Knowledge mining is a widely active research area across disciplines such as natural language processing (NLP), data mining (DM), and machine learning (ML). The overall objective of extracting knowledge from data source is to create a structured representation that allows researchers to better understand such data and operate upon it to build applications. Each mentioned discipline has come up with an ample body of research, proposing different methods that can be applied to different data types. A significant number of surveys have been carried out to summarize research works in each discipline. However, no survey has presented a cross-disciplinary review where traits from different fields were exposed to further stimulate research ideas and to try to build bridges among these fields. In this work, we present such a survey.

Video moment localization, also known as video moment retrieval, aiming to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models.

Lenovo Research teamed with members of the factory operations group at Lenovo’s largest laptop manufacturing facility, LCFC, to replace a manual production scheduling system with a decision-making platform built on a deep reinforcement learning architecture. The system schedules production orders at all LCFC’s 43 assembly manufacturing lines, balancing the relative priorities of production volume, changeover cost, and order fulfillment. The multiobjective optimization scheduling problem is solved using a deep reinforcement learning model. The approach combines high computing efficiency with a novel masking mechanism that enforces operational constraints to ensure that the machine-learning model does not waste time exploring infeasible solutions. The use of the new model transformed the production management process enabling a 20% reduction in the backlog of production orders and a 23% improvement in the fulfillment rate. It also reduced the entire scheduling process from six hours to 30 minutes while it retained multiobjective flexibility to allow LCFC to adjust quickly to changing objectives. The work led to increased revenue of US $1.91 billion in 2019 and US $2.69 billion in 2020 for LCFC. The methodology can be applied to other scenarios in the industry.

This paper proposes a novel Boundary-aware Consistent Hidden Representation Learning Network (BA-CHRLN), which contains two branches for semi-supervised 3D medical image segmentation. Inspired by the contrastive learning, the two branches share the same encoder and each has its individual decoder, namely supervised decoder and unsupervised one. A stop-gradient operation is also utilized to prevent collapsing of solutions. Taking the unlabeled images as references, BA-CHRLN imposes the consistency by applying a perturbation on the high-level hidden feature representations, which significantly improves the encoder's representation and the network's robustness. A boundary-aware map is further introduced to capture the organ's boundary without any prior knowledge and additional parameters. Experiments on the Left Atrium (LA) benchmark dataset demonstrate the effectiveness of the BA-CHRLN.