表示像素位移的光流量广泛用于许多计算机视觉任务中以提供像素级运动信息。然而,随着卷积神经网络的显着进展,建议最近的最先进的方法直接在特征级别解决问题。由于特征向量的位移不与像素位移不一致,因此常用方法是:将光流向神经网络向前传递到任务数据集上的微调该网络。利用这种方法,他们期望微调网络来产生编码特征级运动信息的张量。在本文中,我们重新思考此事实上的范式并分析了视频对象检测任务中的缺点。为了缓解这些问题,我们提出了一种具有视频对象检测的\ textBF {i} n-network \ textbf {f} eature \ textbf {f} eature \ textbf {f}低估计模块(iff模块)的新型网络(iff-net)。在不借鉴任何其他数据集的预先训练,我们的IFF模块能够直接产生\ textBF {feature flow},表示特征位移。我们的IFF模块由一个浅模块组成,它与检测分支共享该功能。这种紧凑的设计使我们的IFF-Net能够准确地检测对象,同时保持快速推断速度。此外,我们提出了基于\ Textit {自我监督}的转换剩余损失(TRL),这进一步提高了IFF-Net的性能。我们的IFF-Net优于现有方法,并在Imagenet VID上设置最先进的性能。
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
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion features. In this work, we aim to efficiently encode these two features in a unified 2D framework. To this end, we first propose an STM block, which contains a Channel-wise SpatioTemporal Module (CSTM) to present the spatiotemporal features and a Channel-wise Motion Module (CMM) to efficiently encode motion features. We then replace original residual blocks in the ResNet architecture with STM blcoks to form a simple yet effective STM network by introducing very limited extra computation cost. Extensive experiments demonstrate that the proposed STM network outperforms the state-of-the-art methods on both temporal-related datasets (i.e., Something-Something v1 & v2 and Jester) and scene-related datasets (i.e., Kinetics-400, UCF-101, and HMDB-51) with the help of encoding spatiotemporal and motion features together. * The work was done during an internship at SenseTime.
translated by 谷歌翻译
Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is nontrivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable. We present deep feature flow, a fast and accurate framework for video recognition. It runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field. It achieves significant speedup as flow computation is relatively fast. The end-to-end training of the whole architecture significantly boosts the recognition accuracy. Deep feature flow is flexible and general. It is validated on two video datasets on object detection and semantic segmentation. It significantly advances the practice of video recognition tasks. Code is released at https:// github.com/msracver/Deep-Feature-Flow.
translated by 谷歌翻译
视频对象检测一直是计算机视觉中一个重要但充满挑战的话题。传统方法主要集中于设计图像级或框级特征传播策略以利用时间信息。本文认为,通过更有效,更有效的功能传播框架,视频对象探测器可以在准确性和速度方面提高。为此,本文研究了对象级特征传播,并提出了一个针对高性能视频对象检测的对象查询传播(QueryProp)框架。所提出的查询Prop包含两个传播策略:1)查询传播是从稀疏的钥匙帧到密集的非钥匙框架执行的,以减少非钥匙帧的冗余计算; 2)查询传播是从以前的关键帧到当前关键框架进行的,以通过时间上下文建模来改善特征表示。为了进一步促进查询传播,自适应传播门旨在实现灵活的钥匙框架选择。我们在Imagenet VID数据集上进行了广泛的实验。 QueryProp通过最先进的方法实现了可比的精度,并实现了不错的精度/速度权衡。代码可在https://github.com/hf1995/queryprop上获得。
translated by 谷歌翻译
尽管运动补偿大大提高了视频质量,但单独执行运动补偿和视频脱张需要大量的计算开销。本文提出了一个实时视频Deblurring框架,该框架由轻巧的多任务单元组成,该单元以有效的方式支持视频脱张和运动补偿。多任务单元是专门设计的,用于使用单个共享网络处理两个任务的大部分,并由多任务详细网络和简单的网络组成,用于消除和运动补偿。多任务单元最大程度地减少了将运动补偿纳入视频Deblurring的成本,并实现了实时脱毛。此外,通过堆叠多个多任务单元,我们的框架在成本和过度质量之间提供了灵活的控制。我们通过实验性地验证了方法的最先进的质量,与以前的方法相比,该方法的运行速度要快得多,并显示了实时的实时性能(在DVD数据集中测量了30.99db@30fps)。
translated by 谷歌翻译
在本文中,我们专注于探索有效的方法,以更快,准确和域的不可知性语义分割。受到相邻视频帧之间运动对齐的光流的启发,我们提出了一个流对齐模块(FAM),以了解相邻级别的特征映射之间的\ textit {语义流},并将高级特征广播到高分辨率特征有效地,有效地有效。 。此外,将我们的FAM与共同特征的金字塔结构集成在一起,甚至在轻量重量骨干网络(例如Resnet-18和DFNET)上也表现出优于其他实时方法的性能。然后,为了进一步加快推理过程,我们还提出了一个新型的封闭式双流对齐模块,以直接对齐高分辨率特征图和低分辨率特征图,在该图中我们将改进版本网络称为SFNET-LITE。广泛的实验是在几个具有挑战性的数据集上进行的,结果显示了SFNET和SFNET-LITE的有效性。特别是,建议的SFNET-LITE系列在使用RESNET-18主链和78.8 MIOU以120 fps运行的情况下,使用RTX-3090上的STDC主链在120 fps运行时,在60 fps运行时达到80.1 miou。此外,我们将四个具有挑战性的驾驶数据集(即CityScapes,Mapillary,IDD和BDD)统一到一个大数据集中,我们将其命名为Unified Drive细分(UDS)数据集。它包含不同的域和样式信息。我们基准了UDS上的几项代表性作品。 SFNET和SFNET-LITE仍然可以在UDS上取得最佳的速度和准确性权衡,这在如此新的挑战性环境中是强大的基准。所有代码和模型均可在https://github.com/lxtgh/sfsegnets上公开获得。
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
视频对象检测(VID)是具有挑战性的,因为对象外观的较高变化以及某些帧中的不同变化。在正面,与静止图像相比,视频的某个框架中的检测可以吸引其他帧的支撑。因此,如何在不同框架上汇总特征对于VID问题至关重要。大多数现有的聚合算法都是针对两阶段探测器定制的。但是,由于两阶段的性质,该类别中的探测器通常在计算上很昂贵。这项工作提出了一种简单而有效的策略来解决上述问题,该策略花费了很高的准确性上的边缘开销。具体而言,我们与传统的两阶段管道不同,我们主张在单阶段检测之后放置区域级别的选择,以避免处理大量的低质量候选者。此外,还构建了一个新的模块来评估目标框架及其参考的关系,并指导聚合。进行了广泛的实验和消融研究,以验证我们的设计功效,并揭示其优于其他最先进的VID方法的优势。我们的基于YOLOX的模型可以实现有希望的性能(例如,在单个2080TI GPU上的Imagenet VID数据集上的30 fps的87.5%AP50)使其对大规模或实时应用程序有吸引力。实现很简单,演示代码和模型已在https://github.com/yuhengsss/yolov上提供。
translated by 谷歌翻译
光流是一种易于构思和珍贵的提示,用于推进无监督的视频对象细分(UVOS)。以前的大多数方法直接提取并融合了在UVOS设置中分割目标对象的运动和外观特征。但是,光流本质上是连续帧之间所有像素的瞬时速度,因此使运动特征与相应帧之间的主要对象不太对齐。为了解决上述挑战,我们为外观和运动特征对齐方式提出了一个简洁,实用和有效的体系结构,称为层次特征对齐网络(HFAN)。具体而言,HFAN中的关键优点是顺序特征对齐(FAM)模块和特征适应(FAT)模块,这些模块被利用用于处理外观和运动特征。 FAM能够分别将外观和运动特征与主要对象语义表示分别对齐。此外,脂肪是针对外观和运动特征的自适应融合而显式设计的,以实现跨模式特征之间的理想权衡。广泛的实验证明了拟议的HFAN的有效性,该实验在Davis-16上达到了新的最新性能,达到88.7 $ \ MATHCAL {J} \&\ MATHCAL {F} $,即相对改进,即相对改进比最佳发布结果比3.5%。
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
The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN based methods can achieve good performance but are computationally intensive, making it expensive to deploy. In this paper, we propose a generic and effective Temporal Shift Module (TSM) that enjoys both high efficiency and high performance. Specifically, it can achieve the performance of 3D CNN but maintain 2D CNN's complexity. TSM shifts part of the channels along the temporal dimension; thus facilitate information exchanged among neighboring frames. It can be inserted into 2D CNNs to achieve temporal modeling at zero computation and zero parameters. We also extended TSM to online setting, which enables real-time low-latency online video recognition and video object detection. TSM is accurate and efficient: it ranks the first place on the Something-Something leaderboard upon publication; on Jetson Nano and Galaxy Note8, it achieves a low latency of 13ms and 35ms for online video recognition. The code is available at: https://github. com/mit-han-lab/temporal-shift-module.
translated by 谷歌翻译
基于3DCNN,ConvlSTM或光流的先前方法在视频显着对象检测(VSOD)方面取得了巨大成功。但是,它们仍然遭受高计算成本或产生的显着图质量较差的困扰。为了解决这些问题,我们设计了一个基于时空存储器(STM)网络,该网络从相邻帧中提取当前帧的有用时间信息作为VSOD的时间分支。此外,以前的方法仅考虑无时间关联的单帧预测。结果,模型可能无法充分关注时间信息。因此,我们最初将框架间的对象运动预测引入VSOD。我们的模型遵循标准编码器 - 编码器体系结构。在编码阶段,我们通过使用电流及其相邻帧的高级功能来生成高级的时间特征。这种方法比基于光流的方法更有效。在解码阶段,我们提出了一种有效的空间和时间分支融合策略。高级特征的语义信息用于融合低级特征中的对象细节,然后逐步获得时空特征以重建显着性图。此外,受图像显着对象检测(ISOD)中常用的边界监督的启发,我们设计了一种运动感知损失,用于预测对象边界运动,并同时对VSOD和对象运动预测执行多任务学习,这可以进一步促进模型以提取提取的模型时空特征准确并保持对象完整性。在几个数据集上进行的广泛实验证明了我们方法的有效性,并且可以在某些数据集上实现最新指标。所提出的模型不需要光流或其他预处理,并且在推理过程中可以达到近100 fps的速度。
translated by 谷歌翻译
基于文本的视频细分旨在通过用文本查询指定演员及其表演动作来细分视频序列中的演员。由于\ emph {emph {语义不对称}的问题,以前的方法无法根据演员及其动作以细粒度的方式将视频内容与文本查询对齐。 \ emph {语义不对称}意味着在多模式融合过程中包含不同量的语义信息。为了减轻这个问题,我们提出了一个新颖的演员和动作模块化网络,该网络将演员及其动作分别定位在两个单独的模块中。具体来说,我们首先从视频和文本查询中学习与参与者相关的内容,然后以对称方式匹配它们以定位目标管。目标管包含所需的参与者和动作,然后将其送入完全卷积的网络,以预测演员的分割掩模。我们的方法还建立了对象的关联,使其与所提出的时间建议聚合机制交叉多个框架。这使我们的方法能够有效地细分视频并保持预测的时间一致性。整个模型允许联合学习参与者的匹配和细分,并在A2D句子和J-HMDB句子数据集上实现单帧细分和完整视频细分的最新性能。
translated by 谷歌翻译
我们介绍了一种名为RobustAbnet的新表检测和结构识别方法,以检测表的边界并从异质文档图像中重建每个表的细胞结构。为了进行表检测,我们建议将Cornernet用作新的区域建议网络来生成更高质量的表建议,以更快的R-CNN,这显着提高了更快的R-CNN的定位准确性以进行表检测。因此,我们的表检测方法仅使用轻巧的RESNET-18骨干网络,在三个公共表检测基准(即CTDAR TRACKA,PUBLAYNET和IIIT-AR-13K)上实现最新性能。此外,我们提出了一种新的基于分裂和合并的表结构识别方法,其中提出了一个新型的基于CNN的新空间CNN分离线预测模块将每个检测到的表分为单元格,并且基于网格CNN的CNN合并模块是应用用于恢复生成细胞。由于空间CNN模块可以有效地在整个表图像上传播上下文信息,因此我们的表结构识别器可以坚固地识别具有较大的空白空间和几何扭曲(甚至弯曲)表的表。得益于这两种技术,我们的表结构识别方法在包括SCITSR,PubTabnet和CTDAR TrackB2-Modern在内的三个公共基准上实现了最先进的性能。此外,我们进一步证明了我们方法在识别具有复杂结构,大空间以及几何扭曲甚至弯曲形状的表上的表格上的优势。
translated by 谷歌翻译
视频突出对象检测旨在在视频中找到最具视觉上的对象。为了探索时间依赖性,现有方法通常是恢复性的神经网络或光学流量。然而,这些方法需要高计算成本,并且往往会随着时间的推移积累不准确性。在本文中,我们提出了一种带有注意模块的网络,以学习视频突出物体检测的对比特征,而没有高计算时间建模技术。我们开发了非本地自我关注方案,以捕获视频帧中的全局信息。共注意配方用于结合低级和高级功能。我们进一步应用了对比学学习以改善来自相同视频的前景区域对的特征表示,并将前景 - 背景区域对被推除在潜在的空间中。帧内对比损失有助于将前景和背景特征分开,并且帧间的对比损失提高了时间的稠度。我们对多个基准数据集进行广泛的实验,用于视频突出对象检测和无监督的视频对象分割,并表明所提出的方法需要较少的计算,并且对最先进的方法进行有利地执行。
translated by 谷歌翻译
半监督视频对象分割(VOS)的任务已经大大提升,最先进的性能是通过密集的基于匹配的方法进行的。最近的方法利用时空存储器(STM)网络并学习从所有可用源检索相关信息,其中使用对象掩模的过去帧形成外部存储器,并且使用存储器中的掩码信息分段为查询作为查询的当前帧进行分割。然而,当形成存储器并执行匹配时,这些方法仅在忽略运动信息的同时利用外观信息。在本文中,我们倡导\ emph {motion信息}的返回,并提出了一个用于半监督VOS的运动不确定性感知框架(MUMET)。首先,我们提出了一种隐含的方法来学习相邻帧之间的空间对应,构建相关成本卷。在构建密集的对应期间处理遮挡和纹理区域的挑战性案例,我们将不确定性纳入密集匹配并实现运动不确定性感知特征表示。其次,我们介绍了运动感知的空间注意模块,以有效地融合了语义特征的运动功能。关于具有挑战性的基准的综合实验表明,\ TextBF {\ Textit {使用少量数据并将其与强大的动作信息组合可以带来显着的性能Boost}}。我们只使用Davis17达到$ \ Mathcal {} $培训{76.5 \%} $ \ mathcal {f} $培训,这显着优于低数据协议下的\ texit {sota}方法。 \ textit {代码将被释放。}
translated by 谷歌翻译
Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles which combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy and optimization function, etc. In this paper, we provide a review on deep learning based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely Convolutional Neural Network (CNN). Then we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network based learning systems.
translated by 谷歌翻译
Temporal modeling is key for action recognition in videos. It normally considers both short-range motions and long-range aggregations. In this paper, we propose a Temporal Excitation and Aggregation (TEA) block, including a motion excitation (ME) module and a multiple temporal aggregation (MTA) module, specifically designed to capture both short-and long-range temporal evolution. In particular, for short-range motion modeling, the ME module calculates the feature-level temporal differences from spatiotemporal features. It then utilizes the differences to excite the motion-sensitive channels of the features. The long-range temporal aggregations in previous works are typically achieved by stacking a large number of local temporal convolutions. Each convolution processes a local temporal window at a time. In contrast, the MTA module proposes to deform the local convolution to a group of subconvolutions, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-convolutions, and each frame could complete multiple temporal aggregations with neighborhoods. The final equivalent receptive field of temporal dimension is accordingly enlarged, which is capable of modeling the long-range temporal relationship over distant frames. The two components of the TEA block are complementary in temporal modeling. Finally, our approach achieves impressive results at low FLOPs on several action recognition benchmarks, such as Kinetics, Something-Something, HMDB51, and UCF101, which confirms its effectiveness and efficiency.
translated by 谷歌翻译
从一组多曝光图像中重建无精神的高动态范围(HDR)图像是一项具有挑战性的任务,尤其是在大型对象运动和闭塞的情况下,使用现有方法导致可见的伪影。为了解决这个问题,我们提出了一个深层网络,该网络试图学习以正规损失为指导的多尺度特征流。它首先提取多尺度功能,然后对非参考图像的特征对齐。对齐后,我们使用残留的通道注意块将不同图像的特征合并。广泛的定性和定量比较表明,我们的方法可实现最新的性能,并在颜色伪像和几何变形大大减少的情况下产生出色的结果。
translated by 谷歌翻译