使用预定义的锚窗或启发式自下而上的边界匹配策略来解决此任务,这些策略是推理时间的主要瓶颈。此外,主要的挑战是由于缺乏全球上下文信息而无法捕获远程动作。在本文中,我们介绍了一个无锚的框架,称为HTNET,该框架预测了一组<开始时间,结束时间,类,类>三胞胎,这些视频基于变压器体系结构。在预测粗边界之后,我们通过背景特征采样(BFS)模块和分层变压器对其进行完善,这使我们的模型能够汇总全局上下文信息,并有效利用视频中固有的语义关系。我们演示了我们的方法如何在两个TAL基准数据集上定位准确的动作实例并实现最先进的性能:Thumos14和ActivityNet 1.3。
translated by 谷歌翻译
基于自我注意力的变压器模型已显示出令人印象深刻的图像分类和对象检测结果,并且最近用于视频理解。受此成功的启发,我们研究了变压器网络在视频中的时间动作本地化的应用。为此,我们提出了ActionFormer,这是一个简单而强大的模型,可在不使用动作建议或依靠预定义的锚点窗口中识别其及时识别其类别并识别其类别。 ActionFormer将多尺度特征表示与局部自我发作相结合,并使用轻加权解码器对每个时刻进行分类并估算相应的动作边界。我们表明,这种精心策划的设计会在先前的工作中进行重大改进。如果没有铃铛和口哨声,ActionFormer在Thumos14上的TIOU = 0.5的地图达到了71.0%的地图,表现优于最佳先前模型的绝对百分比14.1。此外,ActionFormer在ActivityNet 1.3(平均地图36.6%)和Epic-Kitchens 100(+先前工作的平均地图+13.5%)上显示出很强的结果。我们的代码可从http://github.com/happyharrycn/actionformer_release获得。
translated by 谷歌翻译
有效地对视频中的空间信息进行建模对于动作识别至关重要。为了实现这一目标,最先进的方法通常采用卷积操作员和密集的相互作用模块,例如非本地块。但是,这些方法无法准确地符合视频中的各种事件。一方面,采用的卷积是有固定尺度的,因此在各种尺度的事件中挣扎。另一方面,密集的相互作用建模范式仅在动作 - 欧元零件时实现次优性能,给最终预测带来了其他噪音。在本文中,我们提出了一个统一的动作识别框架,以通过引入以下设计来研究视频内容的动态性质。首先,在提取本地提示时,我们会生成动态尺度的时空内核,以适应各种事件。其次,为了将这些线索准确地汇总为全局视频表示形式,我们建议仅通过变压器在一些选定的前景对象之间进行交互,从而产生稀疏的范式。我们将提出的框架称为事件自适应网络(EAN),因为这两个关键设计都适应输入视频内容。为了利用本地细分市场内的短期运动,我们提出了一种新颖有效的潜在运动代码(LMC)模块,进一步改善了框架的性能。在几个大规模视频数据集上进行了广泛的实验,例如,某种东西,动力学和潜水48,验证了我们的模型是否在低拖鞋上实现了最先进或竞争性的表演。代码可在:https://github.com/tianyuan168326/ean-pytorch中找到。
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
自2020年推出以来,Vision Transformers(VIT)一直在稳步打破许多视觉任务的记录,通常被描述为``全部'''替换Convnet。而且对于嵌入式设备不友好。此外,最近的研究表明,标准的转话如果经过重新设计和培训,可以在准确性和可伸缩性方面与VIT竞争。在本文中,我们采用Convnet的现代化结构来设计一种新的骨干,以采取行动,以采取行动特别是我们的主要目标是为工业产品部署服务,例如仅支持标准操作的FPGA董事会。因此,我们的网络仅由2D卷积组成,而无需使用任何3D卷积,远程注意插件或变压器块。在接受较少的时期(5x-10x)训练时,我们的骨干线超过了(2+1)D和3D卷积的方法,并获得可比的结果s在两个基准数据集上具有vit。
translated by 谷歌翻译
Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured temporal pyramid. On top of the pyramid, we further introduce a decomposed discriminative model comprising two classifiers, respectively for classifying actions and determining completeness. This allows the framework to effectively distinguish positive proposals from background or incomplete ones, thus leading to both accurate recognition and localization. These components are integrated into a unified network that can be efficiently trained in an end-to-end fashion. Additionally, a simple yet effective temporal action proposal scheme, dubbed temporal actionness grouping (TAG) is devised to generate high quality action proposals. On two challenging benchmarks, THUMOS14 and ActivityNet, our method remarkably outperforms previous state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling actions with various temporal structures. 1
translated by 谷歌翻译
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.
translated by 谷歌翻译
在视频的每一帧中,流式传输视频识别原因及其动作。良好的流识别模型捕获了长期动态和视频的短期变化。不幸的是,在大多数现有方法中,计算复杂性随所考虑的动力学的长度线性或二次增长。此问题在基于变压器的体系结构中特别明显。为了解决这个问题,我们通过内核镜头重新制定了视频变压器中的跨注意事项,并应用了两种暂时的平滑核:盒子内核或拉普拉斯内核。最终的流动注意力可以从框架到框架重新重新计算,并且仅需要恒定的时间更新每个帧。基于这个想法,我们构建了一种时间平滑变压器Testra,它具有恒定的缓存和计算开销的任意输入。具体而言,它的运行$ 6 \ times $ $ $比基于滑动窗口的同等滑动变压器的运行速度快,在流设置中具有2,048帧。此外,由于时间跨度的增加,Testra在Thumos'14和Epic-Kitchen-100上取得了最新的结果,这是两个标准的在线操作检测和动作预期数据集。 Testra的实时版本优于Thumos'14数据集上的所有事先方法。
translated by 谷歌翻译
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