Abstract: Example implementations are directed to systems and methods for developing a topic model for a set of video series that include overlapping topics, wherein each video series includes segments directed to one or more of topics, wherein the topic model is based on topic distributions detected from the segments; analyzing auxiliary information, for each video series, to determine sequence information for the segments of the video series; and generating an array for topic transitions using sequence pattern mining on the distributions and the sequence information, wherein a next segment is determined for a selected segment based on an alignment decision using the array and sequence based scoring.

Abstract: A method of generating a caption for a social media post is provided. The method may include receiving a social media post to be posted to a social media network; collecting reference data relevant to determining common activities occurring at a category of location associated with the social media post; inferring potential topics for captions from a topic inference model, based on the collected reference data associated with the social media post; setting parameters associated with a language model based on the inferred topic; and generating at least one caption for the social media post based on the identified language model, and the inferred topic.

Abstract: Online educational videos are often difficult to navigate. Furthermore, most video interfaces do not lend themselves to note-taking. Described system detects and reuses boundaries that tend to occur in these types of videos. In particular, many educational videos are organized around distinct breaks that correspond to slide changes, scroll events, or a combination of both. Described algorithms can detect these structural changes in the video content. From these events the system can generate navigable overviews to help users searching for specific content. Furthermore, these boundary events can help the system automatically associate rich media annotations to manually-defined bookmarks. Finally, when manual or automatically recovered spoken transcripts are available, the spoken text can be combined with the temporal segmentation implied by detected events for video indexing and retrieval. This text can also be used to seed a set of text annotations for user selection or be combined with user text input.

Abstract: An augmented reality (AR) environment synchronization method, includes, for each of a plurality of devices associated with respective users in the AR environment, receiving plane information, and generating object/unique identifier information; across the devices, coordinating the plane information; performing context-aware matching of the object/unique identifier information across the devices to generate a match between respective objects sensed by the devices; and providing synchronization control to the devices, to permit an annotation of the matched object to be locked to a landmark and the plane of one of the devices with respect to others of the devices.

Abstract: A method of visualizing recommended pieces of media content is provided. The method includes identifying at least one piece of media content associated with a received content feature associated with a viewed piece of media content, selecting at least one additional piece of media content linked to the viewed piece of media content by a sequential relationship, generating a two-dimensional visualization based on a content similarity between the identified at least one piece of media content, the viewed piece of media content, and the selected at least one additional piece of media content and the sequential relationship; and displaying the generated two-dimensional visualization.

Abstract: A method of converting a document from a first structure to a second structure, includes extracting data of the document to associate a field and a label in the first structure to generate a field/label association, receiving operator input indicative of associating a field/label association with one or more other field/label associations to generate a grouping, and based on the operator input and a spatial arrangement of the first structure, providing the grouping in the second structure as a natural conversational unit.

Abstract: For tourists, interactions with digital public displays often depend on specific technologies that users may not be familiar with (Quick Response codes, near field communication, and so on) may not have access to because of networking issues, may lack a required application or device technology, may not want to use because of time constraints, or may not want to use because they are worried about sharing their data with a third-party service. Example implementations described herein are directed to a system that allows users to seamlessly share content with a public travel kiosk system.

Abstract: Example implementations described herein are directed to systems and methods for providing documents in the chat of a chat application. Example implementations can involve detecting, in a chat of a chat application, an indication to edit a document; inserting a fragment of the document into the chat of the chat application, the fragment configured to be editable within the chat of the chat application; and modifying the document based on input provided to the fragment of the document in the chat of the chat application.

Abstract: Example implementations are directed to systems and methods for developing a topic model for a set of video series that include overlapping topics, wherein each video series includes segments directed to one or more of topics, wherein the topic model is based on topic distributions detected from the segments; analyzing auxiliary information, for each video series, to determine sequence information for the segments of the video series; and generating an array for topic transitions using sequence pattern mining on the distributions and the sequence information, wherein a next segment is determined for a selected segment based on an alignment decision using the array and sequence based scoring.

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: A computer-implemented method, the method being performed in a system comprising an electronic lock and a client device comprising a central processing unit, a localization signal receiver and a memory, the computer-implemented method comprising: receiving at least one localization signal using the localization signal receiver; measuring a strength of the received localization signal; using the central processing unit to extract a identifier from the received localization signal; determining a location of the client device based at least on the measured strength of the received localization signal and the extracted identifier; and causing the electronic lock to unlock based on the determined location.

Abstract: Example implementations described herein are directed to a system for inserting document links or document fragments in messaging applications. For input provided to a messaging application, example implementations can parse the input to determine document parameters, determine previously linked documents in messages of the messaging application corresponding to the document parameters; and embed at least one of a selected document fragment or document link from the determined previously linked documents.

Abstract: Systems and methods for generating an overview for videos by reconstructing a representation of underlying content and linking from points in the overview to specific points in the video. Mechanisms are provided to create three different types of navigable overviews for different types of how-to and instructional videos. A two-dimensional overview is generated when content is two-dimensional, such as instructional videos on electronic whiteboard or other flat content. The three-dimensional overview is created when the content is three-dimensional, such as how-to videos illustrating the use of specific three-dimensional tangible articles. In three-dimensional case, when 3D model is available, the video segments are directly linked to corresponding points on the model. When a model is not available, a rough overview is first created from the captured video and camera orientation metadata.

Abstract: System that automatically embeds interactive document snippets inside chat conversation stream. Specifically, described are techniques to automatically crop meaningful areas on document pages based on users' actions and underlying content to embed them inside chat window. Embedded snippets are easy to view because smart cropping provides viewers enough context. Snippets are playable inside the chat window so users can view the snippet without having to open the corresponding document. Importantly, viewers can reply inline to a document snippet, also without having to open the original document page. Like traditional text messages, snippets are appended to the conversation chat window, allowing co-workers to see what was added. When users choose to focus on document itself (as opposed to working inside the chat window only), the system automatically shows all relevant document snippets as well as chat messages, helping the person quickly see what conversations happened around this part of the document.

Abstract: Systems and methods for generating an overview for videos by reconstructing a representation of underlying content and linking from points in the overview to specific points in the video. Mechanisms are provided to create three different types of navigable overviews for different types of how-to and instructional videos. A two-dimensional overview is generated when content is two-dimensional, such as instructional videos on electronic whiteboard or other flat content. The three-dimensional overview is created when the content is three-dimensional, such as how-to videos illustrating the use of specific three-dimensional tangible articles. In three-dimensional case, when 3D model is available, the video segments are directly linked to corresponding points on the model. When a model is not available, a rough overview is first created from the captured video and camera orientation metadata.

Abstract: A method and system for generating recommendations. The method including extracting concept information from visual content associated with content posted to a social media platform, detecting one or more preferences based on the extracted concept information, generating a matrix based on the detected one or more preferences, calculating a first similarity between the one or more preferences associated with a first user and one or more preferences associated with a second user based on the generated matrix, and generating a recommendation based on the matrix and the calculated first similarity.

Abstract: Example implementations provide the representation a remote user in a video-mediated meeting when the user webcam feed is not available or not used, such as if they are attending to a meeting via a wearable device without a camera, or are on-the-go and prefer not to display their webcam feed for privacy or bandwidth-related reasons. In such cases, the system will infer when the user is active in the meeting and allow users to select to display an animated set of keyframes (from past meetings or representing computer-based activity) as a proxy for the user representation. Example implementations may facilitate a richer representation of a meeting participant (as opposed to a static picture or no information) and may lead to enhanced social dynamics within the meeting.

Abstract: Example implementations described herein are directed to systems and methods for representing meeting content. Such implementations may involve processing an online presentation for one or more media segments, extracting information from the one or more media segments indicative of one or more relationships between one or more participants of the online presentation and generating an interface for the online presentation, the interface indicative of the one or more relationships between the one or more participants of the online presentation. Through such example implementations, online presentations can be indexed and an interface can be generated for the online presentation that allows for content of the presentation to be searchable.

Abstract: A computer-implemented method, the method being performed in a system comprising an electronic lock and a client device comprising a central processing unit, a localization signal receiver and a memory, the computer-implemented method comprising: receiving at least one localization signal using the localization signal receiver; measuring a strength of the received localization signal; using the central processing unit to extract a identifier from the received localization signal; determining a location of the client device based at least on the measured strength of the received localization signal and the extracted identifier; and causing the electronic lock to unlock based on the determined location.

Abstract: Example implementations provide the representation a remote user in a video-mediated meeting when the user webcam feed is not available or not used, such as if they are attending to a meeting via a wearable device without a camera, or are on-the-go and prefer not to display their webcam feed for privacy or bandwidth-related reasons. In such cases, the system will infer when the user is active in the meeting and allow users to select to display an animated set of keyframes (from past meetings or representing computer-based activity) as a proxy for the user representation. Example implementations may facilitate a richer representation of a meeting participant (as opposed to a static picture or no information) and may lead to enhanced social dynamics within the meeting.