In this paper, we develop an efficient multi-scale network to predict action classes in partial videos in an end-to-end manner. Unlike most existing methods with offline feature generation, our method directly takes frames as input and further models motion evolution on two different temporal scales.Therefore, we solve the complexity problems of the two stages of modeling and the problem of insufficient temporal and spatial information of a single scale. Our proposed End-to-End MultiScale Network (E2EMSNet) is composed of two scales which are named segment scale and observed global scale. The segment scale leverages temporal difference over consecutive frames for finer motion patterns by supplying 2D convolutions. For observed global scale, a Long Short-Term Memory (LSTM) is incorporated to capture motion features of observed frames. Our model provides a simple and efficient modeling framework with a small computational cost. Our E2EMSNet is evaluated on three challenging datasets: BIT, HMDB51, and UCF101. The extensive experiments demonstrate the effectiveness of our method for action prediction in videos.

How to identify and segment camouflaged objects from the background is challenging. Inspired by the multi-head self-attention in Transformers, we present a simple masked separable attention (MSA) for camouflaged object detection. We first separate the multi-head self-attention into three parts, which are responsible for distinguishing the camouflaged objects from the background using different mask strategies. Furthermore, we propose to capture high-resolution semantic representations progressively based on a simple top-down decoder with the proposed MSA to attain precise segmentation results. These structures plus a backbone encoder form a new model, dubbed CamoFormer. Extensive experiments show that CamoFormer surpasses all existing state-of-the-art methods on three widely-used camouflaged object detection benchmarks. There are on average around 5% relative improvements over previous methods in terms of S-measure and weighted F-measure.

Deep neural networks (DNNs) have successfully been applied in many fields in the past decades. However, the increasing number of multiply-and-accumulate (MAC) operations in DNNs prevents their application in resource-constrained and resource-varying platforms, e.g., mobile phones and autonomous vehicles. In such platforms, neural networks need to provide acceptable results quickly and the accuracy of the results should be able to be enhanced dynamically according to the computational resources available in the computing system. To address these challenges, we propose a design framework called SteppingNet. SteppingNet constructs a series of subnets whose accuracy is incrementally enhanced as more MAC operations become available. Therefore, this design allows a trade-off between accuracy and latency. In addition, the larger subnets in SteppingNet are built upon smaller subnets, so that the results of the latter can directly be reused in the former without recomputation. This property allows SteppingNet to decide on-the-fly whether to enhance the inference accuracy by executing further MAC operations. Experimental results demonstrate that SteppingNet provides an effective incremental accuracy improvement and its inference accuracy consistently outperforms the state-of-the-art work under the same limit of computational resources.

Recent cross-lingual cross-modal works attempt to extend Vision-Language Pre-training (VLP) models to non-English inputs and achieve impressive performance. However, these models focus only on understanding tasks utilizing encoder-only architecture. In this paper, we propose ERNIE-UniX2, a unified cross-lingual cross-modal pre-training framework for both generation and understanding tasks. ERNIE-UniX2 integrates multiple pre-training paradigms (e.g., contrastive learning and language modeling) based on encoder-decoder architecture and attempts to learn a better joint representation across languages and modalities. Furthermore, ERNIE-UniX2 can be seamlessly fine-tuned for varieties of generation and understanding downstream tasks. Pre-trained on both multilingual text-only and image-text datasets, ERNIE-UniX2 achieves SOTA results on various cross-lingual cross-modal generation and understanding tasks such as multimodal machine translation and multilingual visual question answering.

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries because they are usually occluded in other training views. In this paper, we propose SC-DepthV3 for addressing the challenges. Specifically, we introduce an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which we propose novel losses to boost self-supervised training. As a result, our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes. We demonstrate the significantly superior performance of our method over previous methods on six challenging datasets, and we provide detailed ablation studies for the proposed terms. Source code and data will be released at https://github.com/JiawangBian/sc_depth_pl

多模式变压器的最新努力通过合并视觉和文本信息改善了视觉上丰富的文档理解（VRDU）任务。但是，现有的方法主要集中于诸如单词和文档图像贴片之类的细粒元素，这使得他们很难从粗粒元素中学习，包括短语和显着视觉区域（如突出的图像区域）等自然词汇单元。在本文中，我们对包含高密度信息和一致语义的粗粒元素更为重要，这对于文档理解很有价值。首先，提出了文档图来模拟多层次多模式元素之间的复杂关系，其中通过基于群集的方法检测到显着的视觉区域。然后，提出了一种称为mmlayout的多模式变压器，以将粗粒的信息纳入基于图形的现有预训练的细颗粒的多峰变压器中。在mmlayout中，粗粒信息是从细粒度聚集的，然后在进一步处理后，将其融合到细粒度中以进行最终预测。此外，引入常识增强以利用天然词汇单元的语义信息。关于四个任务的实验结果，包括信息提取和文档问答，表明我们的方法可以根据细粒元素改善多模式变压器的性能，并使用更少的参数实现更好的性能。定性分析表明，我们的方法可以在粗粒元素中捕获一致的语义。

样品选择是减轻标签噪声在鲁棒学习中的影响的有效策略。典型的策略通常应用小损失标准来识别干净的样品。但是，这些样本位于决策边界周围，通常会与嘈杂的例子纠缠在一起，这将被此标准丢弃，从而导致概括性能的严重退化。在本文中，我们提出了一种新颖的选择策略，\ textbf {s} elf- \ textbf {f} il \ textbf {t} ering（sft），它利用历史预测中嘈杂的示例的波动来过滤它们，可以过滤它们，这可以是可以过滤的。避免在边界示例中的小损失标准的选择偏置。具体来说，我们介绍了一个存储库模块，该模块存储了每个示例的历史预测，并动态更新以支持随后的学习迭代的选择。此外，为了减少SFT样本选择偏置的累积误差，我们设计了一个正规化术语来惩罚自信的输出分布。通过通过此术语增加错误分类类别的重量，损失函数在轻度条件下标记噪声是可靠的。我们对具有变化噪声类型的三个基准测试并实现了新的最先进的实验。消融研究和进一步分析验证了SFT在健壮学习中选择样本的优点。

在本文中，我们分析了数据新鲜度对实时监督学习的影响，在该学习中，对神经网络进行了培训，可以根据功能（例如，视频框架）推断出时间变化的目标（例如，车辆在前面的位置） ）在传感节点（例如，相机或激光雷达）上观察到。人们可能会期望随着功能变得陈旧，实时监督学习的表现会单调地降低。使用信息理论分析，我们表明，如果特征和目标数据序列可以与马尔可夫链紧密接近，这是正确的。如果数据序列远非马克维亚人，那是不正确的。因此，实时监督学习的预测错误是信息时代（AOI）的函数，该函数可能是非单调的。进行了几项实验，以说明预测误差的单调和非单调行为。为了最大程度地减少实时的推理误差，我们提出了一种用于发送功能的新“选择 - 逃避器”模型，该模型比早期研究中使用的“生成意志”模型更一般。通过使用Gittins和Whittle索引，开发了低复杂性调度策略来最大程度地减少推理误差，在此发现Gittins索引理论与信息时代（AOI）之间的新联系最小化。这些调度结果（i）可将一般AOI函数（单调或非单调）和（ii）最小化，以最大程度地减少一般特征传输时间分布。提出了数据驱动的评估，以说明提出的调度算法的好处。

可控的人图像合成任务可以通过对身体姿势和外观的明确控制来实现广泛的应用。在本文中，我们提出了一个基于跨注意的样式分布模块，该模块在源语义样式和目标姿势转移的目标姿势之间计算。该模块故意选择每个语义表示的样式，并根据目标姿势分配它们。交叉注意的注意力矩阵表达了目标姿势与所有语义的源样式之间的动态相似性。因此，可以利用它来从源图像路由颜色和纹理，并受到目标解析图的进一步限制，以实现更清晰的目标。同时，为了准确编码源外观，还添加了不同语义样式之间的自我注意力。我们的模型的有效性在姿势转移和虚拟的尝试任务上进行了定量和质量验证。

最近的研究表明，诸如RNN和Transformers之类的深度学习模型为长期预测时间序列带来了显着的性能增长，因为它们有效地利用了历史信息。但是，我们发现，如何在神经网络中保存历史信息，同时避免过度适应历史上的噪音，这仍然有很大的改进空间。解决此问题可以更好地利用深度学习模型的功能。为此，我们设计了一个\ textbf {f}要求\ textbf {i} mpraved \ textbf {l} egendre \ textbf {m} emory模型，或{\ bf film}：它应用了legendre promotions topimate legendre provientions近似历史信息，近似历史信息，使用傅立叶投影来消除噪声，并添加低级近似值以加快计算。我们的实证研究表明，所提出的膜显着提高了由（\ textbf {20.3 \％}，\ textbf {22.6 \％}）的多变量和单变量长期预测中最新模型的准确性。我们还证明，这项工作中开发的表示模块可以用作一般插件，以提高其他深度学习模块的长期预测性能。代码可从https://github.com/tianzhou2011/film/获得。