Nokia Technologies Oy

Francesco Cricrì

Hamed Rezazadegan Tavakoli

Miska Matias Hannuksela

Emre Baris Aksu

Honglei Zhang

Arto Juhani Lehtiniemi

Jussi Artturi Leppänen

Antti Johannes Eronen

Nannan Zou

Miikka Tapani Vilermo

Sujeet Shyamsundar Mate

Jani Lainema

Igor Danilo Diego Curcio

Yu You

Ville-Veikko Mattila

Caglar Aytekin

Xingyang Ni

Peter O Fasogbon

Goutham Rangu

Homayun Afrabandpey

The embodiments relate to a method for encoding two or more tensors. The method comprises processing the two or more tensors having respective dimensions so that the dimensions of said two or more sensors have the same number (); identifying which axis of each individual tensor is swappable to result in concatenable tensors around an axis of concatenation (); reshaping the tensors so that the dimensions are modified based on the swapped axis (); concatenating the tensors around the axis of concatenation to result in concatenated tensor (); compressing the concatenated tensor (); generating syntax structures for carrying concatenation and axis swapping information (); and generating a bitstream by combining the syntax structures and the compressed concatenated tensor (). The embodiments also relate to a method for decoding, and to apparatuses for implementing the methods.

Method, an apparatus and a computer program product for neural network compression

The embodiments relate to an apparatus and a method for encoding and decoding. The encoding method comprises receiving () visual data; converting () the visual data into a latent representation comprising channels; quantizing () the latent representation; processing () the channels of the quantized latent representation (x) according to a predefined channel dependency mode by generating () a mixed representation (y) comprising predicted values and original values from the quantized latent representation; generating () a mask representation (m) indicating which elements in the mixed representation are with original values; estimating () parameters (q) for a probability distribution function or a probability distribution of elements with the predicted values; encoding () elements with the predicted values using the original values from the quantized latent representation and the estimated probability distribution function for these elements into a bitstream; updating () a mixed representation (y) with the original values from the quantized latent representation (x) and the mask representation (m) accordingly; repeating () the processing for all elements.

Method, an apparatus and a computer program product for video encoding and video decoding

An apparatus comprising: at least one processor; and at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive a signal, the signal comprising a sparse signal; perform residual coding on the signal; perform predictive coding on the signal; determine a residual, the residual comprising a residual of the signal and a base signal or a residual of an approximation and the base signal, the approximation being an approximation of the signal; and determine whether to transmit the residual or the signal over a communication channel.

Predictive and residual coding of sparse signals for weight update compression

Various embodiments provide an apparatus, a method, and a computer program product. 1. An apparatus incudes at least one processor; and at least one non-transitory memory includes 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 an overfitting operation, at an encoder side, to obtain an overfitted probability model, wherein overfitting comprises one or more training operations applied to a probability model, wherein one or more parameters of the probability model are trained; use the overfitted probability model to provide probability estimates to a lossless codec or a substantially lossless codec for encoding data or a portion of the data; and signal information to a decoder on whether to perform the overfitting operation at the decoder side.

Apparatus method and computer program product for probability model overfitting

In example embodiments, an apparatus, a method, and a computer program product are provided. An example apparatus include processing circuitry; and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processing circuitry, cause the apparatus at least to: overfit a neural network on each media item, from a batch of media items, for a number of iterations to obtain an overfitted neural network model for the each media item; evaluate the overfitted neural network model on the each media item to obtain evaluation errors; and update parameters of the neural network to be based on the evaluation errors.

Apparatus, method and computer program product for optimizing parameters of a compressed representation of a neural network

A method is provided for defining a metadata box of a neural network representation (NNR) item data, wherein the NNR item data comprises an NNR bitstream; and defining an association between the NNR item data and an NNR configuration by using a configuration item property, wherein the NNR configuration item property comprises information about stored NNR item data. Corresponding apparatuses and computer program products are also provided.

Carriage and signaling of neural network representations

The embodiments relate to a method comprising establishing a three-dimensional conversational interaction with one or more receivers; generating a pointcloud relating to a user and capturing audio from one or more audio source; generating conversational scene description comprising at least a first dynamic object describing a virtual space for the three-dimensional conversational interaction, wherein the first dynamic object refers to one or more objects specific to the three-dimensional conversational interaction, wherein said one or more objects comprises at least data relating to transformable pointcloud; audio obtained from said one or more audio source and input obtained from one or more connected devices controlling at least the pointcloud, wherein said objects are linked to each other for seamless manipulation; applying the conversational scene description into a metadata, and transmitting the metadata with the respective audio in realtime to said one or more receivers.

A method, an apparatus, and a computer program product are provided. An example method includes defining an enhancement message comprising at least one of the following: an identifying number for identifying a post-processing filter; a mode identity (idc) field used of indicating association of a post-processing filter with the identifying number; a flag for specifying the enhancement message being used for a current layer; and the payload byte comprising a bitstream; and using the enhancement message for at least one of specifying a neural network that is used as a post-processing filter or cancelling a use of a previous post-processing filter with the same identifying number.

High-level syntax for signaling neural networks within a media bitstream

An example method is provided to include receiving a media bitstream comprising one or more media units and a first enhancement information message, wherein the first enhancement information message comprises at least two independently parsable structures, a first independently parsable structure comprising information about at least one purpose of one or more neural networks (NNs) to be applied to the one or more media units, and a second independently parsable structure comprising or identifying one or more neural networks; decoding the one or more media units; and using the one or more neural networks to enhance or filter one or more frames of the decoded the one or more media units, based on the at least one purpose. An example method includes. Corresponding apparatuses and computer program products are also provided.

In example embodiments, an apparatus, a method, and a computer program product are provided. The 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, wherein the at least one information unit comprises syntax definitions for the at least one neural network or a portion of the at least one neural network; and wherein a serialized bitstream comprises one or more of the at least one information units.

High level syntax and carriage for compressed representation of neural networks

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.

Augmented reality system

A method comprising: obtaining (), in a first apparatus (), media content, encoding (), in a neural data compression network of the first apparatus (), 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 () the encoded media content to a second apparatus ().

Apparatus, a method and a computer program for running a neural network

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.

Reverse neural network for object re-identification

A method comprising: causing definition of a display window in a displayed virtual scene; displaying window content inside the display window, in the displayed virtual scene; in dependence upon a first user action, causing a first change in the window content displayed inside the display window to first window content different to the window content, without changing the display window; and in dependence upon a second user action causing a second change in the window content displayed in the display window to second window content, different to the first window content and the window content, and causing a variation in the display window to become a modified display window different to the display window.

Method, apparatus or computer program for user control of access to displayed content

An apparatus configured to: &#x2022;in respect of virtual reality content comprising video imagery configured to provide a virtual reality space for viewing in virtual reality, wherein a virtual reality view presented to a user provides for viewing of the virtual reality content, the virtual reality view comprising a spatial portion of the video imagery that forms the virtual reality space and being smaller in spatial extent than the spatial extent of the video imagery of the virtual reality space and &#x2022;based on one or more of; &#x2022;i) a viewing direction in the virtual reality space of at least one virtual reality view provided to the user; and &#x2022;ii) a selected object in the video imagery, &#x2022;providing for one or more of generation or display of causal summary content comprising selected content from the virtual reality content at least prior to a time point in the virtual reality content currently viewed by the user, the causal summary content at least focussed on an object or event appearing in the at least one virtual reality view or the selected object to show the historic occurrence of the object or event or selected object in the virtual reality content, &#x2022;wherein the provision of one or more of generation or display of causal summary content is further based on the virtual reality view provided to the user historically not including the object or event or selected object for at least a predetermined period of time thereby providing causal summary content for objects or events that were missed by the user while watching the virtual reality content.

Growing community of inventors

Tampere, Finland

Francesco Cricrì