Google Inc.

International Business Machines Corporation

Mario Lucic

Birgit Monika Pfitzmann

Daniel M Keysers

George E Stark

Chen Sun

Alexey Dosovitskiy

Cordelia Luise Schmid

Dorothea W Wiesmann

Mostafa Dehghani

Jakob D Uszkoreit

Neil Matthew Tinmouth Houlsby

Ioana Giurgiu

Lucas Klaus Beyer

Alexander Kolesnikov

Xiaohua Zhai

Georg Heigold

Thomas Unterthiner

Yin Ching Jessica Yung

Anurag Arnab

Jasmina Bogojeska

David Lanyi

Ilya Tolstikhin

Andreas Peter Steiner

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using mixer neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more mixer neural network layers.

Multi-layer perceptron-based computer vision neural networks

A computer-implemented method for classifying video data with improved accuracy includes obtaining, by a computing system comprising one or more computing devices, video data comprising a plurality of video frames; extracting, by the computing system, a plurality of video tokens from the video data, the plurality of video tokens comprising a representation of spatiotemporal information in the video data; providing, by the computing system, the plurality of video tokens as input to a video understanding model, the video understanding model comprising a video transformer encoder model; and receiving, by the computing system, a classification output from the video understanding model.

Systems and methods for improved video understanding

In one embodiment, a computer-implemented method includes obtaining incident data related to a plurality of servers, including a first server. Configuration data is obtained for each of the plurality of servers. The configuration data includes information about a set of one or more configuration items of the first server. A predictive modeler is trained to predict incident characteristics, based at least in part on the incident data and the configuration data. A modification is selected to the set of configuration items of the first server. Predicted incident characteristics of the first server are simulated, by a computer processor, based on the selected modifications. It is recommended that the selected modifications be made to the first server if predetermined criteria are met by the simulation.

System recommendations based on incident analysis

Growing community of inventors

Adliswil, Switzerland

Mario Lucic