A method for scene perception using video captioning based on a spatio-temporal graph model is described. The method includes decomposing the spatio-temporal graph model of a scene in input video into a spatial graph and a temporal graph. The method also includes modeling a two branch framework having an object branch and a scene branch according to the spatial graph and the temporal graph to learn object interactions between the object branch and the scene branch. The method further includes transferring the learned object interactions from the object branch to the scene branch as privileged information. The method also includes captioning the scene by aligning language logits from the object branch and the scene branch according to the learned object interactions.

An apparatus links an entity in a first knowledge-graph with a word in a text. The apparatus, based on a number of first-edges coupled to each of first-nodes serving as a transition-source and a number of second-edges coupled to each of second-nodes serving as a transition-destination in the first knowledge-graph, identifies a third-edge to be deleted from edges coupled to a third-node among the second-nodes which has a preset input-order indicating a number of edges that transition to the third-node, and generates a second knowledge-graph by deleting the third-edge from the first knowledge-graph. The apparatus couples first and second nodes which have been coupled to each other by the third-edge in the first knowledge-graph, via a fourth-node to which the first and second nodes are coupled by edges in the second knowledge-graph, and provides the word in the text and the entity linked with the word to a user.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for clustering data are disclosed. In one aspect, a method includes the actions of receiving feature vectors. The actions further include accessing rules that each relate one or more values of the feature vectors to a respective label of a plurality of labels. The actions further include, based on the rules, generating heuristics that each identify related values of the feature vectors. The actions further include, for each of the heuristics, generating a matrix that reflects a similarity of the feature vectors. The actions further include, based on the matrices that each reflects a respective similarity of the feature vectors, generating clusters that each include a subset of the feature vectors. The actions further include, for each cluster, determining a label of the plurality of labels.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for clustering data are disclosed. In one aspect, a method includes the actions of receiving feature vectors. The actions further include accessing rules that each relate one or more values of the feature vectors to a respective label of a plurality of labels. The actions further include, based on the rules, generating heuristics that each identify related values of the feature vectors. The actions further include, for each of the heuristics, generating a matrix that reflects a similarity of the feature vectors. The actions further include, based on the matrices that each reflects a respective similarity of the feature vectors, generating clusters that each include a subset of the feature vectors. The actions further include, for each cluster, determining a label of the plurality of labels.

Systems, apparatuses and methods may provide for technology that identifies telemetry data associated with an execution of a cluster of artificial intelligence (AI) operations on an accelerated backend system, wherein the telemetry data includes one or more of temperature classifier data, compute classifier data or failure data, and determines whether to send a current instance of the cluster of AI operations to the accelerated backend system or a default backend system based on the telemetry data.

The present invention provides a method of generating a robust global map using a plurality of limited field-of-view cameras to capture an environment. Provided is a method for generating a three-dimensional map comprising: receiving a plurality of sequential image data wherein each of the plurality of sequential image data comprises a plurality of sequential images, further wherein the plurality of sequential images is obtained by a plurality of limited field-of-view image sensors; determining a pose of each of the plurality of sequential images of each of the plurality of sequential image data; determining one or more overlapping poses using the determined poses of the sequential image data; selecting at least one set of images from the plurality of sequential images wherein each set of images are determined to have overlapping poses; and constructing one or more map portions derived from each of the at least one set of images.

Methods, systems, and computer-readable storage media for providing, by a machine learning (ML) platform, a first binary classifier, processing, by the first binary classifier a super-set of invoices to provide a plurality of sets of invoices based on matching pairs of invoices in the super-set of invoices, providing, by the ML platform, a second binary classifier, processing, by the second binary classifier, a bank statement and the plurality of sets of invoices to define two or more super-invoices based on aggregate features of invoices in the plurality of sets of invoices, and match the bank statement to a super-invoice of the two or more super-invoices, and outputting a match of the bank statement to the super-invoice.

The invention relates to a machine-implementable method, preferably a computer-implemented method, and system for the selection of a set of dependent and independent variables to form quantity equations for engineering problems. The method includes the encoding and decoding of dimensionless groups in an integer lattice. A preferred embodiment of the invention considers an integer lattice given by the cartesian product .sub.2×.sup.7. The result of the method provides a system of quantity equations in the dependent and independent variables.

The invention relates to a machine-implementable method, preferably a computer-implemented method, and system for the selection of a set of dependent and independent variables to form quantity equations for engineering problems. The method includes the encoding and decoding of dimensionless groups in an integer lattice. A preferred embodiment of the invention considers an integer lattice given by the cartesian product .sub.2×.sup.7. The result of the method provides a system of quantity equations in the dependent and independent variables.

A method for capturing a scene in a virtual environment for an immersive reality application running in a headset is provided. The method includes determining initiation of an auto-capture session in a headset by a user, the headset running an immersive reality application hosted by a remote server, executing a gaze model based on the initiation, detecting through the gaze model a gaze of the user, tracking the gaze of the user, capturing a scene in a virtual environment based on the gaze of the user, and storing the scene as a media file in storage. A headset and a memory storing instructions to cause the headset and a remote server to perform the above method are also provided.