Abstract: The invention relates to a method (100) for providing synthetic data for use in machine learning, wherein the synthetic data comprise synthetic, photorealistic image information, said method comprising the following method steps: generating (101) simulation data, wherein the simulation data are in the form of annotated data and are generated by a simulation environment, determining (102) annotations from the generated simulation data, generating (103) the synthetic data by means of semantic image synthesis (SIS) using the determined annotations as input for the semantic image synthesis (SIS), annotating (104) the generated synthetic data based on an output from the simulation environment.

Abstract: The invention relates to a method (100) for an automated generation of synthetic scenes (175), comprising the following steps: providing (101) scene data (110) representing a plurality of template scenes (120), providing (102) object data (115) specifying various objects (125) for insertion into the synthetic scene (175), providing (103) at least one scene parameter (130) for the template scenes (120), which describes at least one characteristic of the template scenes (120), generating (106) intermediate representations (140) for the synthetic scenes (175), wherein, regarding the intermediate representations (140), at least one selected object (125) is in each case inserted into a selected template scene (120), wherein the insertion of the at least one selected object (125) is parametrized based on the provided scene parameter (130) in order to account for physical plausibility in the respective intermediate representation (140), determining (107) conditioning data (150) from the generated intermediate rep

Abstract: A method and video capture device is provided having a front camera for capturing images of a front scene initially having an object of interest for the user of the device. A rear camera is also included and configured to capture images of the head of a user of the device. The rear camera also includes a processing circuit to estimate the eye movement of the user and the displacement of the object of interest in the front scene captured from the estimated eye movement of the user. The rear camera further includes a decision making circuit to determine, from the estimated displacement of the object of interest, if the object of interest leaves the captured front scene and, when that is the case triggers an action.

Abstract: A technique for improving the performance of image classification systems is proposed which consists of learning an adaptation architecture on top of the input features jointly with linear classifiers, e.g., SVM. This adaptation method is agnostic to the type of input feature and applies either to features built using aggregators, e.g., BoW, FV, or to features obtained from the activations or outputs from DCNN layers. The adaptation architecture may be single (shallow) or multi-layered (deep). This technique achieves a higher performance compared to current state of the art classification systems.

Abstract: A method for processing in an encoder, the method comprising receiving, by the encoder, a set of local descriptors derived from an image, obtaining, by the encoder, K code words, wherein K>1; and determining, by the encoder, a first element of a bag-of-words image feature vector by using a differentiable function having a difference between each of the local descriptors and one of the K code words as a first parameter, wherein each of the K code words is used in the differentiable function for determining a different element of the bag-of-words image feature vector.