知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

45 records (took 0.015 seconds)

    Coded Picture with Mixed VCL NAL Unit Type
    11.
    发明公开
    Coded Picture with Mixed VCL NAL Unit Type 审中-公开

    公开(公告)号：US20240048737A1

    公开(公告)日：2024-02-08

    申请号：US18379386

    申请日：2023-10-12

    Applicant: Nokia Technologies Oy

    Inventor： Miska Matias Hannuksela ,  Kashyap Kammachi Sreedhar ,  Emre Aksu

    IPC: H04N19/30 ,  H04N19/70 ,  H04N19/172 ,  H04N19/167 ,  H04N19/184 ,  H04N19/169 ,  H04N19/132

    CPC classification number: H04N19/30 ,  H04N19/70 ,  H04N19/172 ,  H04N19/167 ,  H04N19/184 ,  H04N19/188 ,  H04N19/132

    Abstract: 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: indicate a mixed network abstraction layer unit type pictures sample group used to merge video base tracks having a subpicture track; indicate a sample group description entry of the mixed network abstraction layer unit type pictures sample group, the sample group description entry indicating a group of pairs of mixed network abstraction layer unit type track reference indices, which reference video subpicture tracks or track groups; and wherein when a video bitstream is resolved from a video base track containing a mixed network abstraction layer unit type sample group with merging pairs of video subpicture tracks signaled in a mixed network abstraction layer unit type pictures sample group entry, then there is mixing of different network abstraction layer unit types.

    Method, an apparatus and a computer program product for video encoding and video decoding
    12.
    发明授权
    Method, an apparatus and a computer program product for video encoding and video decoding 有权

    公开(公告)号：US11722751B2

    公开(公告)日：2023-08-08

    申请号：US17789883

    申请日：2020-12-30

    Applicant: Nokia Technologies Oy

    Inventor： Kashyap Kammachi Sreedhar ,  Miska Hannuksela ,  Sujeet Mate ,  Emre Aksu

    IPC: H04N21/84 ,  H04N21/854

    CPC classification number: H04N21/84 ,  H04N21/85406

    Abstract: The embodiments relate to a method, including writing a first and a second media entity in a container file; creating a media presentation description (MPD) with a first and a second Representation; the Representations belonging to Adaptation Sets; the Representations being associated with the media entities of the container file; when one of the Representations belongs to a media entity which is a thumbnail to a viewpoint or a thumbnail to an overlay, the method includes writing in the MPD file an association/correspondence/grouping information of the said one Representation with another Representation belonging to a media entity which is a viewpoint or an overlay, correspondingly. The embodiments also relate to a method for parsing, and technical equipment for implementing the methods.

    Reverse neural network for object re-identification
    15.
    发明授权
    Reverse neural network for object re-identification 有权

    公开(公告)号：US11188783B2

    公开(公告)日：2021-11-30

    申请号：US16156928

    申请日：2018-10-10

    Applicant: Nokia Technologies Oy

    Inventor： Francesco Cricrì ,  Emre Aksu ,  Xingyang Ni

    IPC: G06K9/62 ,  G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G06K9/46

    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.

    High-Level Syntax for Priority Signaling in Neural Network Compression
    17.
    发明申请
    High-Level Syntax for Priority Signaling in Neural Network Compression 有权

    公开(公告)号：US20210103813A1

    公开(公告)日：2021-04-08

    申请号：US17060658

    申请日：2020-10-01

    Applicant: Nokia Technologies Oy

    Inventor： Goutham RANGU ,  Hamed Rezazadegan Tavakoli ,  Francesco Cricri ,  Miska matias Hannuksela ,  Emre Aksu

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Apparatuses, methods, and computer programs for compressing a neural network are disclosed. An apparatus includes at least one processor; and at least one non-transitory memory including computer program code, the memory and the computer program code configured to, with the at least one processor, cause the apparatus to: receive information from a second device, where the information comprises at least one parameter configured to be used for compression of a neural network, where the at least one parameter is in regard to at least one first aspect or task of the neural network; and compress the neural network, where the neural network is compressed based, at least partially, upon the at least one parameter received from the second device. The apparatus may also receive a compressed neural network from the second device, and further compress the compressed neural network based on the information.

    Method, an apparatus and a computer program product for video encoding and video decoding
    18.
    发明授权
    Method, an apparatus and a computer program product for video encoding and video decoding 有权

    公开(公告)号：US12088971B2

    公开(公告)日：2024-09-10

    申请号：US17786766

    申请日：2020-12-17

    Applicant: Nokia Technologies Oy

    Inventor： Miska Hannuksela ,  Emre Aksu ,  Kashyap Kammachi Sreedhar

    IPC: G06F16/71 ,  H04N9/804 ,  H04N19/105 ,  H04N19/184 ,  H04N21/85 ,  H04N19/00

    CPC classification number: H04N9/8042 ,  H04N19/105 ,  H04N19/184

    Abstract: The embodiments relate to a method for writing, in a container file, two or more subpicture tracks; writing, in the container file, a base track, which is intended to be resolved into a video bitstream; indicating, in the base track, a layout of subpictures; writing, in the container file, a sample group description entry indicative of a first subpicture track or a group of subpicture tracks for each subpicture position in the layout of subpictures, wherein the first subpicture track includes the subpicture sequence for the respective subpicture position and wherein any track among the group of subpicture tracks includes a valid subpicture sequence for the respective subpicture position; and indicating in the container file, samples of the base track for which the sample group description entry is intended to be used for reconstructing the video bitstream. The embodiments also relate to a method for parsing, as well as technical equipment for implementing the method for writing and the method for parsing.

    Apparatus, a method and a computer program for video coding and decoding
    20.
    发明授权
    Apparatus, a method and a computer program for video coding and decoding 有权

    公开(公告)号：US11622119B2

    公开(公告)日：2023-04-04

    申请号：US17575946

    申请日：2022-01-14

    Applicant: Nokia Technologies Oy

    Inventor： Miska Hannuksela ,  Mikko Honkala ,  Jani Lainema ,  Francesco Cricri ,  Emre Aksu

    IPC: H04N19/176 ,  H04N19/149 ,  H04N19/436 ,  H04N19/65 ,  G06N3/08

    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.

Patent Agency Ranking