Abstract: A method for performing video domain adaptation for human action recognition is presented. The method includes using annotated source data from a source video and unannotated target data from a target video in an unsupervised domain adaptation setting, identifying and aligning discriminative clips in the source and target videos via an attention mechanism, and learning spatial-background invariant human action representations by employing a self-supervised clip order prediction loss for both the annotated source data and the unannotated target data.

Abstract: A system and method are provided for automatically estimating a repair cost for a vehicle. A method includes: receiving, at a server computing device over an electronic network, one or more images of a damaged vehicle from a client computing device; performing image processing operations on each of the one or more images to detect external damage to a first set of parts of the vehicle; inferring internal damage to a second set of parts of the vehicle based on the detected external damage; and, calculating an estimated repair cost for the vehicle based on the detected external damage and inferred internal damage based on accessing a parts database that includes repair and labor costs for each part in the first and second sets of parts.

Abstract: Systems and methods for automatically authenticating an incoming call are disclosed. In one implementation a method for automatically authenticating an incoming call includes receiving a call from a calling device. The call includes an identifier associated with the calling device. The method further includes receiving, separately from the call, authentication data associated with a device or a user, determining, using the identifier and the authentication data, that the authentication data is associated with the same calling device that initiated the call, verifying the authentication data, and based on a result of the verification, determining that the call is initiated by an authenticated device or user.

Abstract: A chronically implanted medical device is disclosed that has an outermost layer formed from a conjugate of a polymer with lipoic acid, the conjugate having free 1,2-dithiolane groups. It is contemplated that this layer scavenges reactive oxygen species, i.e. acts as an antioxidant, and thus reduces inflammation and other adverse effects around the implant itself.

Abstract: The invention provides a system and method that automatically generates a user interface (HMI) based on a selection of spreadsheet cells. The spreadsheet controls operations within the processor(s) of one or more vision system cameras. After selecting a range of cells in the spreadsheet, the user applies the system and method by pressing a button, or using a menu command that results in an automatically generated HMI with appropriate scaling of interface elements and a desired layout of such elements on the associated screen. Advantageously, the system and method essentially reduces the user's workflow to two steps, selecting spreadsheet cells and generating the HMI around them. The generated HMI runs in a web browser that can be instantiated on a user device, and communicates directly to a vision system processor(s). Data can pass directly between the user interface running in a web browser and the vision system processor(s).

Abstract: Our Names in physical and real world have transformed into ‘username’s in virtual digital world. Anything that we need to access in digital world asks us for a ‘username’, which can be user selected (like an e-mail address) or provided to a user (like an employee ID/Number). This ‘username’ has indeed become a SuperName, giving access to restricted areas, based on privileges, links to other services as well. So, to a cybercriminal, if a ‘username; is known, more than half the job is done. And once corresponding password is cracked, the whole digital identity lies threadbare. Damages done through transactions of such unauthorized access may get quantified, but dent to privacy is far more damaging.

Abstract: Systems and methods for providing called devices with sets of context data associated with communication sessions are disclosed. In one implementation, a method for generating context data associated with a communications session may include receiving, from a calling device at a first subsystem, a request to establish a communications session. The request may include a first identifier associated with the calling device. The method may further include receiving, at a second subsystem, activities data associated with the calling device that transmitted the request to establish the communications session. The activities data may include a second identifier associated with the calling device and may be indicative of device activities of the calling device.

Abstract: According to certain embodiments, a message bus system comprises a first client and a second client. The first client is configured to publish messages associated with a message topic to a message bus, and the second client is configured to receive the messages associated with the message topic from the message bus. The message bus system is configured to unsubscribe the second client from the message topic based at least in part on determining that a demand of the second client for the messages associated with the message topic has fallen below a threshold.

Abstract: Disclosed herein are systems and methods for providing mobile call authentication. For instance, a token indicative of a call request can be received from a calling party. The token can include a called party number and a time of the request. A subscriber database can be accessed to determine identifying information associated with the calling party based at least in part on the token. The token can be authenticated based at least in part on the identifying information and using one or more predefined authentication protocols. The token can be stored in a call session registry storing data indicative of a plurality of active telephone call events. A verification request for the call request can be received from the called party. The call request can be verified based at least in part on the token. The called party can be notified that the call request has been verified.

Abstract: Disclosed herein are systems and methods for providing optimal branded content to end consumers. The approach takes into account the different available branded display contents that are available, the different metrics that can drive choices, the technological parameters that can influence the provisioning of the branded display content. In addition, the preferences of the end consumer may also influence the provisioning of the branded display content.

Abstract: The present invention relates to techniques for activating a lock in a vehicle. Said techniques discuss capturing an image of an interior of the vehicle, the image comprising an occupant on a seat of the vehicle, detecting a weight value of the occupant on a respective seat of the vehicle, processing the image for determining whether the occupant is a human or an object or an animal. It further discusses in response to the determination that the occupant is the human processing the image for determining a parameter of the human, and activating a lock based on the parameter, or the weight value and the parameter.

Abstract: A dual-modulated QR code (DMQR code) is in the format of a conventional QR code but uses elongated markers instead of black squares in the code modules. The positions of the markers within the DMQR code represent a nonconfidential primary message, and the orientations of the markers within the modules of the DMQR code represent a confidential secondary message.

Abstract: A method is provided for unsupervised domain adaptation for video classification. The method learns a transformation for each target video clips taken from a set of target videos, responsive to original features extracted from the target video clips. The transformation corrects differences between a target domain corresponding to target video clips and a source domain corresponding to source video clips taken from a set of source videos. The method adapts the target to the source domain by applying the transformation to the original features extracted to obtain transformed features for the plurality of target video clips. The method converts the original and transformed features of same ones of the target video clips into a single classification feature for each of the target videos. The method classifies a new target video relative to the set of source videos using the single classification feature for each of the target videos.

Abstract: According to certain embodiments, a message bus system comprises a first client and a second client. The first client is configured to publish messages associated with a message topic to a message bus, and the second client is configured to receive the messages associated with the message topic from the message bus. The message bus system is configured to unsubscribe the second client from the message topic based at least in part on determining that a demand of the second client for the messages associated with the message topic has fallen below a threshold.

Abstract: According to certain embodiments, a message bus system comprises a first client and a second client. The first client is configured to publish messages associated with a message topic to a message bus, and the second client is configured to receive the messages associated with the message topic from the message bus. The message bus system is configured to unsubscribe the second client from the message topic based at least in part on determining that a demand of the second client for the messages associated with the message topic has fallen below a threshold.

Abstract: A method is provided for drone-video-based action recognition. The method learns a transformation for each of target video clips taken from a set of target videos, responsive to original features extracted from the target video clips. The transformation corrects differences between a target drone domain corresponding to the target video clips and a source non-drone domain corresponding to source video clips taken from a set of source videos. The method adapts the target to the source domain by applying the transformation to the original features to obtain transformed features for the target video clips. The method converts the original and transformed features of same ones of the target video clips into a single classification feature for each of the target videos. The method classifies a human action in a new target video relative to the set of source videos using the single classification feature for each of the target videos.

Abstract: Using various embodiments, methods and systems to provide safeguard a neighborhood or community are described. In one embodiment, a system is configured to receiving a license plate data of a vehicle, fetch indices of a set of known license plate data from a schema object, where the set includes vehicle license plate information of a plurality of vehicles of a neighborhood or community. In one embodiment, the set can be represented in memory using by a binary tree in memory. The system is then configured to sort the binary tree using a tree sorting algorithm. Thereafter, a tree searching algorithm is used to determine whether the license plate data is found in the binary tree. When the license plate data is found in the binary tree, it is determined that the vehicle is known to the neighborhood or community, otherwise it is determined to be not known.

Abstract: The present disclosure relates generally to systems, methods, and devices for closed loop deep brain stimulation. In particular, a neural signal is measured and provided to software. The software includes a feature generator and a brain network model that takes the neural signal and estimates other neural signals that are not directly measured, and operates as a model of the brain. The software determines a stimulation signal to be sent to stimulating electrodes. Estimated signals by the brain network model are continuously compared to actual signals from the brain. The closed loop feedback system advantageously allows for electrical stimulation levels and patterns to be continuously updated while delivered to a patient.

Abstract: A computer-implemented method is provided for domain adaptation between a source domain and a target domain. The method includes applying, by a hardware processor, an attention network to features extracted from images included in the source and target domains to provide attended features relating to a given task to be domain adapted between the source and target domains. The method further includes applying, by the hardware processor, a deformation network to at least some of the attended features to align the attended features between the source and target domains using warping to provide attended and warped features. The method also includes training, by the hardware processor, a target domain classifier using the images from the source domain. The method additionally includes classifying, by the hardware processor using the trained target domain classifier, at least one image from the target domain.

Abstract: Methods and systems for object detection include training dataset-specific object detectors using respective annotated datasets, each of the annotated datasets including annotations for a respective set of one or more object classes. The annotated datasets are cross-annotated using the dataset-specific object detectors. A unified object detector is trained, using the cross-annotated datasets, to detect all of the object classes of the annotated datasets. Objects are detected in an input image using the unified object detector.