Abstract: Example implementations are directed to a method of receiving information associated with an activity, analyzing the information to identify a first pattern and a second pattern, and generating a customized recommendation model for the second pattern based on the first pattern. In response to a detected trigger indicating a transition to the second pattern, the method assesses context factors to verify the transition to the second pattern without interrupting the first pattern. Based on the verification, the method applies the model to provide redirection based on the recommendation.

Abstract: A computer-implemented method, comprising, extracting a video sequence, the video sequence including a series of video frames, estimating current poses of one or more subjects within each video frame and determining joint locations for a joint associated with the one or more subjects within each video frame, computing optical flows from the video sequence, extracting motion features from the video sequence based on the optical flows, and predicting at least one future pose.

Abstract: To prevent the spread of hospital-acquired infections, embodiments described herein monitor mobile device usage in clinical settings (by a physician, nurse, etc.) to characterize potential pathogenic contamination of the mobile device, the user's hands, and the surfaces in contact with the device. Our method considers the physical properties of how the device is handled and held during use, as well as the location and setting before, during, and after use to estimate potential contamination and transmission of pathogens. A system can use the estimation, along with knowledge (e.g., of the user's upcoming schedule) to alert them of potential contamination hazards and suggest when to avoid mobile device use as well as when to sanitize the device and user's hands.

Abstract: A computer-implemented method, comprising, extracting a video sequence, the video sequence including a series of video frames, estimating current poses of one or more subjects within each video frame and determining joint locations for a joint associated with the one or more subjects within each video frame, computing optical flows from the video sequence, extracting motion features from the video sequence based on the optical flows, and predicting at least one future pose.

Abstract: Example implementations are directed to systems and methods for a context aware conversational agent for self-learning. In an example implementation, a method includes generating a journaling model based on activity data and engagement data associated with one or more tasks of a user. The journaling model uses machine-learning to identify a context pattern using the activity data, and maps performance associated with the one or more tasks based at least on the engagement data. The method adaptively provides a prompt to gather additional engagement data based on the context pattern in view of real-time activity data, where the prompt is generated based on the journaling model. The journaling model is updated based on the additional engagement data.

Abstract: Example implementations described herein are directed to a dual interface system configured to facilitate and analyze micro-journal entries. Example implementations can involve providing a first interface directed at a plurality of organizations, the first interface configured to receive micro-journal entries; aggregating the micro-journal entries across the plurality of organizations; providing analytics results of the micro-journal entries across the plurality of organizations to a second interface; receiving, through the second interface, a selection of an organization from the plurality of organizations for pushing a prompt based on the analytics results; and configuring the first interface of the selected organization from the plurality of organizations to provide the prompt, the prompt configured to receive additional micro-journal entries.

Abstract: Systems and methods of the present disclosure can involve several work spaces wherein each of the work spaces are associated with a set of activities and wherein each of the work spaces are coupled to one or more radio frequency (RF) sensors. Through RF sensor data detected from interactions with the work surface, example implementations described herein can determine which activity from the set of activities is being conducted through the application of a recognition algorithm that is generated from a machine learning algorithm.

Abstract: A computer-implemented method, comprising extracting each frame of a video sequence, estimating current poses of a subject within each frame and determining joint locations for a joint associated with the subject within each frame, computing optical flows between each pair of consecutive video frames, extracting motion features from each video frame of the video sequence based on the optical flows, encoding state information based on the current poses and the motion features, determining a current action label for each motion feature in the state information for a first frame; predicting future action labels for each motion feature in a second frame subsequent to the first frame, based on the current pose, action label and state information, predicting future poses for each motion feature in the second frame based on the current poses and the state information; and refining the current action label, the future action labels, and the future poses.

Abstract: Recent technical advances have expanded the breadth, scope, and affordability of virtual reality (VR) and augmented reality (AR) systems. More people can use VR and AR systems than ever before. However, hand-held physical controls for these systems have not made similar advances yet. For this reason, it remains difficult for developers to create applications that take advantage of the full range of human abilities. In this proposal, we describe a system and method for combining off-the-shelf smartwatches with a set of inexpensive grips or sheaths to control VR/AR systems. With our approach, all of the computation and power for the controller derive from the smartwatch unit, allowing the grips to take almost any form, and allowing developers and designers to integrate a much wider array of interaction styles into their applications.

Abstract: A computer-implemented method is provided for receiving a request from a third party source or on a template to generate a payload, receiving live video via a viewer, and performing recognition on an object in the live video to determine whether the object is an item in the payload, filtering the object against a threshold indicative of a likelihood of the object matching a determination of the recognition, receiving an input indicative of a selection of the item, and updating the template based on the received input, and providing information associated with the object to complete the request.

Abstract: Example implementations are directed to a method of receiving information associated with an activity, analyze the information to identify a first pattern and a second pattern, generate a customized transition model for returning to the first pattern. In response to a detected trigger indicating a transition to the first pattern, the method assesses context factors to apply the customized transition to dynamically manage access to digital resources during the transition to the first pattern. In response to a determination that a transition to the first pattern satisfies a threshold, the method restores access to the digital resources.

Abstract: To prevent the spread of hospital-acquired infections, embodiments described herein monitor mobile device usage in clinical settings (by a physician, nurse, etc.) to characterize potential pathogenic contamination of the mobile device, the user's hands, and the surfaces in contact with the device. Our method considers the physical properties of how the device is handled and held during use, as well as the location and setting before, during, and after use to estimate potential contamination and transmission of pathogens. A system can use the estimation, along with knowledge (e.g., of the user's upcoming schedule) to alert them of potential contamination hazards and suggest when to avoid mobile device use as well as when to sanitize the device and user's hands.

Abstract: Recent technical advances have expanded the breadth, scope, and affordability of virtual reality (VR) and augmented reality (AR) systems. More people can use VR and AR systems than ever before. However, hand-held physical controls for these systems have not made similar advances yet. For this reason, it remains difficult for developers to create applications that take advantage of the full range of human abilities. In this proposal, we describe a system and method for combining off-the-shelf smartwatches with a set of inexpensive grips or sheaths to control VR/AR systems. With our approach, all of the computation and power for the controller derive from the smartwatch unit, allowing the grips to take almost any form, and allowing developers and designers to integrate a much wider array of interaction styles into their applications.

Abstract: A method of controlling access to an enclosed area having a boundary includes generating a first inaudible audio signal inside the enclosed area, and generating a second signal, each configured to be sensed by a sensing device, wherein the first inaudible audio signal is not capable of penetrating the boundary; determining a state of the enclosed area, based on either the first inaudible audio signal, or the first inaudible audio signal and the second signal, being sensed by the sensing device; and based on the state, generating an instruction to perform access control for the enclosed area.

Abstract: A method of controlling access to an enclosed area having a boundary includes generating a first inaudible audio signal inside the enclosed area, and generating a second signal, each configured to be sensed by a sensing device, wherein the first inaudible audio signal is not capable of penetrating the boundary; determining a state of the enclosed area, based on either the first inaudible audio signal, or the first inaudible audio signal and the second signal, being sensed by the sensing device; and based on the state, generating an instruction to perform access control for the enclosed area.

Abstract: Example implementations are directed to methods and systems for curating messages from viewers to identify a question associated with a recorded video that include video data, where the question is extracted from a queue of the video data; analyze the video data to determine one or more answer segments for the question that satisfy a confidence score based on a location of the question in the recorded video; and generate an answer summary for the question with links to each of the one or more segments, where the links are ranked based on the confidence score.

Abstract: Example implementations are directed to systems and methods for a context aware conversational agent for self-learning. In an example implementation, a method includes generating a journaling model based on activity data and engagement data associated with one or more tasks of a user. The journaling model uses machine-learning to identify a context pattern using the activity data, and maps performance associated with the one or more tasks based at least on the engagement data. The method adaptively provides a prompt to gather additional engagement data based on the context pattern in view of real-time activity data, where the prompt is generated based on the journaling model. The journaling model is updated based on the additional engagement data.

Abstract: In one embodiment, an apparatus includes a processor circuit; a media distribution component for execution on the processor circuit to manage presentation of a media presentation on multiple electronic displays, the media presentation comprising a video part and an auxiliary data part, the auxiliary data part comprising sensor data corresponding to the video part, the media distribution component to manage presentation of the video part on an external display and the auxiliary data part on an integrated display. Other embodiments are disclosed and claimed.

Abstract: Example implementations are directed to methods and systems for curating messages from viewers to identify a question associated with a recorded video that include video data, where the question is extracted from a queue of the video data; analyze the video data to determine one or more answer segments for the question that satisfy a confidence score based on a location of the question in the recorded video; and generate an answer summary for the question with links to each of the one or more segments, where the links are ranked based on the confidence score.

Abstract: Systems and methods of the present disclosure can involve several work spaces wherein each of the work spaces are associated with a set of activities and wherein each of the work spaces are coupled to one or more radio frequency (RF) sensors. Through RF sensor data detected from interactions with the work surface, example implementations described herein can determine which activity from the set of activities is being conducted through the application of a recognition algorithm that is generated from a machine learning algorithm.