Abstract: A computer-implemented method for training an agent in a first context including an entity and an environment of the entity, to allow an apparatus to perform a navigation task in a second context comprising the apparatus and a physical environment of the apparatus, the apparatus adapted to receive images of the physical environment of the apparatus and comprising a steering device adapted to control the direction of the apparatus, the method comprising: obtaining one or more navigation tasks comprising: generating a navigation task; scoring the navigation task using a machine-learned model trained to estimate the easiness of tasks; in response to the score satisfying a selection criterion, selecting the navigation task as one of the one or more navigation tasks; and training the agent using a reinforcement learning method comprising attempting to perform, by the entity, the one or more navigation tasks using images of the environment of the entity.

Abstract: A computer vision method for generating a three dimensional reconstruction of an object, the method comprising: receiving a set of photometric stereo images of the object, the set of photometric stereo images comprising a plurality of images using illumination from different directions using one or more light sources; using a trained neural network to generate a normal map of the object; and producing a 3D reconstruction of said object from said normal map, wherein using said trained neural network comprises converting said set of photometric stereo images to an input form suitable for an input layer of said neural network, wherein said input form comprises, for each pixel, a representation of the different lighting directions and their corresponding intensities which have been obtained from photometric stereo images to which a compensation has been applied, the compensation being determined from an estimate of the distance between the lighting source and a point on the object to which the pixel correspond

Abstract: A method of detecting abnormalities in ECG signals by providing an ECG signal to a neural network, performing a first series of convolution operations to a first subset of layers and in a final layer, and determining a plurality of preliminary classification estimates, each preliminary classification estimate corresponding with a time segment of the ECG signal. Furthermore, determining input data for a second subset of layers of the neural network by concatenating the preliminary classification with the output of a layer of the first subset of layers that precedes the final layer of the first subset of layers. Within the second subset of layers of the neural network, performing a second series of convolution operations. In a final layer of the second subset, determining plurality of final classification estimates, each final classification estimate corresponding with a time segment of the ECG signal.

Abstract: A method for processing video data comprising a plurality of image frames, the method comprising: obtaining a forward model and a backward model of the plurality of image frames; processing the forward model and the backward model to propagate at least one label in the region or patch to at least one other image frame of the video sequence, using a probabilistic method for estimating the label in the at least one other image frame in forward and backward correspondences, wherein, during the processing, a pixel having a most likely label with a probability lower than a threshold value is assigned a predetermined generic label; and generating a labelled result for any given image frame by applying an image label difference, based on label uncertainty between the forward and backward correspondences, to the given image frame.

Abstract: A system for producing a 3D image of an object, the system includes: a processor adapted to receive multiview stereo photometric data, the multiview photometric stereo data including a first set of image data, wherein the first set of image data includes images captured by the first camera at a plurality of positions with illumination from different illumination directions such that there are a plurality of images from a different illumination direction for each position of the first camera, the processor being adapted to process the multiview photometric stereo data using a photometric stereo approach with a formulation of the irradiance using a reflection model that models both diffuse and specular reflection.

Abstract: An image processing method for segmenting an image, the method comprising: receiving an image; processing said image with a common processing stage to produce a first feature map; inputting said first feature map to a parallel processing stage, said second processing stage comprising first and second parallel branches that receive the first feature map; and combining the output of the first and second branches to produce a semantic segmented image, wherein the common processing stage comprises a neural network, the neural network having at least one separable convolution module configured to perform separable convolution and downsample the image to produce first feature map and said first branch comprises a neural network comprising at least one separable convolution module configured to perform separable convolution.

Abstract: A computer-implemented method for training an agent in a first context including an entity and an environment of the entity, to allow an apparatus to perform a navigation task in a second context comprising the apparatus and a physical environment of the apparatus, the apparatus adapted to receive images of the physical environment of the apparatus and comprising a steering device adapted to control the direction of the apparatus, the method comprising: obtaining one or more navigation tasks comprising: generating a navigation task; scoring the navigation task using a machine-learned model trained to estimate the easiness of tasks; in response to the score satisfying a selection criterion, selecting the navigation task as one of the one or more navigation tasks; and training the agent using a reinforcement learning method comprising attempting to perform, by the entity, the one or more navigation tasks using images of the environment of the entity.

Abstract: A computer vision method for generating a three dimensional reconstruction of an object, the method comprising: receiving a set of photometric stereo images of the object, the set of photometric stereo images comprising a plurality of images using illumination from different directions using one or more light sources; using a trained neural network to generate a normal map of the object; and producing a 3D reconstruction of said object from said normal map, wherein using said trained neural network comprises converting said set of photometric stereo images to an input form suitable for an input layer of said neural network, wherein said input form comprises, for each pixel, a representation of the different lighting directions and their corresponding intensities which have been obtained from photometric stereo images to which a compensation has been applied, the compensation being determined from an estimate of the distance between the lighting source and a point on the object to which the pixel correspond

Abstract: A system for emulating a subject, to allow a user to interact with a computer generated talking head with the subject's face and voice; said system comprising a processor, a user interface and a personality storage section, the user interface being configured to emulate the subject, by displaying a talking head which comprises the subject's face and output speech from the mouth of the face with the subject's voice, the user interface further comprising a receiver for receiving a query from the user, the emulated subject being configured to respond to the query received from the user, the processor comprising a dialogue section and a talking head generation section, wherein said dialogue section is configured to generate a response to a query inputted by a user from the user interface and generate a response to be outputted by the talking head, the response being generated by retrieving information from said personality storage section, said personality storage section comprising content created by or about

Abstract: A method of detecting abnormalities in an ECG signals, comprising receiving an ECG signal, extracting at least one ECG beat the ECG signal; providing the at least one ECG beat to a neural network. Within the neural network, performing at least two layers of convolution operations, and for a beat of the ECG signal, determining a confidence map for the location of each of the P, Q, R, S and T points, determining, from the respective confidence maps the position or absence of points, the points comprising each of the P, Q, R, S and T points; and reporting the positions and/or absence of the points.

Abstract: A system for producing a 3D image of an object, the system includes: a processor adapted to receive multiview stereo photometric data, the multiview photometric stereo data including a first set of image data, wherein the first set of image data includes images captured by the first camera at a plurality of positions with illumination from different illumination directions such that there are a plurality of images from a different illumination direction for each position of the first camera, the processor being adapted to process the multiview photometric stereo data using a photometric stereo approach with a formulation of the irradiance using a reflection model that models both diffuse and specular reflection.

Abstract: An image processing method for segmenting an image, the method comprising: receiving an image; processing said image with a common processing stage to produce a first feature map; inputting said first feature map to a parallel processing stage, said second processing stage comprising first and second parallel branches that receive the first feature map; and combining the output of the first and second branches to produce a semantic segmented image, wherein the common processing stage comprises a neural network, the neural network having at least one separable convolution module configured to perform separable convolution and downsample the image to produce first feature map and said first branch comprises a neural network comprising at least one separable convolution module configured to perform separable convolution.

Abstract: A method for processing video data comprising a plurality of image frames, the method comprising: obtaining a forward model and a backward model of the plurality of image frames; processing the forward model and the backward model to propagate at least one label in the region or patch to at least one other image frame of the video sequence, using a probabilistic method for estimating the label in the at least one other image frame in forward and backward correspondences, wherein, during the processing, a pixel having a most likely label with a probability lower than a threshold value is assigned a predetermined generic label; and generating a labelled result for any given image frame by applying an image label difference, based on label uncertainty between the forward and backward correspondences, to the given image frame.

Abstract: We disclose herein a method of detecting abnormalities in electrocardiogram (ECG) signals, the method comprising receiving a set of ECG signals from an ECG device; amplifying only the peaks of at least some of the set of ECG signals to produce ECG beat markings from which a heart rate is derivable to detect an irregular rhythm between at least two ECG beats; extracting a single ECG beat from the set of ECG signals from the ECG device by using said ECG beat markings; feeding the extracted single ECG beat into a first neural network; producing, at the first neural network, a compact representation of the extracted single ECG signal so as to generate a feature extraction output; and using, at a second neural network, the feature extraction output from the first neural network to generate a score associated with the abnormalities in the ECG signals.

Abstract: A method of detecting abnormalities in an ECG signals, comprising receiving an ECG signal, extracting at least one ECG beat the ECG signal; providing the at least one ECG beat to a neural network. Within the neural network, performing at least two layers of convolution operations, and for a beat of the ECG signal, determining a confidence map for the location of each of the P, Q, R, S and T points, determining, from the respective confidence maps the position or absence of points, the points comprising each of the P, Q, R, S and T points; and reporting the positions and/or absence of the points.

Abstract: A method of detecting abnormalities in ECG signals by providing an ECG signal to a neural network, performing a first series of convolution operations to a first subset of layers and in a final layer, and determining a plurality of preliminary classification estimates, each preliminary classification estimate corresponding with a time segment of the ECG signal. Furthermore, determining input data for a second subset of layers of the neural network by concatenating the preliminary classification with the output of a layer of the first subset of layers that precedes the final layer of the first subset of layers. Within the second subset of layers of the neural network, performing a second series of convolution operations. In a final layer of the second subset, determining plurality of final classification estimates, each final classification estimate corresponding with a time segment of the ECG signal.

Abstract: We disclose herein a method of detecting abnormalities in electrocardiogram (ECG) signals, the method comprising receiving a set of ECG signals from an ECG device; amplifying only the peaks of at least some of the set of ECG signals to produce ECG beat markings from which a heart rate is derivable to detect an irregular rhythm between at least two ECG beats; extracting a single ECG beat from the set of ECG signals from the ECG device by using said ECG beat markings; feeding the extracted single ECG beat into a first neural network; producing, at the first neural network, a compact representation of the extracted single ECG signal so as to generate a feature extraction output; and using, at a second neural network, the feature extraction output from the first neural network to generate a score associated with the abnormalities in the ECG signals.

Abstract: A system for capturing 3D image data of a scene, including three light sources, each configured to emit light at a different wavelength to the other two sources and to illuminate the scene to be captured; a first video camera configured to receive light from the light sources which has been reflected from the scene, to isolate light received from each of the light sources, and to output data relating to the image captured for each of the three light sources; a depth sensor configured to capture depth map data of the scene; and an analysis unit configured to receive data from the first video camera and process the data to obtain data relating to a normal field obtained from the images captured for each of the three light sources, and to combine the normal field data with the depth map data to capture 3D image data of the scene.

Abstract: A system for emulating a subject, to allow a user to interact with a computer generated talking head with the subject's face and voice; said system comprising a processor, a user interface and a personality storage section, the user interface being configured to emulate the subject, by displaying a talking head which comprises the subject's face and output speech from the mouth of the face with the subject's voice, the user interface further comprising a receiver for receiving a query from the user, the emulated subject being configured to respond to the query received from the user, the processor comprising a dialogue section and a talking head generation section, wherein said dialogue section is configured to generate a response to a query inputted by a user from the user interface and generate a response to be outputted by the talking head, the response being generated by retrieving information from said personality storage section, said personality storage section comprising content created by or about

Abstract: A method of animating a computer generation of a head, the head having a mouth which moves in accordance with speech to be output by the head, said method comprising: providing an input related to the speech which is to be output by the movement of the lips; dividing said input into a sequence of acoustic units; selecting expression characteristics for the inputted text; converting said sequence of acoustic units to a sequence of image vectors using a statistical model, wherein said model has a plurality of model parameters describing probability distributions which relate an acoustic unit to an image vector, said image vector comprising a plurality of parameters which define a face of said head; and outputting said sequence of image vectors as video such that the mouth of said head moves to mime the speech associated with the input text with the selected expression, wherein a parameter of a predetermined type of each probability distribution in said selected expression is expressed as a weighted sum of pa