The ultimate goal of continuous sign language recognition(CSLR) is to facilitate the communication between special people and normal people, which requires a certain degree of real-time and deploy-ability of the model. However, in the previous research on CSLR, little attention has been paid to the real-time and deploy-ability. In order to improve the real-time and deploy-ability of the model, this paper proposes a zero parameter, zero computation temporal superposition crossover module(TSCM), and combines it with 2D convolution to form a "TSCM+2D convolution" hybrid convolution, which enables 2D convolution to have strong spatial-temporal modelling capability with zero parameter increase and lower deployment cost compared with other spatial-temporal convolutions. The overall CSLR model based on TSCM is built on the improved ResBlockT network in this paper. The hybrid convolution of "TSCM+2D convolution" is applied to the ResBlock of the ResNet network to form the new ResBlockT, and random gradient stop and multi-level CTC loss are introduced to train the model, which reduces the final recognition WER while reducing the training memory usage, and extends the ResNet network from image classification task to video recognition task. In addition, this study is the first in CSLR to use only 2D convolution extraction of sign language video temporal-spatial features for end-to-end learning for recognition. Experiments on two large-scale continuous sign language datasets demonstrate the effectiveness of the proposed method and achieve highly competitive results.

针对以下问题：基于深度学习的时空层次连续语言识别模型具有大量计算，这限制了模型的实时应用，本文提出了一个时间上的超级分辨率网络（TSRNET）。将数据重构为密集的特征序列，以减少整体模型计算，同时将最终识别精度损失保持在最小值。连续的手语识别模型（CSLR）通过TSRNET主要由三个部分组成：帧级特征提取，时间序列特征提取和TSRNET，其中TSRNET位于框架级特征提取和时间序列的特征提取之间，主要包括在内两个分支：详细描述符和粗糙描述符。稀疏的框架级特征通过两个设计的分支获得的功能融合，作为重建的密集帧级特征序列，连接师时间分类（CTC）损失用于训练和优化，在时间序列特征提取部分之后。为了更好地恢复语义级别的信息，通过本文提出的自我生成的对抗训练方法对整体模型进行了训练，以降低模型错误率。训练方法将TSRNET视为发电机，框架级处理部分和时间处理部分是鉴别器。此外，为了统一不同基准下模型准确性损失的评估标准，本文提出了单词错误率偏差（WERD），该单词错误率（WERD）在估计的单词错误率（WER）和由The获得的参考WER之间的错误率。重建的帧级特征序列和完整的原始帧级特征序列为WERD。在两个大规模手语数据集上进行的实验证明了该模型的有效性。

连续的手语识别（CSLR）是一项具有挑战性的研究任务，因为对手语数据的时间顺序缺乏准确的注释。最近流行的用法是基于CSLR的“ CNN + RNN”的混合模型。但是，当在这些作品中提取时间特征时，大多数方法都使用固定的时间接受字段，并且不能很好地提取每个手语单词的时间功能。为了获得更准确的时间特征，本文提出了一个多尺度的时间网络（MSTNET）。网络主要由三个部分组成。重新连接和两个完全连接（FC）层构成框架特征提取部分。时间方面的特征提取部分通过首先使用拟议的多尺度时间块（MST-block）提高不同尺度的时间功能来进行时间特征学习，以提高时间建模能力，然后进一步编码不同的时间特征。通过变压器模块缩放以获得更准确的时间特征。最后，拟议的多级连接派时间分类（CTC）损失零件用于训练以获得识别结果。多级CTC损失可以更好地学习和更新CNN中的浅网络参数，该方法没有参数增加，并且可以灵活地嵌入其他模型中。两个公开可用数据集的实验结果表明，我们的方法可以在没有任何先验知识的情况下以端到端的方式有效地提取手语特征，从而提高CSLR的准确性并实现竞争成果。

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.

传统时空网络的建模，计算成本和准确性是视频动作识别中最集中的研究主题。传统的2D卷积具有较低的计算成本，但它无法捕获时间关系;基于3D卷积的卷积神经网络（CNNS）模型可以获得良好的性能，但其计算成本很高，参数的数量很大。在本文中，我们提出了一个即插即用的时空移位模块（STSM），它是一种有效且高性能的通用模块。具体地，在将STSM插入其他网络之后，可以在不增加计算和参数的数量的情况下提高网络的性能。特别是，当网络是2D CNN时，我们的STSM模块允许网络了解高效的时空特征。我们对该拟议模块进行了广泛的评估，进行了许多实验，以研究其在视频动作识别方面的有效性，并在动力学-400和某些东西上实现了最先进的结果 - 某种东西的数据集。

The increasing number of surveillance cameras and security concerns have made automatic violent activity detection from surveillance footage an active area for research. Modern deep learning methods have achieved good accuracy in violence detection and proved to be successful because of their applicability in intelligent surveillance systems. However, the models are computationally expensive and large in size because of their inefficient methods for feature extraction. This work presents a novel architecture for violence detection called Two-stream Multi-dimensional Convolutional Network (2s-MDCN), which uses RGB frames and optical flow to detect violence. Our proposed method extracts temporal and spatial information independently by 1D, 2D, and 3D convolutions. Despite combining multi-dimensional convolutional networks, our models are lightweight and efficient due to reduced channel capacity, yet they learn to extract meaningful spatial and temporal information. Additionally, combining RGB frames and optical flow yields 2.2% more accuracy than a single RGB stream. Regardless of having less complexity, our models obtained state-of-the-art accuracy of 89.7% on the largest violence detection benchmark dataset.

机器学习和非接触传感器的进步使您能够在医疗保健环境中理解复杂的人类行为。特别是，已经引入了几种深度学习系统，以实现对自闭症谱系障碍（ASD）等神经发展状况的全面分析。这种情况会影响儿童的早期发育阶段，并且诊断完全依赖于观察孩子的行为和检测行为提示。但是，诊断过程是耗时的，因为它需要长期的行为观察以及专家的稀缺性。我们展示了基于区域的计算机视觉系统的效果，以帮助临床医生和父母分析孩子的行为。为此，我们采用并增强了一个数据集，用于使用在不受控制的环境中捕获的儿童的视频来分析自闭症相关的动作（例如，在各种环境中使用消费级摄像机收集的视频）。通过检测视频中的目标儿童以减少背景噪声的影响，可以预处理数据。在时间卷积模型的有效性的推动下，我们提出了能够从视频帧中提取动作功能并通过分析视频中的框架之间的关系来从视频帧中提取动作功能并分类与自闭症相关的行为。通过对功能提取和学习策略的广泛评估，我们证明了通过膨胀的3D Convnet和多阶段的时间卷积网络实现最佳性能，达到了0.83加权的F1得分，以分类三种自闭症相关的动作，超越表现优于表现现有方法。我们还通过在同一系统中采用ESNET主链来提出一个轻重量解决方案，实现0.71加权F1得分的竞争结果，并在嵌入式系统上实现潜在的部署。

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.

Hand and face play an important role in expressing sign language. Their features are usually especially leveraged to improve system performance. However, to effectively extract visual representations and capture trajectories for hands and face, previous methods always come at high computations with increased training complexity. They usually employ extra heavy pose-estimation networks to locate human body keypoints or rely on additional pre-extracted heatmaps for supervision. To relieve this problem, we propose a self-emphasizing network (SEN) to emphasize informative spatial regions in a self-motivated way, with few extra computations and without additional expensive supervision. Specifically, SEN first employs a lightweight subnetwork to incorporate local spatial-temporal features to identify informative regions, and then dynamically augment original features via attention maps. It's also observed that not all frames contribute equally to recognition. We present a temporal self-emphasizing module to adaptively emphasize those discriminative frames and suppress redundant ones. A comprehensive comparison with previous methods equipped with hand and face features demonstrates the superiority of our method, even though they always require huge computations and rely on expensive extra supervision. Remarkably, with few extra computations, SEN achieves new state-of-the-art accuracy on four large-scale datasets, PHOENIX14, PHOENIX14-T, CSL-Daily, and CSL. Visualizations verify the effects of SEN on emphasizing informative spatial and temporal features. Code is available at https://github.com/hulianyuyy/SEN_CSLR

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.

基于骨架的动作识别方法受到时空骨骼图的语义提取的限制。但是，当前方法在有效地结合时间和空间图尺寸的特征方面很难，一侧往往厚度厚，另一侧较薄。在本文中，我们提出了一个时间通道聚合图卷积网络（TCA-GCN），以动态有效地学习基于骨架动作识别的不同时间和通道维度中的空间和时间拓扑。我们使用时间聚合模块来学习时间维特征和通道聚合模块，以有效地将空间动态通道拓扑特征与时间动态拓扑特征相结合。此外，我们在时间建模上提取多尺度的骨骼特征，并将其与注意机制融合。广泛的实验表明，在NTU RGB+D，NTU RGB+D 120和NW-UCLA数据集上，我们的模型结果优于最先进的方法。

Aiming at the problem that the current video anomaly detection cannot fully use the temporal information and ignore the diversity of normal behavior, an anomaly detection method is proposed to integrate the spatiotemporal information of pedestrians. Based on the convolutional autoencoder, the input frame is compressed and restored through the encoder and decoder. Anomaly detection is realized according to the difference between the output frame and the true value. In order to strengthen the characteristic information connection between continuous video frames, the residual temporal shift module and the residual channel attention module are introduced to improve the modeling ability of the network on temporal information and channel information, respectively. Due to the excessive generalization of convolutional neural networks, in the memory enhancement modules, the hopping connections of each codec layer are added to limit autoencoders' ability to represent abnormal frames too vigorously and improve the anomaly detection accuracy of the network. In addition, the objective function is modified by a feature discretization loss, which effectively distinguishes different normal behavior patterns. The experimental results on the CUHK Avenue and ShanghaiTech datasets show that the proposed method is superior to the current mainstream video anomaly detection methods while meeting the real-time requirements.

基于常规卷积网络的视频超分辨率（VSR）方法具有很强的视频序列的时间建模能力。然而，在单向反复卷积网络中的不同反复单元接收的输入信息不平衡。早期重建帧接收较少的时间信息，导致模糊或工件效果。虽然双向反复卷积网络可以缓解这个问题，但它大大提高了重建时间和计算复杂性。它也不适用于许多应用方案，例如在线超分辨率。为了解决上述问题，我们提出了一种端到端信息预构建的经常性重建网络（IPRRN），由信息预构建网络（IPNet）和经常性重建网络（RRNET）组成。通过将足够的信息从视频的前面集成来构建初始复发单元所需的隐藏状态，以帮助恢复较早的帧，信息预构建的网络在不向后传播之前和之后的输入信息差异。此外，我们展示了一种紧凑的复发性重建网络，可显着改善恢复质量和时间效率。许多实验已经验证了我们所提出的网络的有效性，并与现有的最先进方法相比，我们的方法可以有效地实现更高的定量和定性评估性能。

Most deep-learning-based continuous sign language recognition (CSLR) models share a similar backbone consisting of a visual module, a sequential module, and an alignment module. However, due to limited training samples, a connectionist temporal classification loss may not train such CSLR backbones sufficiently. In this work, we propose three auxiliary tasks to enhance the CSLR backbones. The first task enhances the visual module, which is sensitive to the insufficient training problem, from the perspective of consistency. Specifically, since the information of sign languages is mainly included in signers' facial expressions and hand movements, a keypoint-guided spatial attention module is developed to enforce the visual module to focus on informative regions, i.e., spatial attention consistency. Second, noticing that both the output features of the visual and sequential modules represent the same sentence, to better exploit the backbone's power, a sentence embedding consistency constraint is imposed between the visual and sequential modules to enhance the representation power of both features. We name the CSLR model trained with the above auxiliary tasks as consistency-enhanced CSLR, which performs well on signer-dependent datasets in which all signers appear during both training and testing. To make it more robust for the signer-independent setting, a signer removal module based on feature disentanglement is further proposed to remove signer information from the backbone. Extensive ablation studies are conducted to validate the effectiveness of these auxiliary tasks. More remarkably, with a transformer-based backbone, our model achieves state-of-the-art or competitive performance on five benchmarks, PHOENIX-2014, PHOENIX-2014-T, PHOENIX-2014-SI, CSL, and CSL-Daily.

Sign language recognition (SLR) aims to overcome the communication barrier for the people with deafness or the people with hard hearing. Most existing approaches can be typically divided into two lines, i.e., Skeleton-based and RGB-based methods, but both the two lines of methods have their limitations. RGB-based approaches usually overlook the fine-grained hand structure, while Skeleton-based methods do not take the facial expression into account. In attempts to address both limitations, we propose a new framework named Spatial-temporal Part-aware network (StepNet), based on RGB parts. As the name implies, StepNet consists of two modules: Part-level Spatial Modeling and Part-level Temporal Modeling. Particularly, without using any keypoint-level annotations, Part-level Spatial Modeling implicitly captures the appearance-based properties, such as hands and faces, in the feature space. On the other hand, Part-level Temporal Modeling captures the pertinent properties over time by implicitly mining the long-short term context. Extensive experiments show that our StepNet, thanks to Spatial-temporal modules, achieves competitive Top-1 Per-instance accuracy on three widely-used SLR benchmarks, i.e., 56.89% on WLASL, 77.2% on NMFs-CSL, and 77.1% on BOBSL. Moreover, the proposed method is compatible with the optical flow input, and can yield higher performance if fused. We hope that this work can serve as a preliminary step for the people with deafness.

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。

手语翻译（SLT），它以手语中的视觉内容以口语中的语言生成文本，很重要，以协助听力态度的沟通。灵感来自神经机翻译（NMT），最现有的SLT研究采用了一般序列来序列学习策略。然而，SLT与常规NMT任务显着不同，因为Sign语言通过多个视觉手动方面传达了消息。因此，在本文中，标志语言的这些独特的特征被制定为分层时空图表示，包括高级和微级图形，顶点表征指定的身体部位和边缘表示它们的交互。特别地，高级图表代表了手表和面部的区域中的图案，并且细级图考虑了面部区域的手和地标的关系。为了了解这些图形模式，提出了一种新颖的深度学习架构，即分层时空图神经网络（HST-GNN）。提出了具有邻域上下文的图形卷积和图形自我关注，以表征本地和全局图形属性。基准数据集的实验结果证明了该方法的有效性。

近年来，基于卷积网络的视频动作识别令人鼓舞地普及;然而，受到远程非线性时间关系建模和反向运动信息建模的限制，因此，现有模型的性能是严重的。为了解决这一紧急问题，我们引入了一个具有自我监督（TTSN）的令人惊叹的时间变压器网络。我们的高性能TTSN主要由时间变压器模块和时间序列自我监控模块组成。简明扼要地说，我们利用高效的时间变压器模块来模拟非本地帧之间的非线性时间依赖性，这显着增强了复杂的运动特征表示。我们采用的时间序列自我监控模块我们专注于“随机批量随机通道”的简化策略来反转视频帧的序列，允许从反向时间维度提高运动信息表示并提高模型的泛化能力。在三个广泛使用的数据集（HMDB51，UCF101和某事物）上的广泛实验已经得出结论地证明，我们提出的TTSN充满希望，因为它成功实现了行动识别的最先进性能。

Considerable unsupervised video object segmentation algorithms based on deep learning have the problem of substantive model parameters and computation, which significantly limits the application of the algorithm in practice. This paper proposes a video object segmentation network based on motion guidance, considerably reducing the number of model parameters and computation and improving the video object segmentation performance. The model comprises a dual-stream network, motion guidance module, and multi-scale progressive fusion module. Specifically, RGB images and optical flow estimation are fed into dual-stream network to extract object appearance features and motion features. Then, the motion guidance module extracts the semantic information from the motion features through local attention, which guides the appearance features to learn rich semantic information. Finally, the multi-scale progressive fusion module obtains the output features at each stage of the dual-stream network. It gradually integrates the deep features into the shallow ones yet improves the edge segmentation effect. In this paper, numerous evaluations are conducted on three standard datasets, and the experimental results prove the superior performance of the proposed method.

交通标志检测是无人驾驶系统的具有挑战性的任务，特别是对于检测多尺度目标和检测的实时问题。在交通标志检测过程中，目标的比例大大变化，这将对检测精度产生一定的影响。特征金字塔广泛用于解决这个问题，但它可能会破坏不同的交通标志尺度的功能一致性。此外，在实际应用中，常用方法难以提高多尺度交通标志的检测精度，同时确保实时检测。在本文中，我们提出了一种改进的特征金字塔模型，名为AF-FPN，它利用自适应注意模块（AAM）和特征增强模块（FEM）来减少特征映射生成过程中的信息损失，并提高表示能力特征金字塔。我们用AF-FPN替换了YOLOV5中的原始特征金字塔网络，这在确保实时检测的前提下提高了YOLOV5网络的多尺度目标的检测性能。此外，提出了一种新的自动学习数据增强方法来丰富数据集，提高模型的稳健性，使其更适合实际情况。关于清华腾讯100K（TT100K）数据集的广泛实验结果证明了与多种最先进的方法相比，所提出的方法的有效性和优越性。