Bayesian Inference offers principled tools to tackle many critical problems with modern neural networks such as poor calibration and generalization, and data inefficiency. However, scaling Bayesian inference to large architectures is challenging and requires restrictive approximations. Monte Carlo Dropout has been widely used as a relatively cheap way for approximate Inference and to estimate uncertainty with deep neural networks. Traditionally, the dropout mask is sampled independently from a fixed distribution. Recent works show that the dropout mask can be viewed as a latent variable, which can be inferred with variational inference. These methods face two important challenges: (a) the posterior distribution over masks can be highly multi-modal which can be difficult to approximate with standard variational inference and (b) it is not trivial to fully utilize sample-dependent information and correlation among dropout masks to improve posterior estimation. In this work, we propose GFlowOut to address these issues. GFlowOut leverages the recently proposed probabilistic framework of Generative Flow Networks (GFlowNets) to learn the posterior distribution over dropout masks. We empirically demonstrate that GFlowOut results in predictive distributions that generalize better to out-of-distribution data, and provide uncertainty estimates which lead to better performance in downstream tasks.

越来越多的人期望在对象属性具有高感知不确定性的越来越多的非结构化环境中操纵对象。这直接影响成功的对象操纵。在这项工作中，我们提出了一个基于增强的学习动作计划框架，用于对象操纵，该框架既利用了在现有的多感觉反馈，也可以使用学习的注意力引导的深层负担能力模型作为感知状态。可承受的模型是从多种感官方式中学到的，包括视觉和触摸（触觉和力/扭矩），旨在预测和指示具有相似外观的物体的多个负担能力（即抓地力和推动力）的可操作区域属性（例如，质量分布）。然后，对基于DQN的深钢筋学习算法进行培训，以选择成功对象操纵的最佳动作。为了验证提出的框架的性能，使用开放数据集和收集的数据集对我们的方法进行评估和基准测试。结果表明，所提出的方法和整体框架的表现优于现有方法，并实现更好的准确性和更高的效率。

Emotion-cause pair extraction (ECPE) aims to extract emotion clauses and corresponding cause clauses, which have recently received growing attention. Previous methods sequentially encode features with a specified order. They first encode the emotion and cause features for clause extraction and then combine them for pair extraction. This lead to an imbalance in inter-task feature interaction where features extracted later have no direct contact with the former. To address this issue, we propose a novel Pair-Based Joint Encoding (PBJE) network, which generates pairs and clauses features simultaneously in a joint feature encoding manner to model the causal relationship in clauses. PBJE can balance the information flow among emotion clauses, cause clauses and pairs. From a multi-relational perspective, we construct a heterogeneous undirected graph and apply the Relational Graph Convolutional Network (RGCN) to capture the various relationship between clauses and the relationship between pairs and clauses. Experimental results show that PBJE achieves state-of-the-art performance on the Chinese benchmark corpus.

Pessimism is of great importance in offline reinforcement learning (RL). One broad category of offline RL algorithms fulfills pessimism by explicit or implicit behavior regularization. However, most of them only consider policy divergence as behavior regularization, ignoring the effect of how the offline state distribution differs with that of the learning policy, which may lead to under-pessimism for some states and over-pessimism for others. Taking account of this problem, we propose a principled algorithmic framework for offline RL, called \emph{State-Aware Proximal Pessimism} (SA-PP). The key idea of SA-PP is leveraging discounted stationary state distribution ratios between the learning policy and the offline dataset to modulate the degree of behavior regularization in a state-wise manner, so that pessimism can be implemented in a more appropriate way. We first provide theoretical justifications on the superiority of SA-PP over previous algorithms, demonstrating that SA-PP produces a lower suboptimality upper bound in a broad range of settings. Furthermore, we propose a new algorithm named \emph{State-Aware Conservative Q-Learning} (SA-CQL), by building SA-PP upon representative CQL algorithm with the help of DualDICE for estimating discounted stationary state distribution ratios. Extensive experiments on standard offline RL benchmark show that SA-CQL outperforms the popular baselines on a large portion of benchmarks and attains the highest average return.

SMPL（SMPL）的参数3D身体模型仅代表最小衣服的人，并且很难扩展到衣服，因为它们具有固定的网格拓扑和分辨率。为了解决这些局限性，最近的工作使用隐式表面或点云来建模衣服。虽然不受拓扑的限制，但这种方法仍然很难为偏离身体的偏离的衣服建模，例如裙子和连衣裙。这是因为他们依靠身体来通过将衣服表面放置为参考形状。不幸的是，当衣服远离身体时，这个过程的定义很差。此外，他们使用线性混合剥皮来摆姿势，并将皮肤重量与下面的身体部位绑在一起。相比之下，我们在没有规范化的情况下对局部坐标空间中的衣服变形进行了建模。我们还放松皮肤重量以使多个身体部位影响表面。具体而言，我们用粗糙的阶段扩展了基于点的方法，该方法用学习的姿势独立的“粗大形状”代替了规范化，该方法可以捕获裙子（如裙子）的粗糙表面几何形状。然后，我们使用一个网络来完善该网络，该网络会渗透到粗糙表示中的线性混合剥皮权重和姿势依赖的位移。该方法适合符合身体并偏离身体的服装。我们通过从示例中学习特定于人的化身，然后展示如何以新的姿势和动作来展示它们的有用性。我们还表明，该方法可以直接从原始扫描中学习缺少数据，从而大大简化了创建逼真的化身的过程。代码可用于研究目的，可在{\ small \ url {https://qianlim.github.io/skirt}}中使用。

创建人工社会智能 - 可以理解多人互动的细微差别的算法 - 在处理多模式视频的面部表情和手势方面是一个令人兴奋的新兴挑战。最近的多模式方法已经在许多任务上设定了最新的现状，但是很难在社交互动中对复杂的面对面对话动态进行建模，尤其是在自我监督的设置中。在本文中，我们提出了面对面的对比学习（F2F-CL），这是一个图形神经网络，旨在使用分解节点对社交互动进行建模，以将沿语言转弯界限的多模式面对面互动进行上下文。借助F2F-CL模型，我们建议在同一视频中不同口语转弯的分数节点之间进行对比学习。我们通过实验评估了具有挑战性的社会IQ数据集并显示了最先进的结果。

了解来自第一人称观点的社交互动对于许多应用来说至关重要，从辅助机器人到AR / VR。谈论相互作用的第一步是理解人类的姿势和形状。但是，该领域的研究目前受到数据缺乏的阻碍。现有数据集根据大小，注释，地面真实捕获方式或相互作用的多样性有限。我们通过提出EGOBODY来解决这一缺点，这是一个用于复杂3D场景中的社交交互的新型大规模数据集。我们采用Microsoft Hololens2耳机来记录富裕的EGEntric数据流（包括RGB，深度，眼睛凝视，头部和手动跟踪）。为了获得准确的3D地面真理，我们将耳机用多kinect钻机校准并配合富有呈现的SMPL-X体网格到多视图RGB-D帧，重建3D人类姿势和相对于场景的形状。我们收集68个序列，跨越不同的社会学互动类别，并提出了从自我监视视图的3D全体姿态和形状估计的第一个基准。我们的数据集和代码将在https://sanweiliti.github.io/egobody/egobody.html中进行研究。

SMETS提出了具有可转移信念模型（TBM）中的决策层的有力概率转换（PPT），该决策层在没有更多信息的情况下认为，我们必须使用概率质量函数（PMF）做出决策。在本文中，通过在层次假设空间（HHS）中引入因果关系，提出了信仰进化网络（BEN）和全部因果关系。基于BEN，我们从信息融合视图中解释了PPT，并提出了一种称为完全因果关系概率转化（FCPT）的新概率转换（PT）方法，该方法在双标准评估下具有更好的性能。此外，我们启发性地提出了一种基于FCPT的新概率融合方法。与Dempster组合规则（DRC）相比，在融合相同的证据时，提出的方法具有更合理的结果。

长期以来，PATH规划一直是机器人技术的主要研究领域之一，PRM和RRT是最有效的计划者之一。尽管通常非常有效，但这些基于抽样的计划者在“狭窄通道”的重要情况下可能会变得昂贵。本文开发了专门为狭窄通道问题制定的路径规划范例。核心是基于计划由椭圆形工会封装的刚体机器人的计划。每个环境特征都使用具有$ \ Mathcal {C}^1 $边界的严格凸面来表示几何（例如，超级方面）。这样做的主要好处是，配置空间障碍物可以以封闭形式明确地进行参数化，从而可以使用先验知识来避免采样不可行的配置。然后，通过表征针对多个椭圆形的紧密体积，可以保证涉及旋转的机器人过渡无碰撞，而无需执行传统的碰撞检测。此外，通过与随机抽样策略结合使用，可以将提出的计划框架扩展到解决较高的维度问题，在该问题中，机器人具有移动的基础和铰接的附属物。基准结果表明，所提出的框架通常优于基于采样的计划者的计算时间和成功率，在找到单身机器人和具有较高维度配置空间的狭窄走廊的路径方面。使用建议的框架进行了物理实验，在人形机器人中进一步证明，该机器人在几个混乱的环境中行走，通道狭窄。

Few Shot Instance Segmentation (FSIS) requires models to detect and segment novel classes with limited several support examples. In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework. Our key insights are two folds: Firstly, with the aid of support masks, we can generate dynamic class centers more appropriately to re-weight query features. Secondly, we find that support object queries have already encoded key factors after base training. In this way, the query features can be enhanced twice from two aspects, i.e., feature-level and instance-level. In particular, we firstly design a mask-based dynamic weighting module to enhance support features and then propose to link object queries for better calibration via cross-attention. After the above steps, the novel classes can be improved significantly over our strong baseline. Additionally, our new framework can be easily extended to incremental FSIS with minor modification. When benchmarking results on the COCO dataset for FSIS, gFSIS, and iFSIS settings, our method achieves a competitive performance compared to existing approaches across different shots, e.g., we boost nAP by noticeable +8.2/+9.4 over the current state-of-the-art FSIS method for 10/30-shot. We further demonstrate the superiority of our approach on Few Shot Object Detection. Code and model will be available.