高动态范围（HDR）视频提供比标准低动态范围（LDR）视频更具视觉上的体验。尽管HDR成像具有重要进展，但仍有一个具有挑战性的任务，可以使用传统的现成摄像头捕获高质量的HDR视频。现有方法完全依赖于在相邻的LDR序列之间使用致密光流来重建HDR帧。然而，当用嘈杂的框架应用于交替的曝光时，它们会导致颜色和暴露的曝光不一致。在本文中，我们提出了一种从LDR序列与交替曝光的LDR序列的HDR视频重建的端到端GAN框架。我们首先从Noisy LDR视频中提取清洁LDR帧，并具有在自我监督设置中培训的去噪网络的交替曝光。然后，我们将相邻的交流帧与参考帧对齐，然后在完全的对手设置中重建高质量的HDR帧。为了进一步提高所产生帧的鲁棒性和质量，我们在培训过程中将时间稳定性的正则化术语与成本函数的内容和风格的损耗一起融合。实验结果表明，我们的框架实现了最先进的性能，并通过现有方法生成视频的优质HDR帧。

数据库中的部署机学习（ML）算法是由于现代ML算法的不同计算脚印和多数数据库技术的挑战，每个数据库技术都具有自己的限制性语法。我们介绍了一个基于Apache Spark的微服务编排框架，其扩展了数据库操作以包含Web服务基元。我们的系统可以协调数百台机器的Web服务，并充分利用群集，线程和异步并行性。使用此框架，我们为智能服务提供大规模客户端，如语音，视觉，搜索，异常检测和文本分析。这允许用户将随意使用的智能集成到具有Apache Spark连接器的任何数据存储器中。为了消除网络通信的大多数开销，我们还引入了我们架构的低延迟集装箱版本。最后，我们证明我们调查的服务在各种基准上具有竞争力，并在此框架中展示了两个应用程序来创建智能搜索引擎和实时自动竞赛分析系统。

Classically, the development of humanoid robots has been sequential and iterative. Such bottom-up design procedures rely heavily on intuition and are often biased by the designer's experience. Exploiting the non-linear coupled design space of robots is non-trivial and requires a systematic procedure for exploration. We adopt the top-down design strategy, the V-model, used in automotive and aerospace industries. Our co-design approach identifies non-intuitive designs from within the design space and obtains the maximum permissible range of the design variables as a solution space, to physically realise the obtained design. We show that by constructing the solution space, one can (1) decompose higher-level requirements onto sub-system-level requirements with tolerance, alleviating the "chicken-or-egg" problem during the design process, (2) decouple the robot's morphology from its controller, enabling greater design flexibility, (3) obtain independent sub-system level requirements, reducing the development time by parallelising the development process.

Text-to-text generation models have increasingly become the go-to solution for a wide variety of sequence labeling tasks (e.g., entity extraction and dialog slot filling). While most research has focused on the labeling accuracy, a key aspect -- of vital practical importance -- has slipped through the cracks: understanding model confidence. More specifically, we lack a principled understanding of how to reliably gauge the confidence of a model in its predictions for each labeled span. This paper aims to provide some empirical insights on estimating model confidence for generative sequence labeling. Most notably, we find that simply using the decoder's output probabilities is not the best in realizing well-calibrated confidence estimates. As verified over six public datasets of different tasks, we show that our proposed approach -- which leverages statistics from top-$k$ predictions by a beam search -- significantly reduces calibration errors of the predictions of a generative sequence labeling model.

Data compression is becoming critical for storing scientific data because many scientific applications need to store large amounts of data and post process this data for scientific discovery. Unlike image and video compression algorithms that limit errors to primary data, scientists require compression techniques that accurately preserve derived quantities of interest (QoIs). This paper presents a physics-informed compression technique implemented as an end-to-end, scalable, GPU-based pipeline for data compression that addresses this requirement. Our hybrid compression technique combines machine learning techniques and standard compression methods. Specifically, we combine an autoencoder, an error-bounded lossy compressor to provide guarantees on raw data error, and a constraint satisfaction post-processing step to preserve the QoIs within a minimal error (generally less than floating point error). The effectiveness of the data compression pipeline is demonstrated by compressing nuclear fusion simulation data generated by a large-scale fusion code, XGC, which produces hundreds of terabytes of data in a single day. Our approach works within the ADIOS framework and results in compression by a factor of more than 150 while requiring only a few percent of the computational resources necessary for generating the data, making the overall approach highly effective for practical scenarios.

We consider the problem of continually releasing an estimate of the population mean of a stream of samples that is user-level differentially private (DP). At each time instant, a user contributes a sample, and the users can arrive in arbitrary order. Until now these requirements of continual release and user-level privacy were considered in isolation. But, in practice, both these requirements come together as the users often contribute data repeatedly and multiple queries are made. We provide an algorithm that outputs a mean estimate at every time instant $t$ such that the overall release is user-level $\varepsilon$-DP and has the following error guarantee: Denoting by $M_t$ the maximum number of samples contributed by a user, as long as $\tilde{\Omega}(1/\varepsilon)$ users have $M_t/2$ samples each, the error at time $t$ is $\tilde{O}(1/\sqrt{t}+\sqrt{M}_t/t\varepsilon)$. This is a universal error guarantee which is valid for all arrival patterns of the users. Furthermore, it (almost) matches the existing lower bounds for the single-release setting at all time instants when users have contributed equal number of samples.

Nonnegative matrix factorization can be used to automatically detect topics within a corpus in an unsupervised fashion. The technique amounts to an approximation of a nonnegative matrix as the product of two nonnegative matrices of lower rank. In this paper, we show this factorization can be combined with regression on a continuous response variable. In practice, the method performs better than regression done after topics are identified and retrains interpretability.

Despite the remarkable success achieved by graph convolutional networks for functional brain activity analysis, the heterogeneity of functional patterns and the scarcity of imaging data still pose challenges in many tasks. Transferring knowledge from a source domain with abundant training data to a target domain is effective for improving representation learning on scarce training data. However, traditional transfer learning methods often fail to generalize the pre-trained knowledge to the target task due to domain discrepancy. Self-supervised learning on graphs can increase the generalizability of graph features since self-supervision concentrates on inherent graph properties that are not limited to a particular supervised task. We propose a novel knowledge transfer strategy by integrating meta-learning with self-supervised learning to deal with the heterogeneity and scarcity of fMRI data. Specifically, we perform a self-supervised task on the source domain and apply meta-learning, which strongly improves the generalizability of the model using the bi-level optimization, to transfer the self-supervised knowledge to the target domain. Through experiments on a neurological disorder classification task, we demonstrate that the proposed strategy significantly improves target task performance by increasing the generalizability and transferability of graph-based knowledge.

One of the major errors affecting GNSS signals in urban canyons is GNSS multipath error. In this work, we develop a Gazebo plugin which utilizes a ray tracing technique to account for multipath effects in a virtual urban canyon environment using virtual satellites. This software plugin balances accuracy and computational complexity to run the simulation in real-time for both software-in-the-loop (SITL) and hardware-in-the-loop (HITL) testing. We also construct a 3D virtual environment of Hong Kong and compare the results from our plugin with the GNSS data in the publicly available Urban-Nav dataset, to validate the efficacy of the proposed Gazebo Plugin. The plugin is openly available to all the researchers in the robotics community. https://github.com/kpant14/multipath_sim

In this work, we used a semi-supervised learning method to train deep learning model that can segment the brain MRI images. The semi-supervised model uses less labeled data, and the performance is competitive with the supervised model with full labeled data. This framework could reduce the cost of labeling MRI images. We also introduced robust loss to reduce the noise effects of inaccurate labels generated in semi-supervised learning.