We present a new method for generating controllable, dynamically responsive, and photorealistic human animations. Given an image of a person, our system allows the user to generate Physically plausible Upper Body Animation (PUBA) using interaction in the image space, such as dragging their hand to various locations. We formulate a reinforcement learning problem to train a dynamic model that predicts the person's next 2D state (i.e., keypoints on the image) conditioned on a 3D action (i.e., joint torque), and a policy that outputs optimal actions to control the person to achieve desired goals. The dynamic model leverages the expressiveness of 3D simulation and the visual realism of 2D videos. PUBA generates 2D keypoint sequences that achieve task goals while being responsive to forceful perturbation. The sequences of keypoints are then translated by a pose-to-image generator to produce the final photorealistic video.

Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks. In this work, we focus on two challenging problems in the paradigm of Continual Learning (CL) without involving any old data: (i) the accumulation of catastrophic forgetting caused by the gradually fading knowledge space from which the model learns the previous knowledge; (ii) the uncontrolled tug-of-war dynamics to balance the stability and plasticity during the learning of new tasks. In order to tackle these problems, we present Progressive Learning without Forgetting (PLwF) and a credit assignment regime in the optimizer. PLwF densely introduces model functions from previous tasks to construct a knowledge space such that it contains the most reliable knowledge on each task and the distribution information of different tasks, while credit assignment controls the tug-of-war dynamics by removing gradient conflict through projection. Extensive ablative experiments demonstrate the effectiveness of PLwF and credit assignment. In comparison with other CL methods, we report notably better results even without relying on any raw data.

当前的文本分类方法通常仅在幼稚或复杂的分类器之前将文本编码为嵌入，该分类器忽略了标签文本中包含的建议信息。实际上，人类主要基于子类别的语义含义对文档进行分类。我们通过暹罗伯特（Siamese Bert）和名为Ideas（交互式双重注意力）的交互式双重注意提出了一种新颖的模型结构，以捕获文本和标签名称的信息交换。交互式双重注意力使该模型能够从粗糙到细小的类中开利的类和类内部信息，这涉及区分所有标签并匹配地面真实标签的语义子类。我们提出的方法的表现优于最新方法，使用标签文本显着，结果更稳定。

人类对象相互作用（HOI）检测的任务目标是人类与环境相互作用的细粒度视觉解析，从而实现了广泛的应用。先前的工作证明了有效的体系结构设计和相关线索的集成的好处，以进行更准确的HOI检测。但是，现有方法的设计适当的预训练策略的设计仍未得到充实。为了解决这一差距，我们提出了关系语言图像预训练（RLIP），这是一种利用实体和关系描述的对比预训练的策略。为了有效利用此类预训练，我们做出了三个技术贡献：（1）一种新的并行实体检测和顺序关系推理（Parse）体系结构，可在整体优化的预训练期间使用实体和关系描述； （2）合成数据生成框架，标签序列扩展，扩展了每个Minibatch中可用的语言数据的规模； （3）解释歧义，关系质量标签和关系伪标签的机制，以减轻训练数据中模棱两可/嘈杂样本的影响。通过广泛的实验，我们证明了这些贡献的好处，共同称为rlip-parse，以改善零射击，很少射击和微调的HOI检测性能以及从噪音注释中学习的鲁棒性。代码将在\ url {https://github.com/jacobyuan7/rlip}上找到。

视频识别的标准方法通常在完整的输入视频上运行，由于视频中的时空冗余率广泛，因此效率低下。蒙版视频建模（即视频）的最新进展表明，香草视觉变压器（VIT）仅具有有限的视觉内容来补充时空上下文的能力。受到这一点的启发，我们提出了建议的蒙版动作识别（MAR），该识别（MAR）通过丢弃一定比例的补丁并仅在视频的一部分上操作来减少冗余计算。 MAR包含以下两个必不可少的组件：单元运行掩盖和桥接分类器。具体而言，为了使VIT轻松地感知细节以外的细节，并且会呈现单元格的掩蔽，以保留视频中的时空相关性，从而确保可以在同一空间位置观察到在同一空间位置的贴片，以便轻松地重建。此外，我们注意到，尽管部分观察到的特征可以重建语义上明确的隐形贴片，但它们无法实现准确的分类。为了解决这个问题，提出了一个桥接分类器，以弥合重建的VIT编码功能与专门用于分类的功能之间的语义差距。我们提出的MAR将VIT的计算成本降低了53％，并且广泛的实验表明，MAR始终以明显的边距优于现有的VIT模型。尤其是，我们发现由MAR训练的Vit-Lage胜过由标准培训方案训练的Vit-Bugue，这是通过说服Kinetics-400和某些v2数据集中的利润率，而VIT-LARGE的计算开销仅为14.5％。维特（Vit-Huge）。

空间卷积广泛用于许多深度视频模型。它基本上假设了时空不变性，即，使用不同帧中的每个位置的共享权重。这项工作提出了用于视频理解的时间 - 自适应卷积（Tadaconv），这表明沿着时间维度的自适应权重校准是促进在视频中建模复杂的时间动态的有效方法。具体而言，Tadaconv根据其本地和全局时间上下文校准每个帧的卷积权重，使空间卷积具有时间建模能力。与先前的时间建模操作相比，Tadaconv在通过卷积内核上运行而不是特征，其维度是比空间分辨率小的数量级更有效。此外，内核校准还具有增加的模型容量。通过用Tadaconv替换Reset中的空间互联网来构建坦达2D网络，这与多个视频动作识别和定位基准测试的最先进方法相比，导致PAR或更好的性能。我们还表明，作为可忽略的计算开销的容易插入操作，Tadaconv可以有效地改善许多具有令人信服的边距的现有视频模型。 HTTPS：//github.com/alibaba-mmai-research/pytorch-video -Undersing提供代码和模型。

对比学习的核心思想是区分不同的实例，并从相同实例中强制不同的视图以共享相同的表示。为了避免琐碎的解决方案，增强在生成不同视图中起重要作用，其中显示了随机裁剪来对模型来学习广义和鲁棒的表示。常用的随机作物操作保持沿着训练过程不变的两个视图之间的分布。在这项工作中，我们表明，自适应地控制沿着训练过程的两个增强视图之间的视差增强了学习的表示的质量。具体而言，我们提出了一种参数立方裁剪操作，用于视频对比度学习，其通过可分辨率的3D仿射变换自动批量3D立方。参数使用对抗目标与视频骨干同时培训，并从数据中学习最佳裁剪策略。可视化表明，参数自适应地控制了两个增强视图之间的中心距离和IOU，并且沿着训练过程的差异中的学习变化是有利于学习强烈的表示。广泛的消融研究证明了所提出的参数对多个对比学习框架和视频骨干的有效性。可以使用代码和模型。

利用多尺度功能在解决语义细分问题方面表现出了巨大的潜力。聚集通常是用总和或串联（Concat）进行的，然后是卷积（Conv）层。但是，它将高级上下文完全通过了以下层次结构，而无需考虑它们的相互关系。在这项工作中，我们旨在启用低级功能，以通过跨尺度像素到区域关系操作从相邻的高级特征图中汇总互补上下文。我们利用跨尺度上下文的传播，即使高分辨率的低级特征也可以使远程依赖关系也可以捕获。为此，我们采用有效的功能金字塔网络来获得多尺度功能。我们提出了一个关系语义提取器（RSE）和关系语义传播器（RSP），分别用于上下文提取和传播。然后，我们将几个RSP堆叠到RSP头中，以实现上下文的渐进自上而下分布。两个具有挑战性的数据集和可可的实验结果表明，RSP头在语义细分和泛型分割方面都具有高效率的竞争性。在语义分割任务中，它的表现优于DeepLabv3 [1]，而在语义分割任务中少75％（多重添加）。

Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing a large DNN model in edge computing scenarios (e.g., edge devices and cloud servers). In this paper, we propose a novel backdoor attack specifically on the dynamic multi-exit DNN models. Particularly, we inject a backdoor by poisoning one DNN model's shallow hidden layers targeting not this vanilla DNN model but only its dynamically deployed multi-exit architectures. Our backdoored vanilla model behaves normally on performance and cannot be activated even with the correct trigger. However, the backdoor will be activated when the victims acquire this model and transform it into a dynamic multi-exit architecture at their deployment. We conduct extensive experiments to prove the effectiveness of our attack on three structures (ResNet-56, VGG-16, and MobileNet) with four datasets (CIFAR-10, SVHN, GTSRB, and Tiny-ImageNet) and our backdoor is stealthy to evade multiple state-of-the-art backdoor detection or removal methods.

U-shaped networks are widely used in various medical image tasks, such as segmentation, restoration and reconstruction, but most of them usually rely on centralized learning and thus ignore privacy issues. To address the privacy concerns, federated learning (FL) and split learning (SL) have attracted increasing attention. However, it is hard for both FL and SL to balance the local computational cost, model privacy and parallel training simultaneously. To achieve this goal, in this paper, we propose Robust Split Federated Learning (RoS-FL) for U-shaped medical image networks, which is a novel hybrid learning paradigm of FL and SL. Previous works cannot preserve the data privacy, including the input, model parameters, label and output simultaneously. To effectively deal with all of them, we design a novel splitting method for U-shaped medical image networks, which splits the network into three parts hosted by different parties. Besides, the distributed learning methods usually suffer from a drift between local and global models caused by data heterogeneity. Based on this consideration, we propose a dynamic weight correction strategy (\textbf{DWCS}) to stabilize the training process and avoid model drift. Specifically, a weight correction loss is designed to quantify the drift between the models from two adjacent communication rounds. By minimizing this loss, a correction model is obtained. Then we treat the weighted sum of correction model and final round models as the result. The effectiveness of the proposed RoS-FL is supported by extensive experimental results on different tasks. Related codes will be released at https://github.com/Zi-YuanYang/RoS-FL.