In this paper, we introduce 3D-CSL, a compact pipeline for Near-Duplicate Video Retrieval (NDVR), and explore a novel self-supervised learning strategy for video similarity learning. Most previous methods only extract video spatial features from frames separately and then design kinds of complex mechanisms to learn the temporal correlations among frame features. However, parts of spatiotemporal dependencies have already been lost. To address this, our 3D-CSL extracts global spatiotemporal dependencies in videos end-to-end with a 3D transformer and find a good balance between efficiency and effectiveness by matching on clip-level. Furthermore, we propose a two-stage self-supervised similarity learning strategy to optimize the entire network. Firstly, we propose PredMAE to pretrain the 3D transformer with video prediction task; Secondly, ShotMix, a novel video-specific augmentation, and FCS loss, a novel triplet loss, are proposed further promote the similarity learning results. The experiments on FIVR-200K and CC_WEB_VIDEO demonstrate the superiority and reliability of our method, which achieves the state-of-the-art performance on clip-level NDVR.

图形神经网络（GNN）的输入图的大小不断增加，突显了使用多GPU平台的需求。但是，由于计算不平衡和效率较低的通信，现有的多GPU GNN解决方案遭受了劣质性能。为此，我们提出了MGG，这是一种新型的系统设计，可以通过以GPU为中心的软件管道在多GPU平台上加速GNN。 MGG探讨了通过细粒度计算通信管道中隐藏GNN工作负载中远程内存访问延迟的潜力。具体而言，MGG引入了管​​道感知工作负载管理策略和混合数据布局设计，以促进通信局限性重叠。 MGG实现以优化的管道为中心的内核。它包括工作负载交织和基于经经的映射，以进行有效的GPU内核操作管道和专门的内存设计以及优化，以更好地数据访问性能。此外，MGG还结合了轻巧的分析建模和优化启发式方法，以动态提高运行时不同设置的GNN执行性能。全面的实验表明，MGG在各种GNN设置上的最先进的多GPU系统要比最先进的多GPU系统：平均比具有统一虚拟内存设计的多GPU系统快3.65倍，平均比DGCL框架快7.38倍。

已经进行了一项详尽的研究，以研究基于跨度的联合实体和关系提取任务的模型。但是，这些模型在模型训练过程中采样了大量的负实体和负关系，这是必不可少的，但导致数据分布严重不平衡，进而导致次优模型性能。为了解决上述问题，我们为基于跨度的联合实体和关系提取提出了两个阶段范式，其中涉及在第一阶段对实体和关系进行分类，并预测第二阶段的这些实体和关系的类型阶段。两阶段范式使我们的模型能够显着缩小数据分布差距，包括负实体与其他实体之间的差距，以及负面关系与其他关系之间的差距。此外，我们首次尝试将实体类型和实体距离与全球特征相结合，这已被证明有效，尤其是对于关系提取而言。几个数据集的实验结果表明，基于两阶段范式的基于跨度的联合提取模型增强，全局功能始终优于先前用于联合提取任务的基于最新的跨度模型，并建立了新的标准基准。定性和定量分析进一步验证了提出的范式和全球特征的有效性。

本文介绍了Yidun Nisp团队向视频关键字唤醒挑战提交的系统。我们提出了一个普通话关键字发现系统（KWS），具有几种新颖且有效的改进，包括大骨干（B）模型，一个关键字偏置（B）机制和版本建模单元的引入。通过考虑一下，我们将总系统BBS-KWS作为缩写。 BBS-KWS系统由端到端的自动语音识别（ASR）模块和KWS模块组成。 ASR模块将语音特征转换为文本表示，文本表示将大骨干网络应用于声学模型，并考虑了音节建模单元。另外，关键字偏置机制用于改善ASR推断阶段中的关键字的召回率。 KWS模块应用多个标准，以确定关键字的缺席或存在，例如多级匹配，模糊匹配和连接主义时间分类（CTC）前缀分数。为了进一步改进我们的系统，我们对CN-Celeb数据集进行半监督学习，以获得更好的概括。在VKW任务中，BBS-KWS系统实现了基线的显着收益，并在两条轨道中获得了第一名。

RGB-D显着性检测将来自RGB图像和深度图的信息集成在挑战条件下改善突出区域的预测。 RGB-D显着性检测的关键是在两个模态的多个尺度上完全挖掘和保险丝信息。以前的方法倾向于通过本地操作分开应用多尺度和多模态融合，这不能捕获远程依赖性。在这里，我们提出了一个基于变换器的网络来解决这个问题。我们所提出的架构由两个模块组成：基于变换器的模态功能增强模块（TWFEM）和基于变压器的特征融合模块（TFFM）。 TFFM通过同时将特征与来自多个位置的两个模式集成在所有位置上的特征来进行足够的特征融合。 TWFEM通过在TFFM之前的同一模态中选择和集成来自其他刻度的互补信息来增强每种比例的特征。我们表明，变压器是一种统一的操作，它在特征融合和特征增强中具有良好的功效，并简化了模型设计。六个基准数据集的广泛实验结果表明，我们所提出的网络对最先进的RGB-D显着性检测方法表现出有利。

预计变形量子算法将展示量子计算在近期嘈杂量子计算机上的优点。然而，由于算法的大小增加，训练这种变分量子算法遭受梯度消失。以前的工作无法处理由现实量子硬件的必然噪声效应引起的渐变消失。在本文中，我们提出了一种新颖的培训方案，以减轻这种噪声引起的渐变消失。我们首先介绍一种新的成本函数，其中通过在截断的子空间中使用无意程可观察来显着增强梯度。然后，我们证明可以通过从新的成本函数与梯度优化原始成本函数来达到相同的最小值。实验表明，我们的新培训方案对于各种任务的主要变分量子算法非常有效。

多年来，通过广泛研究了与量化的神经网络。遗憾的是，在GPU上的有限精度支持（例如，INT1和INT4）上通常限制具有多样化的精度（例如，1位重量和2位激活）的事先努力。为了打破这种限制，我们介绍了第一个任意精密神经网络框架（APNN-TC），以充分利用对AMPERE GPU张量核心的量化优势。具体地，APNN-TC首先结合了一种新的仿真算法来支持与INT1计算基元和XOR /和BOOLEAN操作的任意短比特宽度计算。其次，APNN-TC集成了任意精密层设计，以有效地将仿真算法映射到带有新型批处理策略和专业内存组织的张量核心。第三，APNN-TC体现了一种新型任意精密NN设计，可最大限度地减少层次的内存访问，并进一步提高性能。广泛的评估表明，APNN-TC可以通过Cutlass内核和各种NN模型实现显着加速，例如Reset和VGG。

A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources. Prior works either extract information from the RGB image and depth separately or use costly post-processing steps, limiting their performances in highly cluttered scenes and real-time applications. In this work, we present DenseFusion, a generic framework for estimating 6D pose of a set of known objects from RGB-D images. DenseFusion is a heterogeneous architecture that processes the two data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated. Furthermore, we integrate an end-to-end iterative pose refinement procedure that further improves the pose estimation while achieving near real-time inference. Our experiments show that our method outperforms state-of-the-art approaches in two datasets, YCB-Video and LineMOD. We also deploy our proposed method to a real robot to grasp and manipulate objects based on the estimated pose. Our code and video are available at https://sites.google.com/view/densefusion/.

Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image. We propose a novel endto-end model that generates such structured scene representation from an input image. The model solves the scene graph inference problem using standard RNNs and learns to iteratively improves its predictions via message passing. Our joint inference model can take advantage of contextual cues to make better predictions on objects and their relationships. The experiments show that our model significantly outperforms previous methods for generating scene graphs using Visual Genome dataset and inferring support relations with NYU Depth v2 dataset.

Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new target goals, and (2) data inefficiency i.e., the model requires several (and often costly) episodes of trial and error to converge, which makes it impractical to be applied to real-world scenarios. In this paper, we address these two issues and apply our model to the task of target-driven visual navigation. To address the first issue, we propose an actor-critic model whose policy is a function of the goal as well as the current state, which allows to better generalize. To address the second issue, we propose AI2-THOR framework, which provides an environment with highquality 3D scenes and physics engine. Our framework enables agents to take actions and interact with objects. Hence, we can collect a huge number of training samples efficiently.We show that our proposed method (1) converges faster than the state-of-the-art deep reinforcement learning methods, (2) generalizes across targets and across scenes, (3) generalizes to a real robot scenario with a small amount of fine-tuning (although the model is trained in simulation), ( 4) is end-to-end trainable and does not need feature engineering, feature matching between frames or 3D reconstruction of the environment.The supplementary video can be accessed at the following link: https://youtu.be/SmBxMDiOrvs.