Abstract: An automated checkout system accesses an image of an item inside a shopping cart and a location of the shopping cart within a store. The automated checkout system identifies a set of candidate items located within a threshold distance of the location of the shopping cart based on an item map. The item map describes a location of each item within the store and the location of each candidate item corresponds to a location of the candidate item on the item map. The automated checkout system inputs visual features of the item extracted from the image to a machine-learning model to identify the item by determining a similarity score between the item and each candidate item of the set of candidate items. After identifying the item, the automated checkout system displays a list comprising the item and additional items within the shopping cart to a user.

Abstract: A method of acquiring feature information of a detected object is provided, including: controlling the detected object to pass through a detection apparatus; controlling an imaging system to perform radiation scanning on the detected object acquiring a radiation scanning image of the detected object acquiring feature information of the detected object through the radiation scanning image. The detected object includes a first part, a detection part and a second part sequentially in a first direction. The acquiring feature information of the detected object through the radiation scanning image includes: acquiring a first boundary line between the detection part and the first part and a second boundary line between the detection part and the second part through the radiation scanning image; and calculating a dimension between the first boundary line and the second boundary line in the first direction to acquire a dimension of the detection part in the first direction.

Abstract: A neurofeedback system includes an EEG apparatus, a presentation apparatus and a controller. The controller is configured to: (i) cause the presentation apparatus to display an overlaid image to the user that comprises a first image flickering at a first frequency and a second image flickering at a second frequency different than the first frequency, the first image being an affective distractor stimulus image and the second image being a task-relevant stimulus image, (ii) receive from the EEG apparatus a number of first steady-state visual evoked potential (SSVEP) signals generated in response the first image of the overlaid image and a number of second SSVEP signals generated in response the second image of the overlaid image, and (iii) calculate feedback indicative of how much attention of the was user allocated to the task-relevant stimulus image versus how much attention of the user was allocated to the affective distractor stimulus image.

Abstract: Provided is a noninvasive hemoglobin detector, including an image acquisition system, an image processing and analysis system and a printing device. The image acquisition system is connected with the image processing and analysis system, and the image acquisition system is used for acquiring, transmitting and storing an image to be tested. The image processing and analysis system is further connected with the printing device, and the image processing and analysis system is used for processing and analyzing the image to be tested to obtain an analysis result. The printing device is used for printing the image to be tested and the analysis result.

Abstract: Provided herein are methods and systems for identifying a face of an infant in an image including providing a computer comprising a processor and a memory trained with a set of training images and programmed with a convolutional neural network (CNN) model for identifying a face of an infant in a test image suspected of comprising an infant's face, wherein each image of the set of training images includes a plurality of facial landmark annotations and at least one pose attribute annotation, providing a test image suspected of comprising an image of an infant's face, and processing the test image using the computer, whereby the infant's face is identified in the test image.

Abstract: The invention relates to a method for preparing a vinyl ether polymer by photo-initiated polymerization, which comprises the step of: under a protective atmosphere, performing photo-initiated polymerization on a vinyl ether monomer in the presence of an organic halogenated hydrocarbon and manganese carbonyl under irradiation of light having a wavelength of 365-550 nm at ?25° C. to 25° C., to obtain a vinyl ether polymer after the reaction is completed. In the method, a vinyl ether monomer is subjected to cationic polymerization in the presence of manganese carbonyl and an organic halogenated hydrocarbon under visible light, to prepare a vinyl ether polymer with controlled molecular weight and narrow molecular weight distribution.

Abstract: Methods and systems for providing a dataset of human in-bed poses include simultaneously gathered images of in-bed poses of humans from imaging modalities including red-green-blue (RGB) and one or more of long wavelength infrared (LWIR), depth imaging, and pressure mapping. The images are obtained under a lighting condition and a cover condition. The dataset can be used to train a model of estimating human in-bed poses and for methods of estimating human in-bed poses. Methods and systems of estimating three-dimensional human poses from two-dimensional input images are provided.

Abstract: Techniques for dynamically generating deeplink search results in response to navigational search queries. In an aspect, to address user search queries, a general-purpose search engine is provided in parallel with a dedicated engine for specifically ranking deeplinks. Upon identifying a received query as a navigational query, a parallel query is generated from a common domain and user query, and provided to the dedicated engine. The engine accesses relevant deeplink URL's from a search index, which may be frequently refreshed and updated with the most recent Web contents. Ranking of deeplink URL's may be performed according to an algorithm that processes query-level features and document-level features of URL's to be ranked. In an aspect, the algorithm may be trained from search engine logs and/or Web browser logs, by calculating a Log-based Normalized Discounted Cumulative Gain (LNDCG) designed to quantify relevance of search results to queries based on user click behavior.

Abstract: The invention relates to a method for preparing a vinyl ether polymer by photo-initiated polymerization, which comprises the step of: under a protective atmosphere, performing photo-initiated polymerization on a vinyl ether monomer in the presence of an organic halogenated hydrocarbon and manganese carbonyl under irradiation of light having a wavelength of 365-550 nm at ?25° C. to 25° C., to obtain a vinyl ether polymer after the reaction is completed. In the method, a vinyl ether monomer is subjected to cationic polymerization in the presence of manganese carbonyl and an organic halogenated hydrocarbon under visible light, to prepare a vinyl ether polymer with controlled molecular weight and narrow molecular weight distribution.

Abstract: A small six-dimensional force and torque sensor, includes a cylindrical housing, a base disposed on the inner wall of the cylindrical housing, eight first elastic beams of the same size and structure for connecting the base, a central boss disposed at the center of the cylindrical housing, four second elastic beams of the same size and structure for connecting the central boss with the first elastic beams. The four second elastic beams are arranged in a cross shape. The eight first elastic beams and the four second elastic beams are respectively attached with a plurality of strain gauges, thus forming full bridge circuits. The sensor is simple in structure, small in size, can realize self-decoupling of the structure in six directions, and is suitable to be used in combination with current industrial systems.

Abstract: A membrane with rejection properties for mono and divalent-salts, BOD and COD good resistance to cleaning chemicals and maintaining high permeability for water. A polymeric coating prepared from polydopamine or hydroquinone or catechol or mixtures thereof, is deposited. In another embodiment, coating process steps and conditions are taught to achieve thickness control to tune the rejection properties of the membranes.

Abstract: A novel six-dimensional force and torque sensor includes a central boss, a cylindrical housing arranged outside the central boss, and twelve elastic beams for connecting the central boss with the cylindrical housing. The twelve elastic beams are respectively provided with strain gauges as needed, and a bottom of the central boss is provided with a mounting hole for mounting a signal processing module. The present invention has the characteristics of self-decoupling, high rigidity, high natural frequency, desirable linearity, ideal repeatability and perfect hysteresis, and ability to measure a large torque (50 N·m). In addition, the sensor can be designed to have different measuring ranges and sensitivities by changing the dimensions of each of the elastic beams.

Abstract: Techniques for dynamically generating deeplink search results in response to navigational search queries. In an aspect, to address user search queries, a general-purpose search engine is provided in parallel with a dedicated engine for specifically ranking deeplinks. Upon identifying a received query as a navigational query, a parallel query is generated from a common domain and user query, and provided to the dedicated engine. The engine accesses relevant deeplink URL's from a search index, which may be frequently refreshed and updated with the most recent Web contents. Ranking of deeplink URL's may be performed according to an algorithm that processes query-level features and document-level features of URL's to be ranked. In an aspect, the algorithm may be trained from search engine logs and/or Web browser logs, by calculating a Log-based Normalized Discounted Cumulative Gain (LNDCG) designed to quantify relevance of search results to queries based on user click behavior.

Abstract: A membrane with rejection properties for mono and divalent-salts, BOD and COD good resistance to cleaning chemicals and maintaining high permeability for water. A polymeric coating prepared from polydopamine or hydroquinone or catechol or mixtures thereof, is deposited. In another embodiment, coating process steps and conditions are taught to achieve thickness control to tune the rejection properties of the membranes.

Abstract: The A method and system for server synchronization with a computing device via a companion device is disclosed. In one embodiment, the method comprises synchronizing a device and an enterprise server via a companion device, which comprises retrieving a record extraction sequence from the server; providing the record extraction sequence to the handheld device from the companion device; and extracting records stored on a database according to the record extraction sequence, wherein the extracted records are not already stored on the computing device.

Abstract: A method and system for direct server synchronization with a computing device is disclosed. In one embodiment, the method comprises synchronizing directly a handheld device and an enterprise server, which comprises retrieving a record extraction sequence from the server; and extracting records stored on a database according to the record extraction sequence, wherein the extracted records are not already stored on the computing device.

Abstract: The A method and system for server synchronization with a computing device via a companion device is disclosed. In one embodiment, the method comprises synchronizing a device and an enterprise server via a companion device, which comprises retrieving a record extraction sequence from the server; providing the record extraction sequence to the handheld device from the companion device; and extracting records stored on a database according to the record extraction sequence, wherein the extracted records are not already stored on the computing device.

Abstract: The A method and system for server synchronization with a computing device via a companion device is disclosed. In one embodiment, the method comprises synchronizing a device and an enterprise server via a companion device, which comprises retrieving a record extraction sequence from the server; providing the record extraction sequence to the handheld device from the companion device; and extracting records stored on a database according to the record extraction sequence, wherein the extracted records are not already stored on the computing device.

Abstract: A method and system for direct server synchronization with a computing device is disclosed. In one embodiment, the method comprises synchronizing directly a handheld device and an enterprise server, which comprises retrieving a record extraction sequence from the server; and extracting records stored on a database according to the record extraction sequence, wherein the extracted records are not already stored on the computing device.