公开(公告)号：US20240265240A1

公开(公告)日：2024-08-08

申请号：US18567736

申请日：2022-06-17

Applicant: Nokia Technologies Oy

Inventor： Honglei ZHANG ,  Francesco CRICRÌ ,  Ramin GHAZNAVI YOUVALARI ,  Hamed REZAZADEGAN TAVAKOLI ,  Nannan ZOU ,  Vinod Kumar MALAMAL VADAKITAL ,  Miska Matias HANNUKSELA ,  Yat Hong LAM ,  Jani LAINEMA ,  Emre Baris AKSU

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: An example apparatus includes at least one processor; and at least one non-transitory memory comprising 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; learn importance of one or more parameters by using a training dataset; define one or more masks for indicating the importance of the one or more parameters for a model finetuning; share at least one mask of the one or more masks with at least one of an encoder or a decoder; finetune at least one parameter of the one or more parameters based at least on the at least one mask; send or signal one or more weight updates corresponding to the at least one parameter in a bitstream to the decoder.

公开(公告)号：US20230269387A1

公开(公告)日：2023-08-24

申请号：US18001987

申请日：2021-06-11

Applicant: Nokia Technologies Oy

Inventor： Francesco CRICRÌ ,  Hamed REZAZADEGAN TAVAKOLI ,  Honglei ZHANG ,  Nannan ZOU

IPC: H04N19/42 ,  H04N19/124 ,  H04N19/176 ,  G06N3/0455 ,  G06N3/0985

CPC classification number: H04N19/42 ,  G06N3/0455 ,  G06N3/0985 ,  H04N19/124 ,  H04N19/176

Abstract: 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.

公开(公告)号：US20230217028A1

公开(公告)日：2023-07-06

申请号：US17999107

申请日：2021-06-03

Applicant: Nokia Technologies Oy

Inventor： Honglei ZHANG ,  Francesco GRICRI ,  Emre Baris AKSU ,  Hamed REZAZADEGAN TAVAKOLI

IPC: H04N19/149 ,  H04N19/30 ,  H04N19/176

CPC classification number: H04N19/149 ,  H04N19/30 ,  H04N19/176

Abstract: In example embodiments, an apparatus, a method, and a computer program product are provided. The apparatus comprises 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 determine a processing order of building blocks to encode or decode a media item; and determine a number of processing steps required to encode or decode the media item; wherein the processing order of building blocks and the number of processing steps are determined based on a content of the media item by using a guided probability model based on a neural network.

公开(公告)号：US20220012637A1

公开(公告)日：2022-01-13

申请号：US17370462

申请日：2021-07-08

Applicant: Nokia Technologies Oy

Inventor： Hamed REZAZADEGAN TAVAKOLI ,  Francesco CRICRI ,  Emre Baris AKSU

IPC: G06N20/00

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.

公开(公告)号：US20250113079A1

公开(公告)日：2025-04-03

申请号：US18978234

申请日：2024-12-12

Applicant: Nokia Technologies Oy

Inventor： Emre AKSU ,  Miska HANNUKSELA ,  Francesco CRICRÌ ,  Hamed REZAZADEGAN TAVAKOLI

IPC: H04N21/435 ,  H04N21/433

Abstract: 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.

公开(公告)号：US20240289590A1

公开(公告)日：2024-08-29

申请号：US18572100

申请日：2022-06-16

Applicant: Nokia Technologies Oy

Inventor： Francesco CRICRÌ ,  Nannan ZOU ,  Honglei ZHANG ,  Hamed REZAZADEGAN TAVAKOLI

IPC: G06N3/045

CPC classification number: G06N3/045

Abstract: Various embodiments provide a method, an apparatus, and computer program product. The method comprising: defining an attention block comprising: a set of initial neural network layers, wherein each layer is caused to process an output of a previous layer, and wherein a first layer processes an input of a dense split attention block; core attention blocks process one or more outputs of the set of initial neural network layers; a concatenation block for concatenating one or more outputs of the core attention blocks and at least one intermediate output of the set of initial neural network layers; one or more final neural network layers process at least the output of the concatenation block; and a summation block caused to sum an output of the final neural network layers and an input to the attention block; and providing an output of the summation block as a final output of the attention block.

公开(公告)号：US20240202507A1

公开(公告)日：2024-06-20

申请号：US18555479

申请日：2022-04-15

Applicant: Nokia Technologies Oy

Inventor： Francesco CRICRÌ ,  Jani LAINEMA ,  Ramin GHAZNAVI YOUVALARI ,  Honglei ZHANG ,  Yat Hong LAM ,  Maria Claudia SANTAMARIA GOMEZ ,  Hamed REZAZADEGAN TAVAKOLI ,  Miska Matias HANNUKSELA

IPC: G06N3/049 ,  G06N3/08 ,  H04N19/90

CPC classification number: G06N3/049 ,  G06N3/08 ,  H04N19/90

Abstract: An apparatus with a corresponding method and 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 the steps (1600) of train or finetune at least one neural network (NN) based at least on a temporal persistence scope; and encode or decode one or more media frames elements based at least on the trained or finetuned at least one neural network. A further apparatus with a corresponding method and computer program product are provided. The further apparatus configured to carry out the steps (1700) of receive a weight-update prediction error from an encoder-side, predict a weight-update based on one or more reference weight updates, and a prediction function or algorithm, and reconstruct a weight update by combining the predicted weight-update and the prediction error.

公开(公告)号：US20240013046A1

公开(公告)日：2024-01-11

申请号：US18247200

申请日：2021-09-02

Applicant: Nokia Technologies Oy

Inventor： Nam LE ,  Francesco CRICRÌ ,  Honglei ZHANG ,  Hamed REZAZADEGAN TAVAKOLI ,  Ramin GHAZNAVI YOUVALARI

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method is provided for computing predetermined loss terms based on original data and decoded data; training one or more neural networks of a system by using the predetermined loss terms; updating weights for one or more of other loss terms; and determining trade-offs between predetermined objectives of the system. Corresponding apparatuses and computer program products are also provided.

公开(公告)号：US20230112309A1

公开(公告)日：2023-04-13

申请号：US17934734

申请日：2022-09-23

Applicant: Nokia Technologies Oy

Inventor： Miska Matias HANNUKSELA ,  Emre Baris AKSU ,  Francesco CRICRÌ ,  Hamed REZAZADEGAN TAVAKOLI

IPC: H04N19/117 ,  H04N19/85 ,  H04N19/70 ,  H04N19/184

Abstract: 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.

公开(公告)号：US20240314362A1

公开(公告)日：2024-09-19

申请号：US18577010

申请日：2022-06-21

Applicant: Nokia Technologies Oy

Inventor： Ramin GHAZNAVI YOUVALARI ,  Honglei ZHANG ,  Francesco CRICRÌ ,  Nam Hai LE ,  Miska Matias HANNUKSELA ,  Hamed REZAZADEGAN TAVAKOLI ,  Jukka Ilari AHONEN

IPC: H04N19/82 ,  H04N19/119 ,  H04N19/139 ,  H04N19/70 ,  H04N19/85

CPC classification number: H04N19/82 ,  H04N19/119 ,  H04N19/139 ,  H04N19/70 ,  H04N19/85

Abstract: A method includes receiving auxiliary information and/or at least one auxiliary feature, the at least one auxiliary feature being based on the auxiliary information; wherein the auxiliary information comprises information available within a decoder, or the auxiliary information comprises a bitstream output from data encoded using an encoder; receiving decoded data generated using the decoder; and generating filtered data with at least one filter using the auxiliary information and/or the at least one auxiliary feature via applying the filter to the decoded data; wherein the at least one filter comprises a learned filter; wherein the filtered data is configured to be used for at least one machine task performed using a model.