Abstract: One illustrative method includes: (a) obtaining a video frame sequence having alternating fast and slow exposure frames; (b) applying a convolutional neural network twice to each frame in the video frame sequence, first when the frame is paired with a preceding frame, and again when the frame is paired with a subsequent frame, each time converting a pair of fast and slow exposure frames into an enhanced dynamic range video frame; and (c) outputting an enhanced video frame sequence. In another illustrative method, the convolutional neural network converts pairs of adjacent fast and slow exposure frames into corresponding pairs of enhanced dynamic range video frames. In yet another illustrative method, neighboring video frames for each given video frame are interpolated to form a fast and slow exposure frame pair, which the convolutional neural network converts into a corresponding enhanced dynamic range video frame.

Abstract: A method (1000) for operating cameras (202) in a cascaded network (100), comprising: capturing a first view (1200) with a first lens (326) having a first focal point (328) and a first centroid (352), the first view (1200) depicting a subject (1106); capturing a second view (1202) with a second lens (326) having a second focal point (328) and a second centroid (352); detecting a first location of the subject (1106), relative the first lens (326), wherein detecting the first location of the subject (1106), relative the first lens (326), is based on audio captured by a plurality of microphones (204); estimating a second location of the subject (1106), relative the second lens (326), based on the first location of the subject (1106) relative the first lens (326); selecting a portion (1206) of the second view (1202) as depicting the subject (1106) based on the estimate of the second location of the subject (1106) relative the second lens (326).

Abstract: A teleconferencing system (100) comprises: a first camera (202) including a first lens (326) having a first focal point (328) and a first centroid (352), and configured to capture a first view (900) corresponding to a subject (702); a second lens (326) having a second focal point (328) and a second centroid (352), and configured to capture a second view (902) corresponding to the subject (702); and a processor (206) coupled to the first camera device (202) and the second camera device (202). The processor (206) is configured to: estimate a first orientation (351) of the subject (702) relative the first lens (326) and a second orientation (351) of the subject relative the second lens (326); and determine that the first orientation (351) is more closely aligned with a first line (307) from the first centroid (352) to the first focal point (328) than is the second orientation (351) aligned with a second line (307) from the second centroid (352) to the second focal point (328).

Abstract: A method may include obtaining a frame of a video stream of multiple video streams of a video conference, obtaining face detection information identifying a face size and a face position of at least one face detected in the frame, and cropping and scaling the frame according to at least one crop and scale parameter using the face detection information to obtain a modified first frame. The at least one crop and scale parameter is based on frames of the multiple video streams. The frames include the frame. The method may further include presenting the modified frame.

Abstract: A method may include identifying, in a frame of a video feed, a region of interest (ROI) and a background, encoding the background using a first quantization parameter to obtain an encoded low-quality background, encoding the ROI using a second quantization parameter to obtain an encoded high-quality ROI, and encoding location information of the ROI to obtain encoded location information. The method may further include combining the encoded low-quality background, the encoded high-quality ROI, and the encoded location information to obtain a combined package. The method may further include transmitting the combined package to a remote endpoint.

Abstract: Techniques are provided for generating feature-level recommendations for content items. One method comprises obtaining feature values related to a content item; applying the feature values to a trained engagement prediction model that generates an influence score for each feature value, wherein the influence score for each feature value indicates an influence of each respective feature value on a performance indicator associated with the content item; generating a recommendation for improving the performance indicator using the influence score for each feature value; and initiating a modification of the content item using the recommendation. Features can be selected using an artificial intelligence technique that performs a sub-image analysis on historical content items to evaluate an area of influence for a region of the historical content items when a feature value of a feature is changed. An automated feature extraction process may extract feature values using machine learning model.

Abstract: The present invention discloses a dehumidification bag capable of being placed in multiple forms, having a bag body and a moisture absorbing medium placed in the bag body, wherein the surface of the bag body is provided with a gas permeable zone, the rest is a sealing zone except for the gas permeable zone, and the moisture absorbing medium absorbs moisture in air through the gas permeable zone; and the bottom of the bag body is provided with an expanding portion that allows the bag body to be placed upright.

Abstract: A method for tracking movement of a presenter during a videoconference comprises tracking the location of subject of interest; quickly detecting error conditions—such as can occur when a subject of interest moves too quickly or when a subject of interest walks past another person—and quickly reinitiating the tracking sequence to help ensure a positive videoconferencing experience.

Abstract: A method for tracking movement of a presenter during a videoconference comprises tracking the location of subject of interest; quickly detecting error conditions—such as can occur when a subject of interest moves too quickly or when a subject of interest walks past another person—and quickly reinitiating the tracking sequence to help ensure a positive videoconferencing experience.

Abstract: The present disclosure discloses a method for synthesizing a diaza-bridged compound and a diaza-bridged compound, belonging to the field of organic synthesis. The present disclosure includes the following reaction: in the formula, R is aryl, substituted aryl, alkyl or haloalkyl, Ra is any one of H, 2-nitrobenzenesulfonyl, 4-nitrobenzenesulfonyl or 2,4-dinitrobenzenesulfonyl, n=1 or 2. Since compound 2 and NH3 are used as raw materials, the present disclosure can not only effectively shorten the process flow and save process costs, but also improve the reaction yield to a certain extent. The present disclosure also provides a diaza-bridged compound, where the structural formula thereof is in the formula, Ra is any one of 2-nitrobenzenesulfonyl, 4-nitrobenzenesulfonyl or 2,4-dinitrobenzenesulfonyl.

Abstract: Aiming at a hardness mismatch phenomenon in the existing structure hardness design process according to an integral intensity viewpoint, the invention provides a quantitative matching design method for structure heat treatment-hardness distribution. The specific method comprises determining an ideal static intensity field distribution of the dangerous section of the structure according to a limit static stress distribution of a dangerous section of the structure; determining an ideal hardness distribution of the dangerous section of the structure by utilizing an intensity-hardness conversion relation; determining heat treatment requirements such as surface hardness, core hardness and the like by combining material and heat treatment mode; determining an actual hardness distribution of the dangerous section of the structure according to a material end quenching curve and the heat treatment requirement.

Abstract: Aiming at a hardness mismatch phenomenon in the existing structure hardness design process according to an integral intensity viewpoint, the invention provides a quantitative matching design method for structure heat treatment-hardness distribution. The specific method comprises determining an ideal static intensity field distribution of the dangerous section of the structure according to a limit static stress distribution of a dangerous section of the structure; determining an ideal hardness distribution of the dangerous section of the structure by utilizing an intensity-hardness conversion relation; determining heat treatment requirements such as surface hardness, core hardness and the like by combining material and heat treatment mode; determining an actual hardness distribution of the dangerous section of the structure according to a material end quenching curve and the heat treatment requirement.

Abstract: The invention provides a structural fatigue strength design method based on an intensity field, aiming at the phenomenon that the stress field is mismatched with the overall strength in the existing structural fatigue strength design process according to the overall strength viewpoint.

Abstract: An apparatus comprising an onboard energy storage device, an onboard power conversion device configured to be electrically coupled to an external power source for receiving electrical power therefrom, and at least one drive system electrically coupled to the onboard energy storage device and the onboard power conversion device, wherein the onboard energy storage device and the onboard power conversion device cooperatively provide electrical power for the at least one drive system. A vehicle and a method for managing power supply are also disclosed.

Abstract: A videoconferencing endpoint is described that uses a cascading sequence of convolutional neural networks to perform face detection and upper body detection of participants in a videoconference at the endpoint, where at least one member of the sequence of neural networks performs upper body detection, and where the final member of the sequence of neural networks performs face detection based on the results of the upper body detection. The models of the neural networks are trained on both large datasets of faces well as images that have been distorted by a wide-angle camera of the videoconferencing endpoint.

Abstract: The invention provides a structural static strength design method based on the strength field, aiming to solve the present phenomenon that the stress field is mismatched with the overall strength in the existing structural static strength design process according to the overall strength perspective.

Abstract: A vehicle system includes a converter, outlets, and a switching arrangement electrically between the outlets and the converter. A controller is programmed to, responsive to a first request, operate the switching arrangement to electrically connect a line and a neutral to a first outlet and operate the converter to output single-phase power to the first outlet. Responsive to a second request, the controller is configured to operate the switching arrangement to electrically connect a plurality of lines and not the neutral to a second outlet, and operate the converter to output three-phase power to the second outlet.

Abstract: To solve the technical problem of the incapacity to perform a quantitative matching design of residual compressive stress in the process of prior structural cold working-residual compressive stress design, the invention provides a method of structural cold working-residual compressive stress distribution quantitative matching design, characterized by treating the fatigue strength of a mechanical structure and parts as a field, and matching a structural stress field and a fatigue strength field organically, to quantitatively match the residual compressive stress in conjunction with characteristics of the cold working process.