Abstract: The present invention provides a method for providing augmented product specifications based on user reviews. The method obtains input data of specifications and user reviews on a plurality of products, each specification including at least a pair of a feature and a feature-value of the product. The method concatenates the user reviews of the products to form product-documents, each product-document corresponding to the concatenated user reviews of a product. The method further employs a topic model to process the input data and learn topic distributions in the product-documents and word distributions in topics. The topics include specifications of the products. The topic model is a type of statistical model for discovering topics that occur in a collection of product-documents. Based on the topic model, the method can provide augmented specifications including one or more of relevant sentences of the feature-value, feature importance information, and product-specific words of the product.

Abstract: A method for a mobile search-ready smart display system containing a smart display having a screen and at least one mobile device having a camera including extracting a plurality of video fingerprints from an ongoing content displayed on the screen. The ongoing content has video frames corresponding to the video fingerprints; determining one or more representative video fingerprints of the video frames from the plurality of video fingerprints; generating one or more encoded representative video fingerprints through encoding the one or more representative video fingerprints into a pixel translucency change; and delivering the one or more encoded representative video fingerprints via a screen-camera communication. The method also includes optimizing the encoding of the one or more representative video fingerprints and the delivering of the one or more encoded representative video fingerprints to find a balance between an error resilience and transmission time.

Abstract: In accordance with various embodiments of the disclosed subject matter, a method and a system for vision-centric deep-learning-based road situation analysis are provided. The method can include: receiving real-time traffic environment visual input from a camera; determining, using a ROLO engine, at least one initial region of interest from the real-time traffic environment visual input by using a CNN training method; verifying the at least one initial region of interest to determine if a detected object in the at least one initial region of interest is a candidate object to be tracked; using LSTMs to track the detected object based on the real-time traffic environment visual input, and predicting a future status of the detected object by using the CNN training method; and determining if a warning signal is to be presented to a driver of a vehicle based on the predicted future status of the detected object.

Abstract: A method and a non-transitory computer-readable medium having computer program for optimizing a system function-flow of a system capable of performing at least one function and comprising a plurality of components by utilizing application programming interface (API) profiling are provided. The method comprises receiving a request to perform the at least one function of the system from a user; obtaining at least one component required to realize the at least one function requested by the user from the plurality of the components; providing a plurality of APIs to the at least one obtained component to choose from; profiling each of the plurality of APIs to get a performance score of each API; based on the profiled APIs, optimizing the system function-flow of the system; determining corresponding APIs for the optimized system function-flow; and performing the at least one function requested by the user based on the determined APIs.

Abstract: A video retrieval method is provided. The method includes dividing video sequences stored in a video database into a plurality of video frames, extracting by a predetermined feature extracting algorithm a plurality of selected fingerprints from the plurality of video frames representing features having characteristic information specific to the plurality of video frames, and storing the plurality of extracted selected fingerprints in a fingerprint database. The method also includes receiving a query video sequence submitted by a user, extracting by the predetermined feature extracting algorithm at least one query fingerprint representing at least one query frame from the received query video sequence, and calculating similarity between the query fingerprint and the selected fingerprints from the fingerprint database to search for a match for the query fingerprint.

Abstract: A method is provided for providing desired application usage experience to a user on a user device. The method includes automatically converting a plurality of App pages into FUNC descriptors to be stored, wherein each FUNC descriptor includes at least non-functional properties of a FUNC, capability of the FUNC, and an interface of the FUNC to invoke the FUNC. The method also includes obtaining at least one user intention inputted by the user; determining at least one FUNC descriptor from the FUNC descriptors for fulfilling the user intention; recommending to the user with at least one FUNC corresponding to the at least one FUNC descriptor by rendering the at least one FUNC descriptor on the user device; and invoking the at least one FUNC directly from the user device without going through a launching page of an App page providing the at least one FUNC.

Abstract: A method for a conversational recommender system includes receiving at least one user preference from a user, generating an abstract explanation reflecting the at least one user preference and based on the abstract explanation, and retrieving a list of items to be evaluated by the user from an item database. The items on the list have a relevance with the user preference. The method further includes determining an initial ranking order of the items to be evaluated by the user, and ranking the items to be evaluated by the user based on a random walk algorithm and the initial ranking order. Items not ranked are remaining items. The method further includes receiving a user feedback of the ranked item, and re-ranking the remaining items based on the user feedback of the ranked items and the random walk algorithm.

Abstract: The present disclosure provides a time-value estimation method for sharing environment, including obtaining time-values of a plurality of shared items from a sharing platform. A time-value is a time duration for the shared item to be shared or traded. Further, a plurality of features of the plurality of shared items from the sharing platform may be extracted. The features may include objective-level features related to a specific item and subjective-level features related to an owner of the specific item. A time-value model may be trained to obtain a time-value estimation function based on the time-values of the plurality of shared items and the plurality of features of the plurality of shared items. The method may further include estimating a time-value of an item in the sharing platform based on the plurality of features of the item and the time-value estimation function.

Abstract: A method for a mobile search-ready smart display system containing a smart display having a screen and at least one mobile device having a camera including extracting a plurality of video fingerprints from an ongoing content displayed on the screen. The ongoing content has video frames corresponding to the video fingerprints; determining one or more representative video fingerprints of the video frames from the plurality of video fingerprints; generating one or more encoded representative video fingerprints through encoding the one or more representative video fingerprints into a pixel translucency change; and delivering the one or more encoded representative video fingerprints via a screen-camera communication. The method also includes optimizing the encoding of the one or more representative video fingerprints and the delivering of the one or more encoded representative video fingerprints to find a balance between an error resilience and transmission time.

Abstract: The present invention provides a method for converting a low dynamic range (LDR) image to a high dynamic range (HDR) image, including obtaining an input LDR image; and in an HDR image database, selecting one or more HDR images that match the input LDR image as candidate images. Further, the candidate images are warped according to a spatial correspondence between the candidate images and the input LDR image. The input LDR image is decomposed to an illumination component and a texture component. The illumination component and the texture component are reconstructed respectively based on the warped candidate images. The reconstructed illumination component and the reconstructed texture component are combined to produce an output HDR image.

Abstract: The present disclosure provides a method for grouping devices in a same place. A plurality of devices may be connected to a server. The devices may be classified two types based on mobility, including a stable device type and a mobile device type. One or more neighborhood devices associated with at least one stable device may be identified based on status information of the plurality of devices. The at least one stable device and the one or more neighborhood devices may respectively record an audio sample at a set time. A similarity score between the audio sample of the one or more neighborhood devices and the audio sample of the at least one stable device may be calculated. Further, one or more devices among the one or more neighborhood devices may be determined as in a same space as the at least one stable device based on the similarity score.

Abstract: The present invention provides a method for converting a low dynamic range (LDR) image to a high dynamic range (HDR) image, including obtaining an input LDR image; and in an HDR image database, selecting one or more HDR images that match the input LDR image as candidate images. Further, the candidate images are warped according to a spatial correspondence between the candidate images and the input LDR image. The input LDR image is decomposed to an illumination component and a texture component. The illumination component and the texture component are reconstructed respectively based on the warped candidate images. The reconstructed illumination component and the reconstructed texture component are combined to produce an output HDR image.

Abstract: The present invention provides a method a method for learning and using relationships among users and apps on a mobile device. The method includes collecting user profile information and app profile information on the mobile device and obtaining ontology knowledge on contexts and relationships. The user profile information is associated with users including one or more owners of the mobile device and one or more people whose information have been accessed on the mobile device. The method further includes generating a network model based on the user profile information, the app profile information and the ontology knowledge. The network model is a heterogeneous information network model that links the users and the apps. Further, information based on the generated network model are outputted, which at least one of a role of a user, a relationship between two apps or app functions, and a recommended apps list.

Abstract: A method is provided for recommending a desired func sequence schedule to a user. The method includes obtaining at least one user intention inputted by the user; creating a func sequence including a plurality of funcs for fulfilling the user intention; and determining user preference on scheduling of the plurality of funcs in the func sequence. The method also includes determining a dependency relationship among the plurality of funcs in the func sequence; and determining scheduling constraints to the scheduling of the plurality of funcs in the func sequence. The method further includes, based on the user preference, the dependency relationship, and the scheduling constraints, performing an optimization process to determine a desired schedule for the plurality of funcs in the func sequence to fulfill the user intention; and recommending the func sequence with the desired schedule to the user.

Abstract: The disclosure is directed to techniques for content-adaptive background skipping for region-of-interest (ROI) video coding. The techniques may be useful in video telephony (VT) applications such as video streaming and videoconferencing, and especially useful in low bit-rate wireless communication applications, such as mobile VT. The disclosed techniques analyze content information of a video frame to dynamically determine whether to skip a non-ROI area within the frame. For example, the skipping determination may be based on content activity, such as ROI shape deformation, ROI motion, non-ROI motion, non-ROI texture complexity, and accumulated distortion due to non-ROI skipping. The skip determination may operate in conjunction with either frame-level or macroblock-level bit allocation.

Abstract: A method is provided for personalized video recommendation based on user interests modeling. The method includes detecting a viewing activity of at least one user of a content-presentation device capable of presenting multiple programs in one or more channels, and representing user interests of the at least one user by using a topic model. The method also includes discovering the user interests from user viewing histories, and generating a personalized video list of personalized video contents. Further, the method includes recommending the personalized video contents to the at least one user; and delivering the recommended personalized video to the at least one user such that the personalized video contents are presented on the content-presentation device.

Abstract: A method is provided for recommending a desired func sequence to a user. The method includes obtaining a user intention list including at least one user intention; separating the user intention into a plurality of tasks; and creating a task flow graph for the plurality of tasks based on user usage data. Each vertex in the task flow graph represents a task and indicating an importance of the task. The method also includes creating a func flow graph based on the user usage data and temporal sequences of the tasks and funcs, and each vertex in the func flow graph represents a func and indicating an importance of the func. Further, the method includes determining a desired func sequence to fulfill the user intention based on the user usage data, the task flow graph, and the func flow graph; and recommending the desired func sequence to the user.

Abstract: An inter-app switching method on a mobile device is provided. The method includes receiving at least one input associated with mobile app usage from a user and determining whether a pre-defined trigger is enabled based on the at least one received input. The method also includes performing routine user operations on the mobile device when the pre-defined trigger is disabled. Further, the method includes discovering a current user intent by utilizing at least one user interaction, recommending at least one mobile app recommendation and access point including at least an entrance to a function and a type of the function (FUNC) to the user, receiving a selection by the user from the at least one recommended FUNC, and directly switching from a current app page to another app page without returning to any home screen on the mobile device when the pre-defined trigger is enabled.

Abstract: A method for balancing recognition accuracy and power consumption is provided. The method includes activating a plurality of sensors onboard a device for a first time period and calculating sensor readings by using a calculation function. The method also includes determining a plurality of sensor subsets of the plurality of sensors and calculating corresponding errors for the plurality of sensor subsets for the first time period. Further, the method includes calculating respective power consumption of running the sensor subsets of the plurality of sensors from the plurality of sensor subsets that produce the error below the user-defined error threshold and selecting a sensor subset with minimum power consumption from the sensor subsets as an optimal sensor subset. In addition, the method includes deactivating the plurality of sensors not in the optimal sensor subset and calculating and displaying sensor readings with the optimal sensor subset for a second time period.

Abstract: The present invention provides a focal-point based recommendation method and system. The method includes collecting textual information displayed on a screen of the mobile terminal; identifying one or more focal points on the screen from a user; collecting contextual information of the mobile terminal; and suggesting one or more point-of-interests (POIs) to the user based on the textual information, the focal points and the contextual information. Further, when the user selects one or more POIs, based on the selected POIs, one or more contents are recommended to the user. The contents include at least one of an app content and an app function.