公开(公告)号：US20220394308A1

公开(公告)日：2022-12-08

申请号：US17720125

申请日：2022-04-13

Applicant: Lemon Inc. ,  Beijing Bytedance Network Technology Co., Ltd. ,  Bytedance INC. ,  Bytedance (HK) Limited

Inventor： Yue Li ,  Li Zhang ,  Kai Zhang ,  Junru Li ,  Meng Wang ,  Siwei Ma ,  Shiqi Wang

IPC: H04N19/82 ,  H04N19/70 ,  H04N19/117

Abstract: A method implemented by a video coding apparatus includes applying a neural network (NN) filter to an unfiltered sample of a video unit to generate a filtered sample. The NN filter is applied based on a syntax element of the video unit. The method also includes converting between a video media file and a bitstream based on the filtered sample that was generated.

公开(公告)号：US20220394288A1

公开(公告)日：2022-12-08

申请号：US17745323

申请日：2022-05-16

Applicant: Lemon Inc.

Inventor： Yue Li ,  Li Zhang ,  Kai Zhang

IPC: H04N19/463 ,  H04N19/117 ,  H04N19/42 ,  H04N7/01 ,  H04N19/31 ,  H04N19/187 ,  H04N19/82

Abstract: A method of processing video data including determining, for a conversion between a video and a bitstream of the video, that the bitstream includes an indicator. The indicator indicates that a first parameter set for a neural network (NN) filter model includes different filter parameters than a second parameter set for the NN filter model. The method further includes performing the conversion based on the indicator. A corresponding video coding apparatus and non-transitory computer readable medium are also disclosed.

公开(公告)号：US20220375024A1

公开(公告)日：2022-11-24

申请号：US17321384

申请日：2021-05-14

Applicant: Lemon Inc.

Inventor： Linjie LUO ,  Guoxian SONG ,  Jing LIU ,  Wanchun MA

IPC: G06T3/00 ,  G06T11/00 ,  G06T5/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and method directed to an inversion-consistent transfer learning framework for generating portrait stylization using only limited exemplars. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be provided to a generative adversarial network (GAN) generator to generate a stylized image. In examples, the variational autoencoder is trained using a plurality of images while keeping the weights of a pre-trained GAN generator fixed, where the pre-trained GAN generator acts as a decoder for the encoder. In other examples, a multi-path attribute aware generator is trained using a plurality of exemplar images and learning transfer using the pre-trained GAN generator.

公开(公告)号：USD969846S1

公开(公告)日：2022-11-15

申请号：US29798523

申请日：2021-07-08

Applicant: Lemon Inc.

Designer： Jiacheng Yang

公开(公告)号：US20220357377A1

公开(公告)日：2022-11-10

申请号：US17732824

申请日：2022-04-29

Applicant: Lemon Inc.

Inventor： Junmou ZHANG ,  Dongrong ZHANG ,  Shan LU ,  Jian WANG

IPC: G01R19/25 ,  G05F1/10 ,  H03K3/037

Abstract: The application provides an apparatus, a system, a detector and a method. The apparatus includes: a power supply voltage detector, including: N buffers, an input terminal of a first buffer being connected to a clock signal, output terminals of other buffers being connected to the input terminal of an adjacent buffer; N latch chains, each of which includes M latches, a clock input terminal of each latch being connected to a clock signal, a D terminal of a first latch of each latch chain being connected to the output terminal of a corresponding buffer, Q terminals of other latches being connected to the D terminal of an adjacent latch, M and N being positive integers, the D terminal of each latch being connected to an area where a power supply voltage is to be detected; and a voltage regulation module connected to the Q terminal of each latch.

公开(公告)号：US20220353565A1

公开(公告)日：2022-11-03

申请号：US17609345

申请日：2021-08-17

Applicant: LEMON INC.

Inventor： Ryan CHOW ,  Jacqueline CRAIG ,  Billy TORRES ,  Peter SCHOEFFMAN ,  Yizhuo WANG ,  Jing XU

IPC: H04N21/431 ,  H04N21/234 ,  H04N21/2668

Abstract: A video distribution system, method, and a storage medium, the system including: at least one database storing a plurality of videos; a computing device communicatively connected with the at least one database and configured to: classify the plurality of videos into a plurality of categories based on attributes associated with the plurality of videos; determine a plurality of cover images; send the plurality of cover images to a user equipment, so that the plurality of cover images are at least partially superimposedly displayed on a first video being played; select a first image from the plurality of cover images in response to a first user input; automatically select a second video from a first category corresponding to the first image; acquire the second video from the at least one database; and send at least a part of the second video to the user equipment to play the second video.

公开(公告)号：US20220353317A1

公开(公告)日：2022-11-03

申请号：US17721049

申请日：2022-04-14

Applicant: Lemon Inc.

Inventor： Ye-kui Wang

IPC: H04L65/65 ,  H04L67/02

Abstract: A mechanism for processing video data is disclosed. An essential property (EssentialProperty) of a Dynamic Adaptive Streaming over Hypertext transfer protocol (DASH) representation is determined. The EssentialProperty indicates that the representation is an external stream representation (ESR). A conversion is performed between a visual media data and a media presentation based on the based on the ESR.

公开(公告)号：US11477437B2

公开(公告)日：2022-10-18

申请号：US17161335

申请日：2021-01-28

Applicant: Lemon Inc.

Inventor： Na Zhang ,  Kai Zhang ,  Li Zhang ,  Hongbin Liu ,  Yuwen He ,  Yue Wang

IPC: H04N19/105 ,  H04N19/132 ,  H04N19/176 ,  H04N19/186 ,  H04N19/46

Abstract: Implementations of the present disclosure provide a solution for encoding and decoding motion information. In this solution, during a conversion between a current video block of a video and a bitstream of the video, a group type of a subgroup of candidates of motion information for the current video block is determined, wherein the group type indicating whether the subgroup of candidates are to be reordered. Further, a list of candidates are constructed based on the group type; and the motion information for the current video block is derived from the list of candidates.

公开(公告)号：US20220329836A1

公开(公告)日：2022-10-13

申请号：US17714014

申请日：2022-04-05

Applicant: Lemon Inc.

Inventor： Yue Li ,  Li Zhang ,  Kai Zhang

IPC: H04N19/436 ,  H04N19/132 ,  H04N19/154 ,  H04N19/124 ,  H04N19/169 ,  H04N19/30 ,  H04N19/186 ,  H04N19/172 ,  H04N19/82 ,  H04N19/70

Abstract: A method implemented by a video coding apparatus includes applying a neural network (NN) filter to an unfiltered sample of a video unit to generate a filtered sample, wherein the NN filter is based on an NN filter model generated using a quality-level indicator (QI) input. The method also includes converting between a video media file and a bitstream based on the filtered sample that was generated.

公开(公告)号：US20220295089A1

公开(公告)日：2022-09-15

申请号：US17200631

申请日：2021-03-12

Applicant: Lemon Inc.

Inventor： Na ZHANG ,  Kai ZHANG ,  Hongbin LIU ,  Li ZHANG ,  Yue WANG

IPC: H04N19/513 ,  H04N19/137 ,  H04N19/105 ,  H04N19/46 ,  H04N19/176

Abstract: Embodiments of the present disclosure provide methods, apparatuses and computer storage media for video processing. One example method comprises determining, during a conversion between a current video block of a video and a bitstream of the video, at least one set of motion candidates for the current video block, each motion candidate comprising predicted motion information determined from neighboring video blocks of the current video block; determining, based on a template of the current video block and from the at least one set of motion candidates, a target motion candidate for the current video block by using a template matching cost rule; and performing the conversion based on the target motion candidate.