Abstract: A method includes maintaining a set of parameters or weights derived through online learning for a neural net; transmitting an update of the parameters or weights to a decoder; deriving a first prediction block based on an output of the neural net using the parameters or weights; deriving a first encoded prediction error block through encoding a difference of the first prediction block and a first input block; encoding the first encoded prediction error block into a bitstream; deriving a reconstructed prediction error block based on the first encoded prediction error block; deriving a second prediction block based on an output of the neural net using the parameters or weights and the reconstructed prediction error block; deriving a second encoded prediction error block through encoding a difference of the second prediction block and a second input block; and encoding the second encoded prediction error block into a bitstream.

Abstract: A method comprising: obtaining a configuration of at least one neural network comprising a plurality of intra-prediction mode agnostic layers and one or more intra-prediction mode specific layers, the one or more intra-prediction mode specific layers corresponding to different intra-prediction modes; obtaining at least one input video frame comprising a plurality of blocks; determining to encode one or more blocks using intra prediction; determining an intra-prediction mode for each of said one or more blocks; grouping blocks having same intra-prediction mode into groups, each group being assigned with a computation path among the plurality of intra-prediction mode agnostic and the one or more intra-prediction mode specific layers; training the plurality of intra-prediction mode agnostic and/or the one or more intra-prediction mode specific layers of the neural networks based on a training loss between an output of the neural networks relating to a group of blocks and ground-truth blocks, wherein the ground-t

Abstract: A system, obtaining a first training dataset, comprising a plurality of first image and pose data pairs; obtaining a first generated dataset, comprising a plurality of first image and estimated pose data pairs, wherein estimated pose data of the first image and estimated pose data pairs are generated by a first neural network trained using the first training dataset; obtaining a second generated dataset, comprising a plurality of second image and estimated pose data pairs, wherein estimated pose data of the second image and estimated pose data pairs are generated by a second neural network trained using the first training dataset; generating the first and second generated datasets a generated training dataset, comprising image and estimated pose data pairs selected from said first generated dataset; and training a third neural network based on a combination of some or all of the first training dataset and the generated training dataset.

Abstract: A method comprising: deriving a first prediction block (608) at least partly based on an output of a neural net (602) using a first set of parameters; deriving a first encoded prediction error block (614-620) through encoding a difference of the first prediction block and a first input block; encoding (620) the first encoded prediction error block into a bitstream; deriving a first reconstructed prediction error block (624) from the first encoded prediction error block; deriving a training signal (628) from one or both of the first encoded prediction error block and/or the first reconstructed prediction error block (624); retraining (630) the neural net (602) with the training signal (628) to obtain a second set of parameters for the neural net (602); deriving a second prediction block (608) at least partly based on an output of the neural net using the second set of parameters; deriving a second encoded prediction error block (614-620) through encoding a difference of the second prediction block and a second

Abstract: A node for a federated machine learning system that comprises the node and one or more other nodes configured for the same machine learning task, the node comprising: a federated student machine learning network configured to update a machine learning model in dependence upon updated machine learning models of the one or more node; a teacher machine learning network; means for receiving unlabeled data; means for teaching, using supervised learning, at least the federated first machine learning network using the teacher machine learning network, wherein the teacher machine learning network is configured to receive the data and produce pseudo labels for supervised learning using the data and wherein the federated student machine learning network is configured to perform supervised learning in dependence upon the same received data and the pseudo-labels.

Abstract: A method comprising: obtaining (400), in a first apparatus (500), media content, encoding (402), in a neural data compression network of the first apparatus (500), the media content wherein one or more parameters of the neural data compression network are determined based on a type of at least one analysis task to be performed on the media content; and transmitting (404) the encoded media content to a second apparatus (502).

Abstract: An apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: estimate an importance of parameters of a neural network based on a graph diffusion process over at least one layer of the neural network; determine the parameters of the neural network that are suitable for pruning or sparsification; remove neurons of the neural network to prune or sparsify the neural network; and provide at least one syntax element for signaling the pruned or sparsified neural network over a communication channel, wherein the at least one syntax element comprises at least one neural network representation syntax element.

Abstract: A method comprising: using a tracked real point of view of a user in a real space and a first mapping between the real space and a virtual space to determine a point of view of a virtual user within the virtual space; causing rendering to the user at least part of a virtual scene determined by the point of view of the virtual user within the virtual space; and using a selected one of a plurality of different mappings to map tracked user actions in the real space to actions of the virtual user in the virtual space, wherein, when a first mode is selected, the method comprises mapping tracked user actions in the real space, using the first mapping, to spatially-equivalent actions of the virtual user in the virtual space, and wherein, when a second mode is selected, the method comprises mapping tracked user actions in the real space, using a second mapping different to the first mapping, to non-spatially-equivalent actions of the virtual user in the virtual space, wherein the second mapping makes available user i

Abstract: The invention relates to a method comprising receiving, by a neural network, a first image comprising at least one target object; receiving, by the neural network, a second image comprising at least one query object; and determining, by the neural network, whether the query object corresponds to the target object, wherein the neural network comprises a discriminator neural network of a generative adversarial network (GAN). The invention further relates to an apparatus and a computer program product that perform the method.

Abstract: An apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: decode encoded data to generate decoded data, the encoded data having a bitrate lower than that of original data, and extract features from the decoded data; decode encoded residual features to generate decoded residual features; and generate enhanced decoded features as a result of combining the decoded residual features with the features extracted from the decoded data.

Abstract: The invention relates to a method, an apparatus and a computer program product for analyzing media content. The method comprises receiving media content; performing feature extraction of the media content at a plurality of convolution layers to produce a plurality of layer-specific feature maps; transmitting from the plurality of convolution layers a corresponding layer-specific feature map to a corresponding de-convolution layer of a plurality of de-convolution layers via a recurrent connection between the plurality of convolution layers and the plurality of de-convolution layers; and generating a reconstructed media content based on the plurality of feature maps.

Abstract: Data may be encoded to minimize distortion after decoding, but the quality required for presentation of the decoded data to a machine and the quality required for presentation to a human may be different. To accommodate different quality requirements, video data may be encoded to produce a first set of encoded data and a second set of encoded data, where the first set may be decoded for use by one of a machine consumer or a human consumer, and a combination of the first set and the second set may be decoded for use by the other of a machine consumer or a human consumer. The first and second set may be produced with a neural encoder and a neural decoder, and/or may be produced with the use of prediction and transform neural network modules. A human-targeted structure and a machine-targeted structure may produce the sets of encoded data.

Abstract: A method, apparatus and computer program product provide an automated neural network training mechanism. The method, apparatus and computer program product receive a decoded noisy image and a set of input parameters for a neural network configured to optimize the decoded noisy image. A denoised image is generated based on the decoded noisy image and the set of input parameters. A denoised noisy error is computed representing an error between the denoised image and the decoded noisy image. The neural network is trained using the denoised noisy error and the set of input parameters and a ground truth noisy error value is received representing an error between the original image and the encoded image. The ground truth noisy error value is compared with the denoised noisy error to determine whether a difference between the ground truth noisy error value and the denoised noisy error is within a pre-determined threshold.

Abstract: An apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: encode or decode a high-level bitstream syntax for at least one neural network; wherein the high-level bitstream syntax comprises at least one information unit having metadata or compressed neural network data of a portion of the at least one neural network; and wherein a serialized bitstream comprises one or more of the at least one information unit.

Abstract: A method comprising: deriving a first prediction block (608) at least partly based on an output of a neural net (602) using a first set of parameters; deriving a first encoded prediction error block (614-620) through encoding a difference of the first prediction block and a first input block; encoding (620) the first encoded prediction error block into a bitstream; deriving a first reconstructed prediction error block (624) from the first encoded prediction error block; deriving a training signal (628) from one or both of the first encoded prediction error block and/or the first reconstructed prediction error block (624); retraining (630) the neural net (602) with the training signal (628) to obtain a second set of parameters for the neural net (602); deriving a second prediction block (608) at least partly based on an output of the neural net using the second set of parameters; deriving a second encoded prediction error block (614-620) through encoding a difference of the second prediction block and a second

Abstract: A method comprising: remotely sensing a real acoustic environment, in which multiple audio signals are captured; and enabling automatic control of mixing of the multiple captured audio signals based on the remote sensing of the real acoustic environment in which the multiple audio signals were captured.

Abstract: This specification describes a method comprising responding to a first gesture by a first user delimiting a visual virtual reality content portion from visual virtual reality content being consumed by the first user via a first head-mounted display by selecting the delimited visual virtual reality content portion, responding to a second gesture by the first user directed towards a content consumption device associated with a second user by identifying the content consumption device as a recipient of the selected visual virtual reality content portion, and causing the selected visual virtual reality content portion to be provided to the content consumption device for consumption by t second user.

Abstract: An apparatus, a method and a computer program product are described comprising: obtaining or receiving video data; providing a current frame and/or one or more previous frames of the obtained or received video data to an input of a neural network; generating a predicted output at an output of the neural network, wherein the predicted output comprises at least one of one or more predicted future frames of the video data and predicted properties of one or more future frames of the video data; determining one or more processing decisions based, at least in part, on the predicted output; and processing the current frame of the video data at least partially according to the one or more processing decisions.

Abstract: A method, apparatus and computer program is described comprising: generating or obtaining at least one augmented reality image for presentation to a user, the augmented reality images comprising one or more virtual objects, displays or devices of an augmented reality system; attenuating real-world audio of the augmented reality system; and controlling the provision of audio to the user in at least one audio focus or beamform direction relating to at least one selected real-world object of the augmented reality system.

Abstract: A method comprising: obtaining a block of a picture or a picture in an encoder; determining if the block/picture is used for on-line learning; if affirmative, encoding the block/picture; reconstructing a coarse version of the block/picture or the respective prediction error block/picture; enhancing the coarse version using a neural net; fine-tuning the neural net with a training signal based on the coarse version; determining if the block/picture is enhanced using the neural net; and if affirmative, encoding the block/picture with enhancing using the neural net.