现有的时间动作检测(TAD)方法依赖于每个视频产生大量的建议。这导致由于提案生成和/或主张行动实例评估以及最终的高计算成本而导致复杂的模型设计。在这项工作中,我们首次提出了一个带有全局分割掩码(TAG)的无建议的时间动作检测模型。我们的核心想法是以完整的视频长度共同学习每个操作实例的全局细分面具。标签模型与基于常规建议的方法有显着不同,通过关注全球时间表示学习,直接在没有建议的情况下直接检测本地起点和终点的行动点。此外,通过对TAD进行整体建模,而不是在单个建议级别上进行本地建模,标签需要更简单的模型体系结构,计算成本较低。广泛的实验表明,尽管设计更简单,但标签的表现优于现有的TAD方法,在两个基准上实现了新的最新性能。重要的是,训练的速度更快约20倍,推理效率更高。我们的标签的Pytorch实现可在https://github.com/sauradip/tags上获得。
translated by 谷歌翻译
现有的时间动作检测(TAD)方法依赖于带有细分级注释的大量培训数据。因此,收集和注释这样的训练集非常昂贵且不可计入。半监督的TAD(SS-TAD)通过利用规模自由的未标记视频来减轻此问题。但是,SS-Tad也比有监督的TAD更具挑战性的问题,因此研究得多。先前的SS-TAD方法直接结合了现有的基于建议的TAD方法和SSL方法。由于它们的顺序定位(例如,提案生成)和分类设计,它们很容易出现误差传播。为了克服这一局限性,在这项工作中,我们提出了一种基于无建议的时间掩模(点)的新型半监督时间动作检测模型,并具有平行的定位(掩码生成)和分类体系结构。这种新颖的设计通过切断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。我们进一步介绍了用于预测细化的分类和本地化之间的交互机制,以及用于自我监督模型预训练的新借口任务。对两个标准基准测试的广泛实验表明,我们的现场表现要优于最先进的替代方案,通常是很大的边距。 pytorch实施现场可在https://github.com/sauradip/spot上获得
translated by 谷歌翻译
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。
translated by 谷歌翻译
Existing Temporal Action Detection (TAD) methods typically take a pre-processing step in converting an input varying-length video into a fixed-length snippet representation sequence, before temporal boundary estimation and action classification. This pre-processing step would temporally downsample the video, reducing the inference resolution and hampering the detection performance in the original temporal resolution. In essence, this is due to a temporal quantization error introduced during the resolution downsampling and recovery. This could negatively impact the TAD performance, but is largely ignored by existing methods. To address this problem, in this work we introduce a novel model-agnostic post-processing method without model redesign and retraining. Specifically, we model the start and end points of action instances with a Gaussian distribution for enabling temporal boundary inference at a sub-snippet level. We further introduce an efficient Taylor-expansion based approximation, dubbed as Gaussian Approximated Post-processing (GAP). Extensive experiments demonstrate that our GAP can consistently improve a wide variety of pre-trained off-the-shelf TAD models on the challenging ActivityNet (+0.2% -0.7% in average mAP) and THUMOS (+0.2% -0.5% in average mAP) benchmarks. Such performance gains are already significant and highly comparable to those achieved by novel model designs. Also, GAP can be integrated with model training for further performance gain. Importantly, GAP enables lower temporal resolutions for more efficient inference, facilitating low-resource applications. The code will be available in https://github.com/sauradip/GAP
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
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
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
时间行动提案生成(TAPG)是一个具有挑战性的任务,旨在在具有时间边界的未经监控视频中找到动作实例。为了评估提案的信任,现有的作品通常预测建议与地面真理之间的时间交叉联盟(TIOO)监督的提案的行动得分。在本文中,我们通过利用背景预测得分来限制提案的信心,创新地提出了一般的辅助背景约束理念,以进一步抑制低质量的建议。以这种方式,可以轻松地将背景约束概念用于现有的TAPG方法(例如,BMN,GTAD)。从这个角度来看,我们提出了背景约束网络(BCNet),以进一步利用行动和背景的丰富信息。具体地,我们介绍了一种动作 - 背景交互模块,用于可靠的置信度评估,它通过帧和剪辑级别的注意机制模拟了动作和背景之间的不一致。在两个流行的基准测试中进行了广泛的实验,即ActivityNet-1.3和Thumos14。结果表明,我们的方法优于最先进的方法。配备现有的Action Classifier,我们的方法还可以在时间动作本地化任务上实现显着性能。
translated by 谷歌翻译
时间动作检测旨在定位视频中的行动边界。基于边界匹配的当前方法枚举并计算生成提案的所有可能的边界匹配。然而,这些方法忽略了边界预测中的远程上下文聚集。同时,由于相邻匹配的类似语义,局部语义聚集的密集产生的匹配不能改善语义丰富和歧视。在本文中,我们提出了名为Dual Contence聚合网络(DCAN)的端到端提议生成方法以聚合两个级别的上下文,即边界级别和提议级别,用于产生高质量的动作提案,从而提高性能时间作用检测。具体而言,我们设计了多路径时间上下文聚合(MTCA),以实现边界级别的平滑上下文聚合和对边界的精确评估。对于匹配评估,粗细匹配(CFM)旨在聚合上下文,并将匹配的映射从粗内进行精细化。我们对ActivityNet V1.3和Thumos-14进行了广泛的实验。 DCAN在ActivityNet V1.3上获得35.39%的平均地图,在Thumos-14上达到地图54.14%,展示DCAN可以产生高质量的提案,实现最先进的性能。我们在https://github.com/cg1177/dcan发布代码。
translated by 谷歌翻译
已经发现,旨在在未修剪视频的开始和终点范围内发现的时间动作实例的时间动作提案生成可以在很大程度上受益于适当的时间和语义上下文的剥削。最新的努力致力于通过自我发项模块来考虑基于时间的环境和基于相似性的语义上下文。但是,他们仍然遭受混乱的背景信息和有限的上下文特征学习的困扰。在本文中,我们提出了一个基于金字塔区域的新型插槽注意(PRSLOT)模块来解决这些问题。我们的PRSLOT模块不使用相似性计算,而是直接以编码器方式来学习本地关系,并基于注意力输入功能(称为\ textit {slot}}的注意力输入功能,生成了局部区域的表示。具体而言,在输入段级级别上,PRSLOT模块将目标段作为\ textIt {query},其周围区域为\ textit {key},然后通过聚集每个\ textit {query-key}插槽来生成插槽表示。具有平行金字塔策略的本地摘要上下文。基于PRSLOT模块,我们提出了一种基于金字塔区域的新型插槽注意网络,称为PRSA-NET,以学习具有丰富的时间和语义上下文的统一视觉表示,以获得更好的建议生成。广泛的实验是在两个广泛采用的Thumos14和ActivityNet-1.3基准上进行的。我们的PRSA-NET优于其他最先进的方法。特别是,我们将AR@100从以前的最佳50.67%提高到56.12%,以生成提案,并在0.5 TIOU下将地图从51.9 \%\%提高到58.7 \%\%\%\%\%,以在Thumos14上进行动作检测。 \ textit {代码可在} \ url {https://github.com/handhand123/prsa-net}中获得
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
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
时间动作本地化旨在预测未修剪长视频中每个动作实例的边界和类别。基于锚或建议的大多数先前方法忽略了整个视频序列中的全局本地上下文相互作用。此外,他们的多阶段设计无法直接生成动作边界和类别。为了解决上述问题,本文提出了一种新颖的端到端模型,称为自适应感知变压器(简称apperformer)。具体而言,Adaperformer探索了双支球多头的自我发项机制。一个分支会照顾全球感知的关注,该注意力可以模拟整个视频序列并汇总全球相关环境。而其他分支集中于局部卷积转移,以通过我们的双向移动操作来汇总框架内和框架间信息。端到端性质在没有额外步骤的情况下产生视频动作的边界和类别。提供了广泛的实验以及消融研究,以揭示我们设计的有效性。我们的方法在Thumos14数据集上实现了最先进的准确性(根据map@0.5、42.6 \%map@0.7和62.7 \%map@avg),并在活动网络上获得竞争性能, -1.3数据集,平均地图为36.1 \%。代码和型号可在https://github.com/soupero/adaperformer上找到。
translated by 谷歌翻译
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
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
在计算机视觉中长期以来一直研究了时间行动定位。现有的最先进的动作定位方法将每个视频划分为多个动作单位(即,在一级方法中的两级方法和段中的提案),然后单独地对每个视频进行操作,而不明确利用他们在学习期间的关系。在本文中,我们声称,动作单位之间的关系在行动定位中发挥着重要作用,并且更强大的动作探测器不仅应捕获每个动作单元的本地内容,还应允许更广泛的视野与相关的上下文它。为此,我们提出了一般图表卷积模块(GCM),可以轻松插入现有的动作本地化方法,包括两阶段和单级范式。具体而言,我们首先构造一个图形,其中每个动作单元被表示为节点,并且两个动作单元之间作为边缘之间的关系。在这里,我们使用两种类型的关系,一个类型的关系,用于捕获不同动作单位之间的时间连接,另一类是用于表征其语义关系的另一个关系。特别是对于两级方法中的时间连接,我们进一步探索了两种不同的边缘,一个连接重叠动作单元和连接周围但脱节的单元的另一个。在我们构建的图表上,我们将图形卷积网络(GCNS)应用于模拟不同动作单位之间的关系,这能够了解更有信息的表示来增强动作本地化。实验结果表明,我们的GCM始终如一地提高了现有行动定位方法的性能,包括两阶段方法(例如,CBR和R-C3D)和一级方法(例如,D-SSAD),验证我们的一般性和有效性GCM。
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
Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion irrelevant content. This problem requires methods not only generating proposals with precise temporal boundaries, but also retrieving proposals to cover truth action instances with high recall and high overlap using relatively fewer proposals. To address these difficulties, we introduce an effective proposal generation method, named Boundary-Sensitive Network (BSN), which adopts "local to global" fashion. Locally, BSN first locates temporal boundaries with high probabilities, then directly combines these boundaries as proposals. Globally, with Boundary-Sensitive Proposal feature, BSN retrieves proposals by evaluating the confidence of whether a proposal contains an action within its region. We conduct experiments on two challenging datasets: ActivityNet-1.3 and THUMOS14, where BSN outperforms other state-of-the-art temporal action proposal generation methods with high recall and high temporal precision. Finally, further experiments demonstrate that by combining existing action classifiers, our method significantly improves the state-of-the-art temporal action detection performance.
translated by 谷歌翻译
这项工作旨在使用带有动作查询的编码器框架(类似于DETR)来推进时间动作检测(TAD),该框架在对象检测中表现出了巨大的成功。但是,如果直接应用于TAD,该框架遇到了几个问题:解码器中争论之间关系的探索不足,由于培训样本数量有限,分类培训不足以及推断时不可靠的分类得分。为此,我们首先提出了解码器中的关系注意机制,该机制根据其关系来指导查询之间的注意力。此外,我们提出了两项​​损失,以促进和稳定行动分类的培训。最后,我们建议在推理时预测每个动作查询的本地化质量,以区分高质量的查询。所提出的命名React的方法在Thumos14上实现了最新性能,其计算成本比以前的方法低得多。此外,还进行了广泛的消融研究,以验证每个提出的组件的有效性。该代码可在https://github.com/sssste/reaeact上获得。
translated by 谷歌翻译
Temporal action proposal generation is an challenging and promising task which aims to locate temporal regions in real-world videos where action or event may occur. Current bottom-up proposal generation methods can generate proposals with precise boundary, but cannot efficiently generate adequately reliable confidence scores for retrieving proposals. To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map. Based on BM mechanism, we propose an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously. The two-branches of BMN are jointly trained in an unified framework. We conduct experiments on two challenging datasets: THUMOS-14 and ActivityNet-1.3, where BMN shows significant performance improvement with remarkable efficiency and generalizability. Further, combining with existing action classifier, BMN can achieve stateof-the-art temporal action detection performance.
translated by 谷歌翻译