Google Inc.

Robert Boschgmbh

Sap Se

Thomas Kipf

Max Welling

Alexey Dosovitskiy

Michael Herman

Sara Sabour Rouh Aghdam

Georg Heigold

Austin Charles Stone

Gamaleldin Elsayed

Frans Adriaan Oliehoek

Elise Van Der Pol

Rico Jonschkowski

Aravindh Mahendran

Klaus Greff

A method includes obtaining first feature vectors and second feature vectors representing contents of a first and second image frame, respectively, of an input video. The method may also include generating, based on the first feature vectors, first slot vectors, where each slot vector represents attributes of a corresponding entity as represented in the first image frame, and generating, based on the first slot vectors, predicted slot vectors including a corresponding predicted slot vector that represents a transition of the attributes of the corresponding entity from the first to the second image frame. The method may additionally include generating, based on the predicted slot vectors and the second feature vectors, second slot vectors including a corresponding slot vector that represents the attributes of the corresponding entity as represented in the second image frame, and determining an output based on the predicted slot vectors or the second slot vectors.

Conditional object-centric learning with slot attention for video and other sequential data

Growing community of inventors

Amsterdam, Netherlands

Thomas Kipf