Abstract: A set of adversarial training examples for training a query interpreter are generated by: obtaining a target data table for a natural language query; identifying a primary entity of the target data table; for a target domain of the target data table, generating a set of candidate identifiers that are each semantically associated with an identifier of the target domain; for each candidate identifier, providing a premise-hypothesis pair to an NLI model to generate an entailment score; selecting a first subset of candidate identifiers from among the set of candidate identifiers based on the entailment score generated for each premise-hypothesis pair; for each candidate identifier of the first subset, applying the candidate identifier to an instance of the target data table as a table perturbation to generate a perturbed data table; and outputting each perturbed data table as part of an adversarial training example.

Abstract: According to implementations of the subject matter described herein, a clause-based semantic parsing solution is provided. In the solution, a first clause with independent semantics is determined from a target statement. The target statement is converted to a first intermediate statement based on a first logical representation corresponding to the first clause. Subsequently, at least one logical representation corresponding to at least part of semantics of the first intermediate statement is determined. The first logical representation and the at least one logical representation may be used to determine a target logical representation corresponding to semantics of the target statement. Therefore, more accurate semantic parsing can be achieved.

Abstract: This application describes a system and method for diagnosing performance problems on a computing device or a network of computing devices. The application describes identifying common execution patterns between a plurality of execution paths being executed by a computing device or by a plurality of computing device over a network. The common execution pattern being based in part on common operations being performed by the execution paths, the commonality being independent of timing of the operations or the sequencing of the operations and individual executions paths can belong to one or more common execution patterns. Using lattice graph theory, relationships between the common execution patterns can be identified and used to diagnose performance problems on the computing device(s).

Abstract: Interactive multi-view video presents a new type of video capture system. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos are compressed in control PCs and are sent to a server in real-time. The compressed video can also be transcoded through an off-line compression approach to further reduce the data amount. Users can subscribe to a new type of service that allows users to connect to the servers and receive multi-view videos interactively.

Abstract: Interactive multi-view video presents new types of video capture systems, video formats, video compression algorithms, and services. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos are compressed in control PCs and are sent to a server in real-time. Users can subscribe to a new type of service that allows users to connect to the servers and receive multi-view videos interactively. In one embodiment of the invention, an automatic pattern-free calibration tool is employed to calibrate the multiple cameras. In contrast with a pattern-based method which uses the correspondences between image points and pattern points, the pattern-free calibration method is based on the correspondences between image points from different views.

Abstract: Interactive multi-view video presents new types of video capture systems, video formats, video compression algorithms, and services. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos and any associated audio streams are captured in a video beam format which allows for the efficient and expedient search of the vast amount of data in real-time and allows the data to be stored for off-line access.

Abstract: Interactive multi-view video presents new types of video capture systems, video formats, video compression algorithms, and services. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos are compressed and are sent to a server in real-time. The compressed video can also be transcoded through an off-line compression approach to further reduce the data amount. A key idea of off-line compression is to decompose all views into a 3D mapping, which consists of a group of feature points in the 3D environment. Each feature point is represented by its 3D coordinates (x, y, z) and the corresponding color components (Y, U, V). The created mapping is the minimum set of feature points that can reconstruct all of the pixels in each view. After the 3D mapping creation, the obtained feature points are predicted and transformed to further decompose the correlations among them. The transformed results are quantized and encoded as a ‘base layer’ bit stream.

Abstract: Interactive multi-view video presents new types of video capture systems, video formats, video compression algorithms, and services. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos are compressed and are sent to a server in real-time. Users can subscribe to a new type of service that allows users to connect to the servers and receive multi-view videos interactively. In addition to conventional playing controls, users can manipulate controls to the camera positions and orientations, select viewing directions and enjoy special effects such as a sweeping effect and a freeze-and-rotate effect, and so on. Interactive multi-view video provides a brand-new experience in watching events.

Abstract: Interactive multi-view video presents a new type of video capture system. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos are compressed in control PCs and are sent to a server in real-time. The compressed video can also be transcoded through an off-line compression approach to further reduce the data amount. Users can subscribe to a new type of service that allows users to connect to the servers and receive multi-view videos interactively.

Abstract: Interactive multi-view video presents new types of video capture systems, video formats, video compression algorithms, and services. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos and any associated audio streams are captured in a video beam format which allows for the efficient and expedient search of the vast amount of data in real-time and allows the data to be stored for off-line access.

Abstract: Interactive multi-view video presents new types of video capture systems, video formats, video compression algorithms, and services. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos are compressed and are sent to a server in real-time. A big difference from the conventional schemes and the on-line compression of the interactive multi-view video system of the invention lies in a unique “STATIC” mode that is introduced to speed up the predictive coding. To find the STATIC mode, it is necessary to calculate the difference between the original image and a reference image. To further reduce the computing complexity, the decision of whether to use this STATIC mode or not is determined jointly among all views.

Abstract: Interactive multi-view video presents new types of video capture systems, video formats, video compression algorithms, and services. Many video cameras are allocated to capture an event from various related locations and directions. The captured videos are compressed in control PCs and are sent to a server in real-time. Users can subscribe to a new type of service that allows users to connect to the servers and receive multi-view videos interactively. In one embodiment of the invention, an automatic pattern-free calibration tool is employed to calibrate the multiple cameras. In contrast with a pattern-based method which uses the correspondences between image points and pattern points, the pattern-free calibration method is based on the correspondences between image points from different views.