International Business Machines Corporation

University of Illinois

Sinem Guven Kaya

Bing Zhou

Ruchi Mahindru

Yu Deng

Larisa Shwartz

Shang Qing Guo

Lingfei Wu

Shu Tao

Xin Zhou

Martin Franz

Bruce David D'Amora

Rohan R Arora

Rajarshi Haldar

Julia Constanze Hockenmaier

Hui Kang

Noah Zheutlin

Meng Jiang

Qingkai Zeng

Wenhao Yu

Xinyu Que

Gerard Randolph Vanloo

Systems, computer-implemented methods, and computer program products to facilitate sparse depth completion with semantic mesh deformation optimization in an augmented reality environment are provided. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components comprise a depth completion component that generates a first depth map from an image and sparse depth samples. The computer executable components further comprise a semantic mesh deformation component that performs a semantic mesh deformation process, using the sparse depth samples, to generate a second depth map comprising a defined image accuracy.

Depth map generation from sparse depth samples in an augmented reality environment

Techniques facilitating anomaly detection and root cause analysis using distributed trace data. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components comprise: a preprocessing component; and a monitor component. The preprocessing component can generate a trace frame comprising a vectorized representation of textual trace data produced by microservices of a microservice application. The monitor component can identify a state of the microservice application using the trace frame.

Learning from distributed traces for anomaly detection and root cause analysis

A method for estimating response relevance with respect to a received query includes receiving a set of user feedback items, a set of historical feedback data, and a set of context data, creating a user profile model according to the set of historical feedback data, wherein the user profile model indicates a weighting attribute based on the set of historical feedback data, weighting the set of user feedback items according to the created user profile model, creating a response relevance estimation model based on the weighted set of user feedback items, the received set of context data, and the received set of historical feedback data, and ranking one or more responses according to the created response relevance estimation model. The method may further include adjusting the user profile model and the response relevance estimation model responsive to receiving additional data.

Query response relevance determination

An approach for a non-factoid question answering framework across tasks and domains may be provided. The approach may include training a multi-task joint learning model in a general domain. The approach may also include initializing the multi-task joint learning model in a specific target domain. The approach may include tuning the joint learning model in the target domain. The approach may include determining which task of the multiple tasks is more difficult for the multi-task joint learning model to learn. The approach may also include dynamically adjusting the weights of the multi-task joint learning model, allowing the model to concentrate on learning the more difficult learning task.

Non-factoid question answering across tasks and domains

Systems, computer-implemented methods, and computer program products to facilitate automatic multi-dimensional model generation and tracking in an augmented reality environment are provided. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components comprise a label component that annotates a multi-dimensional point cloud representation of an object present in augmented reality data. The computer executable components further comprise a content generation component that generates a multi-dimensional model of a component of the object based on the multi-dimensional point cloud representation.

Automatic multi-dimensional model generation and tracking in an augmented reality environment

Systems, devices, computer-implemented methods, and/or computer program products that facilitate event schema induction from unstructured or semi-structured data. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a schema component and a retrieval component. The schema component can derive an event schema for a document corpus using parsing results obtained from the document corpus. The retrieval component can populate a response to a query with a document of the document corpus using events extracted from the query and the document using the event schema.

Graph-based event schema induction for information retrieval

Embodiments relate to an intelligent computer platform to multi-dimensionally optimize device operation. Static hardware device data are acquired and dynamic hardware characteristic data are tracked over one or more temporal segments. A neural model (NM) is trained with corresponding device and network data. The acquired static and dynamic data are input into the NM, and locale processing patterns corresponding to the inputted data are identified. One or more data points and corresponding measurements of the tracked dynamic hardware characteristic data are temporally analyzed. A processing locale corresponding to the temporal analysis is identified and returned as output data, and one or more encoded actions in compliance with the identified processing locale are selectively implemented.

Optimization framework for real-time rendering of media using machine learning techniques

Obtain access to a three-dimensional point cloud representation of an object including poses of a scanning digital camera and corresponding video frames. Down-sample the three-dimensional point cloud representation to obtain a set of region-of-interest candidates. Filter the region-of-interest candidates to select those of the region-of-interest candidates having appearance changes, which distinguish different visual states, as selected regions of interest, based at least in part on the poses of the camera. Generate region of interest images for the selected regions of interest from corresponding ones of the video frames; and train a deep learning recognition model based on the region of interest images. the trained deep learning recognition model can be used, for example, to determine a visual state of the object for repair instructions.

Fine-grained visual recognition in mobile augmented reality

A method, computer system, and a computer program product for intelligently generating an augmented reality (AR)-assisted repair guidance for a user is provided. The present invention may include detecting a scan of an object. The present invention may then include filtering one or more pose-controlled video frames. The present invention may also include extracting at least one new image feature by utilizing a convolutional neural network (CNN) based on the filtered one or more pose-controlled video frames. The present invention may also include aggregating a plurality of visual information associated with the object by utilizing the CNN, wherein the extracted at least one new image feature is included in the aggregated plurality of visual information. The present invention may further include presenting three dimensional (3D) animated instructions to the user, wherein the 3D animated instructions include an AR-assisted repair guidance for the object.

Active visual recognition in mobile augmented reality

Web navigation pattern histories are used to navigate to a plurality of visited web sites. A navigation map is generated comprised of a node for each visited web site. Each node in the navigation map is connected by an edge to at least one other node in the navigation map, and the edge is associated with the link from the given visited web site to the next web site. For each visited web site, the corresponding node stores an address for the given web site, a relevance rating for the given visited web site, a link from the given visited web site to a next web site and optionally a title of the web site. A presentation of a node in the navigation map is based on the relevance rating. A plurality of navigation maps for a plurality of users can be merged by identifying navigation maps having similar search goals.

Growing community of inventors

New York, NY, United States of America

Sinem Guven Kaya