公开(公告)号：US11871143B2

公开(公告)日：2024-01-09

申请号：US17476885

申请日：2021-09-16

Applicant: Lemon Inc.

Inventor： Ye-Kui Wang

IPC: H04N7/01 ,  H04N19/132 ,  H04N19/136 ,  H04N19/157 ,  H04N19/172 ,  H04N19/105 ,  H04N19/70 ,  H04N19/177 ,  H04N19/184

CPC classification number: H04N7/01 ,  H04N19/105 ,  H04N19/132 ,  H04N19/136 ,  H04N19/157 ,  H04N19/172 ,  H04N19/177 ,  H04N19/184 ,  H04N19/70

Abstract: Systems, methods and apparatus for processing visual media data are described. One example method includes performing a conversion between visual media data and a visual media file that includes one or more tracks that store one or more bitstreams of the visual media data; and wherein the visual media data comprises one or more pictures comprising one or more subpictures or one or more slices; wherein the visual media file stores the one or more tracks according to a format rule; and wherein the format rule specifies that a track that includes a sequence of the one or more slices or the one or more subpictures covers a rectangular area of the one or more pictures.

公开(公告)号：US20230410396A1

公开(公告)日：2023-12-21

申请号：US17843891

申请日：2022-06-17

Applicant: Lemon Inc.

Inventor： Chenyu Sun ,  Maryyann Crichton ,  Xuye Cai ,  Tao Xiong ,  Jing Jie Chen ,  Carmen Worthge ,  Julia Meng ,  Michelle Catalanotto

IPC: G06T13/20 ,  H04N5/262 ,  G06T13/80

CPC classification number: G06T13/205 ,  H04N5/2621 ,  G06T13/80

Abstract: A first type of input may be received via a first component of a computing device during creation of a video item. The first type of input may correspond to a first type of element associated with the video item. Characteristics of signals in the first type of input may be determined, in real time, based on the first type of input. At least one modification may be caused to a second type of element associated with the video item based at least in part on the characteristics of the signals in the first type of input. In some examples, the first type of input may be audio input, and the second type of element may comprise a visual element. In other examples, the first type of input may be video input, and the second type of element may comprise an audio element.

公开(公告)号：US20230401124A1

公开(公告)日：2023-12-14

申请号：US18449213

申请日：2023-08-14

Applicant: Lemon Inc. ,  Beijing Volcano Engine Technology Co., Ltd.

Inventor： Peng Xu ,  Fei Liu ,  Kyoungryun Bae ,  Jinhyuk Kim ,  Hyungjin Im ,  Kyung Ho Kim ,  Prathamesh Amritkar ,  Chaohong Hu ,  Ken Hu

IPC: G06F11/10 ,  G06F11/07 ,  G06F11/30

CPC classification number: G06F11/1068 ,  G06F11/0793 ,  G06F11/076 ,  G06F11/3058

Abstract: Media scans to test the integrity of data stored in non-volatile storage are weighted to improve the efficiency of the scans and preserve operating bandwidth of the corresponding device.

公开(公告)号：US20230385331A1

公开(公告)日：2023-11-30

申请号：US18231499

申请日：2023-08-08

Applicant: LEMON INC.

Inventor： Fernando WANG ,  Michael BUZINOVER ,  Jialiang ZHANG ,  Ning LI

IPC: G06F16/438 ,  G06F16/432

CPC classification number: G06F16/4393 ,  G06F16/433

Abstract: A plurality of music samples and a plurality of images corresponding to the music samples may be stored in a database. The plurality of music samples may be sorted in an order of priority. Information associated with the plurality music samples may be sent to a user device. The user device may display the plurality of images corresponding to the plurality of music samples in the order of priority. The user device may receive information indicative of at least one video associated with a music sample in response to receiving user input indicative of a selection of an image among the plurality of images. The user device may display at least one sample video image corresponding to the at least one video associated with the music sample.

公开(公告)号：US11831921B2

公开(公告)日：2023-11-28

申请号：US17477320

申请日：2021-09-16

Applicant: Lemon Inc.

Inventor： Ye-Kui Wang

IPC: H04N19/70 ,  H04N19/105 ,  H04N19/132 ,  H04N19/169 ,  H04N19/172 ,  H04N19/184 ,  H04N19/186

CPC classification number: H04N19/70 ,  H04N19/105 ,  H04N19/132 ,  H04N19/172 ,  H04N19/184 ,  H04N19/186 ,  H04N19/188

Abstract: Systems, methods and apparatus for processing visual media data are described. One example method includes performing a conversion between visual media data and a visual media file that includes one or more tracks that store one or more bitstreams of the visual media data according to a format rule; wherein the visual media file includes an operating point record and an operating point group box, and wherein the format rule specifies to include, for each operating point indicated in the visual media file, in the operating point record and the operating point group box, a first element indicative of a chroma format, a second element indictive of a bit depth information, a third element indicative of a maximum picture width, and/or a fourth element indicative of a maximum picture height.

公开(公告)号：US20230377591A1

公开(公告)日：2023-11-23

申请号：US17748882

申请日：2022-05-19

Applicant: Lemon Inc.

Inventor： Lamtharn HANTRAKUL ,  David TREVELYAN ,  Haonan CHEN ,  Matthew David AVENT ,  Janne Jayne Harm Renée SPIJKERVET

IPC: G10L21/0264 ,  G10L21/04 ,  G10L25/18

CPC classification number: G10L21/0264 ,  G10L21/04 ,  G10L25/18

Abstract: Example aspects include techniques for implementing real-time and low-latency synthesis of audio. These techniques may include generating a frame by sampling audio input in increments equal to a buffer size of until a threshold corresponding to a frame size used to train a machine learning (ML) model is reached, detecting feature information within the frame, determining, by the ML model, control information for audio reproduction based on the feature information. In addition, the techniques may include generating filtered noise information by inverting the noise magnitude control information using an overlap and add technique, generating, based on the control information, additive harmonic information by combining a plurality of scaled wavetables, and rendering audio output based on the filtered noise information and the additive harmonic information.

公开(公告)号：US20230377368A1

公开(公告)日：2023-11-23

申请号：US17751393

申请日：2022-05-23

Applicant: LEMON Inc.

Inventor： Shuo CHENG ,  Guoxian SONG ,  Wanchun MA ,  Chao Wang ,  Linjie LUO

IPC: G06V40/16 ,  G06V10/74 ,  G06V10/82 ,  G06T11/60

CPC classification number: G06V40/172 ,  G06V10/761 ,  G06V10/82 ,  G06T11/60

Abstract: Methods and systems for generating synthetic images based on an input image are described. The method may include receiving an input image; generating, using an encoder, a first latent code vector representation based on the input image; receiving a latent code corresponding to a feature to be added to the input image; modifying the first latent code vector representation based on the latent code corresponding to the feature to be added; generating, by an image decoder, a synthesized image based on the modified first latent code vector representation; identifying, using a landmark detector, one or more landmarks in the base image; identifying, using a landmark detector, one or more landmarks in the synthesized image; determining a measure of similarity between the landmark identified on the base image and the landmark identified in the synthesized image; and discarding the synthesized image based on the comparison.

公开(公告)号：US20230376242A1

公开(公告)日：2023-11-23

申请号：US17746831

申请日：2022-05-17

Applicant: Lemon Inc.

Inventor： Viacheslav Dubeyko ,  Jian Wang

IPC: G06F3/06

CPC classification number: G06F3/0659 ,  G06F3/0679 ,  G06F3/0604

Abstract: A system includes a first hardware architecture and computational storage. The computational storage includes a second hardware architecture, and memory storing instructions that, when executed by the second hardware architecture, causes the system to perform a first set of operations. The first set of operations include receiving instructions from the first hardware architecture, performing one or more computations on data stored in the second hardware architecture, based on the received instructions, and transmitting a result to the first hardware architecture, based on the one or more performed computations.

公开(公告)号：US20230360620A1

公开(公告)日：2023-11-09

申请号：US17737216

申请日：2022-05-05

Applicant: Lemon Inc.

Inventor： Bochen LI ,  Andrew SHAW ,  Jitong CHEN

IPC: G10H1/00 ,  G10H1/38

CPC classification number: G10H1/0025 ,  G10H1/38 ,  G10H2250/311

Abstract: In examples, a method for converting audio samples to full song arrangements is provided. The method includes receiving audio sample data, determining a melodic transcription, based on the audio sample data, and determining a sequence of music chords, based on the melodic transcription. The method further includes generating a full song arrangement, based on the sequence of music chords, and the audio sample data.

公开(公告)号：US20230343038A1

公开(公告)日：2023-10-26

申请号：US17728662

申请日：2022-04-25

Applicant: Lemon Inc.

Inventor： Linshen XIAO ,  Siding CHEN ,  Jeffrey Jia-Jun CHEN ,  Zhe HUANG ,  Jingcong ZHANG

IPC: G06T19/00 ,  G06T11/00 ,  G06F3/04845

CPC classification number: G06T19/006 ,  G06T11/00 ,  G06F3/04845

Abstract: Example aspects include techniques for creating an augmented reality filter on a mobile device. These techniques may include receiving, in response to a selection of a primary augment reality filter template (ARFT), a primary ARFT package corresponding to the primary ARFT, and receiving, in response to the selection of a secondary ARFT, a secondary ARFT package corresponding to the secondary ARFT. In addition, the techniques may include loading the primary ARFT package and the secondary ARFT package to form a combined ARFT, and modifying, based on user input received via a user interface, the combined ARFT to create a customized augmented reality filter (CARF). Further, the techniques may include generating, for the CARF via the development engine, a configuration file that causes the mobile application to add custom perceptive information to visual data.