Samsung (China)

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes COVID-19 and is spread person-to-person through close contact. We aimed to investigate the effects of physical distance, face masks, and eye protection on virus transmission in health-care and non-health-care (eg, community) settings. METHODS: We did a systematic review and meta-analysis to investigate the optimum distance for avoiding person-to-person virus transmission and to assess the use of face masks and eye protection to prevent transmission of viruses. We obtained data for SARS-CoV-2 and the betacoronaviruses that cause severe acute respiratory syndrome, and Middle East respiratory syndrome from 21 standard WHO-specific and COVID-19-specific sources. We searched these data sources from database inception to May 3, 2020, with no restriction by language, for comparative studies and for contextual factors of acceptability, feasibility, resource use, and equity. We screened records, extracted data, and assessed risk of bias in duplicate. We did frequentist and Bayesian meta-analyses and random-effects meta-regressions. We rated the certainty of evidence according to Cochrane methods and the GRADE approach. This study is registered with PROSPERO, CRD42020177047. FINDINGS: =0·090; posterior probability >95%, low certainty). Eye protection also was associated with less infection (n=3713; aOR 0·22, 95% CI 0·12 to 0·39, RD -10·6%, 95% CI -12·5 to -7·7; low certainty). Unadjusted studies and subgroup and sensitivity analyses showed similar findings. INTERPRETATION: The findings of this systematic review and meta-analysis support physical distancing of 1 m or more and provide quantitative estimates for models and contact tracing to inform policy. Optimum use of face masks, respirators, and eye protection in public and health-care settings should be informed by these findings and contextual factors. Robust randomised trials are needed to better inform the evidence for these interventions, but this systematic appraisal of currently best available evidence might inform interim guidance. FUNDING: World Health Organization.

Knowledge graph completion aims to perform link prediction between entities. In this paper, we consider the approach of knowledge graph embeddings. Recently, models such as TransE and TransH build entity and relation embeddings by regarding a relation as translation from head entity to tail entity. We note that these models simply put both entities and relations within the same semantic space. In fact, an entity may have multiple aspects and various relations may focus on different aspects of entities, which makes a common space insufficient for modeling. In this paper, we propose TransR to build entity and relation embeddings in separate entity space and relation spaces. Afterwards, we learn embeddings by first projecting entities from entity space to corresponding relation space and then building translations between projected entities. In experiments, we evaluate our models on three tasks including link prediction, triple classification and relational fact extraction. Experimental results show significant and consistent improvements compared to state-of-the-art baselines including TransE and TransH.

Representation learning of knowledge bases aims to embed both entities and relations into a low-dimensional space. Most existing methods only consider direct relations in representation learning. We argue that multiple-step relation paths also contain rich inference patterns between entities, and propose a path-based representation learning model. This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, we design a path-constraint resource allocation algorithm to measure the reliability of relation paths. (2) We represent relation paths via semantic composition of relation embeddings.

Feature matching, which refers to establishing reliable correspondence between two sets of features (particularly point features), is a critical prerequisite in feature-based registration. In this paper, we propose a flexible and general algorithm, which is called locally linear transforming (LLT), for both rigid and nonrigid feature matching of remote sensing images. We start by creating a set of putative correspondences based on the feature similarity and then focus on removing outliers from the putative set and estimating the transformation as well. We formulate this as a maximum-likelihood estimation of a Bayesian model with hidden/latent variables indicating whether matches in the putative set are outliers or inliers. To ensure the well-posedness of the problem, we develop a local geometrical constraint that can preserve local structures among neighboring feature points, and it is also robust to a large number of outliers. The problem is solved by using the expectation-maximization algorithm (EM), and the closed-form solutions of both rigid and nonrigid transformations are derived in the maximization step. In the nonrigid case, we model the transformation between images in a reproducing kernel Hilbert space (RKHS), and a sparse approximation is applied to the transformation that reduces the method computation complexity to linearithmic. Extensive experiments on real remote sensing images demonstrate accurate results of LLT, which outperforms current state-of-the-art methods, particularly in the case of severe outliers (even up to 80%).

Text detection and recognition in a natural environment are key components of many applications, ranging from business card digitization to shop indexation in a street. This competition aims at assessing the ability of state-of-the-art methods to detect Multi-Lingual Text (MLT) in scene images, such as in contents gathered from the Internet media and in modern cities where multiple cultures live and communicate together. This competition is an extension of the Robust Reading Competition (RRC) which has been held since 2003 both in ICDAR and in an online context. The proposed competition is presented as a new challenge of the RRC. The dataset built for this challenge largely extends the previous RRC editions in many aspects: the multi-lingual text, the size of the dataset, the multi-oriented text, the wide variety of scenes. The dataset is comprised of 18,000 images which contain text belonging to 9 languages. The challenge is comprised of three tasks related to text detection and script classification. We have received a total of 16 participations from the research and industrial communities. This paper presents the dataset, the tasks and the findings of this RRC-MLT challenge.

Scene text detection is challenging as the input may have different orientations, sizes, font styles, lighting conditions, perspective distortions and languages. This paper addresses the problem by designing a Rotational Region CNN (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CNN). R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CNN includes a Text Region Proposal Network (Text-RPN) to estimate approximate text regions and a multitask refinement network to get the precise inclined box. Our work has the following features. First, we use a novel multi-task regression method to support arbitrarily-oriented scene text detection. Second, we introduce multiple ROIPoolings to address the scene text detection problem for the first time. Third, we use an inclined Non-Maximum Suppression (NMS) to post-process the detection candidates. Experiments show that our method outperforms the state-of-the-art on standard benchmarks: ICDAR 2013, ICDAR 2015, COCO-Text and MSRA-TD500.

We introduce a new transformation estimation algorithm using the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> E estimator and apply it to non-rigid registration for building robust sparse and dense correspondences. In the sparse point case, our method iteratively recovers the point correspondence and estimates the transformation between two point sets. Feature descriptors such as shape context are used to establish rough correspondence. We then estimate the transformation using our robust algorithm. This enables us to deal with the noise and outliers which arise in the correspondence step. The transformation is specified in a functional space, more specifically a reproducing kernel Hilbert space. In the dense point case for nonrigid image registration, our approach consists of matching both sparsely and densely sampled SIFT features, and it has particular advantages in handling significant scale changes and rotations. The experimental results show that our approach greatly outperforms state-of-the-art methods, particularly when the data contains severe outliers.

In hyperspectral remote sensing data mining, it is important to take into account of both spectral and spatial information, such as the spectral signature, texture feature, and morphological property, to improve the performances, e.g., the image classification accuracy. In a feature representation point of view, a nature approach to handle this situation is to concatenate the spectral and spatial features into a single but high dimensional vector and then apply a certain dimension reduction technique directly on that concatenated vector before feed it into the subsequent classifier. However, multiple features from various domains definitely have different physical meanings and statistical properties, and thus such concatenation has not efficiently explore the complementary properties among different features, which should benefit for boost the feature discriminability. Furthermore, it is also difficult to interpret the transformed results of the concatenated vector. Consequently, finding a physically meaningful consensus low dimensional feature representation of original multiple features is still a challenging task. In order to address these issues, we propose a novel feature learning framework, i.e., the simultaneous spectral-spatial feature selection and extraction algorithm, for hyperspectral images spectral-spatial feature representation and classification. Specifically, the proposed method learns a latent low dimensional subspace by projecting the spectral-spatial feature into a common feature space, where the complementary information has been effectively exploited, and simultaneously, only the most significant original features have been transformed. Encouraging experimental results on three public available hyperspectral remote sensing datasets confirm that our proposed method is effective and efficient.

Domestic waste classification was incorporated into legal provisions recently in China. However, relying on manpower to detect and classify domestic waste is highly inefficient. To that end, in this article, we propose a multimodel cascaded convolutional neural network (MCCNN) for domestic waste image detection and classification. MCCNN combined three subnetworks (DSSD, YOLOv4, and Faster-RCNN) to obtain the detections. Moreover, to suppress the false-positive predicts, we utilized a classification model cascaded with the detection part to judge whether the detection results are correct. To train and evaluate MCCNN, we designed a large-scale waste image dataset (LSWID), containing 30 000 domestic waste multilabeled images with 52 categories. To the best of our knowledge, the LSWID is the largest dataset on domestic waste images. Furthermore, a smart trash can is designed and applied to a Shanghai community, which helped to make waste recycling more efficient. Experimental results showed a state-of-the-art performance, with an average improvement of 10% in detection precision.

Abstract Flexible lithium‐ion batteries are critical for the next‐generation electronics. However, during the practical application, they may break under deformations such as twisting and cutting, causing their failure to work or even serious safety problems. A new family of all‐solid‐state and flexible aqueous lithium ion batteries that can self‐heal after breaking has been created by designing aligned carbon nanotube sheets loaded with LiMn 2 O 4 and LiTi 2 (PO 4 ) 3 nanoparticles on a self‐healing polymer substrate as electrodes, and a new kind of lithium sulfate/sodium carboxymethylcellulose serves as both gel electrolyte and separator. The specific capacity, rate capability, and cycling performance can be well maintained after repeated cutting and self‐healing. These self‐healing batteries are demonstrated to be promising for wearable devices.

While most wearable gesture recognition approaches focus on the forearm or fingers, the wrist may be a more suitable location for practical use. We present the design and validation of a real-time gesture recognition wristband based on surface electromyography and inertial measurement unit sensing fusion, which can recognize 8 air gestures and 4 surface gestures with 2 distinct force levels. Ten healthy subjects performed an initial gesture recognition experiment, followed by a second experiment 1 h later and a third experiment 1 day later. Classification accuracies for the initial experiment were 92.6% and 88.8% for air and surface gestures, respectively, and there were no changes in accuracy results during testing 1 h. and 1 day later (p > 0.05). These results demonstrate the feasibility of wrist-based gesture recognition paving the way for potential future integration in to a smart watch or other wrist-worn wearable for intuitive human computer interaction.

Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though many methods have been proposed for horizontal and oriented texts, detecting irregular shape texts such as curved texts is still a challenging problem. To solve the problem, we propose a robust scene text detection method with adaptive text region representation. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. This gives more accurate description of text regions. Experimental results on five benchmarks, namely, CTW1500, TotalText, ICDAR2013, ICDAR2015 and MSRA-TD500, show that the proposed method achieves state-of-the-art in scene text detection.

In this paper we study the problem of monocular relative depth perception in the wild. We introduce a simple yet effective method to automatically generate dense relative depth annotations from web stereo images, and propose a new dataset that consists of diverse images as well as corresponding dense relative depth maps. Further, an improved ranking loss is introduced to deal with imbalanced ordinal relations, enforcing the network to focus on a set of hard pairs. Experimental results demonstrate that our proposed approach not only achieves state-of-the-art accuracy of relative depth perception in the wild, but also benefits other dense per-pixel prediction tasks, e.g., metric depth estimation and semantic segmentation.

Non-orthogonal multiple access (NOMA) as an efficient method of radio resource sharing has its roots in network information theory. For generations of wireless communication systems design, orthogonal multiple access schemes in the time, frequency, or code domain have been the main choices due to the limited processing capability in the transceiver hardware, as well as the modest traffic demands in both latency and connectivity. However, for the next generation radio systems, given its vision to connect everything and the much evolved hardware capability, NOMA has been identified as a promising technology to help achieve all the targets in system capacity, user connectivity, and service latency. This article provides a systematic overview of the state-of-the-art design of the NOMA transmission based on a unified transceiver design framework, the related standardization progress, and some promising use cases in future cellular networks, based on which interested researchers can get a quick start in this area.

The presentation of Bluetooth Low Energy (BLE; e.g., Bluetooth 4.0) makes Bluetooth based indoor positioning have extremely broad application prospects. In this paper, we propose a received signal strength indication (RSSI) based Bluetooth positioning method. There are two phases in the procedure of our positioning: offline training and online locating. In the phase of offline training, we use piecewise fitting based on the lognormal distribution model to train the propagation model of RSSI for every BLE reference nodes, respectively, in order to reduce the influence of the positioning accuracy because of different locations of BLE reference nodes. Here we design a Gaussian filter to pre-process the receiving signals in different sampling points. In the phase of online locating, we use weighted sliding window to reduce fluctuations of the real-time signals. In addition, we propose a distance weighted filter based on triangle trilateral relations theorem, which can reduce the influence of positioning accuracy due to abnormal RSSI and improve the location accuracy effectively. Besides, in order to reduce the errors of targets coordinates caused by ordinary least squares method, we propose a collaborative localization algorithm based on Taylor series expansion. Another important feature of our method is the active learning ability of BLE reference nodes. Every reference node adjusts its pre-trained model according to the received signals from detecting nodes actively and periodically, which improve the accuracy of positioning greatly. Experiments show that the probability of locating error less than 1.5 meter is higher than 80% using our positioning method.

This paper presents a novel tree-based cost aggregation method for dense stereo matching. Instead of employing the minimum spanning tree (MST) and its variants, a new tree structure, "Segment-Tree", is proposed for non-local matching cost aggregation. Conceptually, the segment-tree is constructed in a three-step process: first, the pixels are grouped into a set of segments with the reference color or intensity image, second, a tree graph is created for each segment, and in the final step, these independent segment graphs are linked to form the segment-tree structure. In practice, this tree can be efficiently built in time nearly linear to the number of the image pixels. Compared to MST where the graph connectivity is determined with local edge weights, our method introduces some 'non-local' decision rules: the pixels in one perceptually consistent segment are more likely to share similar disparities, and therefore their connectivity within the segment should be first enforced in the tree construction process. The matching costs are then aggregated over the tree within two passes. Performance evaluation on 19 Middlebury data sets shows that the proposed method is comparable to previous state-of-the-art aggregation methods in disparity accuracy and processing speed. Furthermore, the tree structure can be refined with the estimated disparities, which leads to consistent scene segmentation and significantly better aggregation results.

Despite the increasing popularity of head mounted displays (HMDs), development of efficient text entry methods on these devices has remained under explored. In this paper, we investigate the feasibility of head-based text entry for HMDs, by which, the user controls a pointer on a virtual keyboard using head rotation. Specifically, we investigate three techniques: TapType, DwellType, and GestureType. Users of TapType select a letter by pointing to it and tapping a button. Users of DwellType select a letter by pointing to it and dwelling over it for a period of time. Users of GestureType perform word-level input using a gesture typing style. Two lab studies were conducted. In the first study, users typed 10.59 WPM, 15.58 WPM, and 19.04 WPM with DwellType, TapType, and GestureType, respectively. Users subjectively felt that all three of the techniques were easy to learn and considered the induced fatigue to be acceptable. In the second study, we further investigated GestureType. We improved its gesture-word recognition algorithm by incorporating the head movement pattern obtained from the first study. This resulted in users reaching 24.73 WPM after 60 minutes of training. Based on these results, we argue that head-based text entry is feasible and practical on HMDs, and deserves more attention.

Endowing dialogue systems with personas is essential to deliver more human-like conversations. However, this problem is still far from well explored due to the difficulties of both embodying personalities in natural languages and the persona sparsity issue observed in most dialogue corpora. This paper proposes a pre-training based personalized dialogue model that can generate coherent responses using persona-sparse dialogue data. In this method, a pre-trained language model is used to initialize an encoder and decoder, and personal attribute embeddings are devised to model richer dialogue contexts by encoding speakers' personas together with dialogue histories. Further, to incorporate the target persona in the decoding process and to balance its contribution, an attention routing structure is devised in the decoder to merge features extracted from the target persona and dialogue contexts using dynamically predicted weights. Our model can utilize persona-sparse dialogues in a unified manner during the training process, and can also control the amount of persona-related features to exhibit during the inference process. Both automatic and manual evaluation demonstrates that the proposed model outperforms state-of-the-art methods for generating more coherent and persona consistent responses with persona-sparse data.

Pure polyaniline (PANI) films with different molecular chain packing states were successfully prepared by simply tuning the <italic>m</italic>-cresol content in the solvent.

Knowledge sharing has been recognised as a key enhancer of supply-chain performance. However, the sharing of knowledge may not take place easily and automatically among the supply-chain partners. This paper attempts to shed some light on the mechanisms underpinning knowledge sharing in supply chains. In particular, we focus on knowledge sharing in a dyadic buyer–supplier relationship. We posit that trust and power are two important antecedents of two types of knowledge sharing between a buyer and supplier, namely technical exchange and technology transfer. To build our research model, a large-scale mail survey was conducted from a contact list of 800 companies provided by the Singapore Logistics Association. The results of the structural equation modelling suggest that trust has significant effects on technical exchange and technology transfer. Further, power also affects technical exchange and technology transfer significantly, though the impacts appear to be weaker than trust. The theoretical and practical implications of this research are discussed.