公开(公告)号：US12106740B2

公开(公告)日：2024-10-01

申请号：US17502890

申请日：2021-10-15

Applicant: Lemon Inc.

Inventor： Ju-Chiang Wang ,  Jordan Smith ,  Wei Tsung Lu

IPC: G06F17/00 ,  G06N3/08 ,  G10H1/00

CPC classification number: G10H1/0008 ,  G06N3/08 ,  G10H2210/076 ,  G10H2250/311

Abstract: Devices, systems, and methods related to implementing supervised metric learning during a training of a deep neural network model are disclosed herein. In examples, audio input may be received, where the audio input includes a plurality of song fragments from a plurality of songs. For each song fragment, an aligning function may be performed to center the song fragment based on determined beat information, thereby creating a plurality of aligned song fragments. For each song fragment of the plurality of song fragments, an embedding vector may be obtained from the deep neural network. Thus, a batch of aligned song fragments from the plurality of aligned song fragments may be selected, such that a training tuple may be selected. A loss metric may be generated based on the selected training tuple and one or more weights of the deep neural network model may be updated based on the loss metric.

公开(公告)号：US20240312596A1

公开(公告)日：2024-09-19

申请号：US18605328

申请日：2024-03-14

Applicant: Beijing Zitiao Network Technology Co., Ltd. ,  LEMON INC.

Inventor： Li LI ,  Matthew BORING ,  Dongpo LI ,  Yun LIAO ,  Runchen ZHAO ,  Tianjia SUN ,  Guanqun ZHANG ,  Can JIN

IPC: G16H20/30 ,  G06N3/126 ,  G16H40/67

CPC classification number: G16H20/30 ,  G06N3/126 ,  G16H40/67

Abstract: The present disclosure provides a data processing method and device, the method includes: acquiring exercise data of a user in a preset time period and a physical parameter preset by the user, wherein the exercise data comprises exercise data of a head, a hand and a leg of the user; and inputting the exercise data and the physical parameter into a pre-trained energy determination model for processing to obtain energy consumed by the user in the preset time period.

公开(公告)号：US12095988B2

公开(公告)日：2024-09-17

申请号：US17848054

申请日：2022-06-23

Applicant: Lemon, Inc.

Inventor： Yue Li ,  Kai Zhang ,  Li Zhang

IPC: H04N19/117 ,  G06N3/04 ,  H04N19/132 ,  H04N19/176 ,  H04N19/82

CPC classification number: H04N19/117 ,  G06N3/04 ,  H04N19/132 ,  H04N19/176 ,  H04N19/82

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 based on an NN filter model configured to obtain an attention based on a coding parameter input. The method also includes performing a conversion between a video media file and a bitstream based on the filtered sample that was generated.

公开(公告)号：US20240289312A1

公开(公告)日：2024-08-29

申请号：US18572606

申请日：2022-06-21

Applicant: LEMON INC.

Inventor： Longyin Wen ,  Xinyao Wang ,  Dexiang Hong ,  Congcong Li

IPC: G06F16/22

CPC classification number: G06F16/2228

Abstract: Methods, apparatuses and electronic devices for information segmentation. The method includes, for a target information node in an information sequence and based on first node information of the target information node, determine a first demarcation point probability value, in which the first demarcation point probability value indicates a probability that the target information node is a first type of demarcation point; determine, based on the first demarcation point probability value and second node information of the target information node, a second demarcation point probability value, in which the second demarcation point probability value indicates a probability that the information node is a second type of demarcation point, and the first type of demarcation point is associated with the second type of demarcation point; and determines, based on the first and the second demarcation point probability value, at least two segmentation modes for the information sequence.

公开(公告)号：US20240282329A1

公开(公告)日：2024-08-22

申请号：US18570923

申请日：2022-08-18

Applicant: Lemon Inc.

Inventor： Qiuqiang Kong ,  Haohe Liu

IPC: G10L21/0308 ,  G10L25/18

CPC classification number: G10L21/0308 ,  G10L25/18

Abstract: Provided in the embodiments of the present disclosure are an audio signal separation method and apparatus, a device, an electronic device, a computer-readable storage medium, a computer program product, and a computer program. The method comprises: determining first amplitude information of a mixed audio signal to be processed, and first phase information of the mixed audio signal; processing the first amplitude information to obtain amplitude difference information and phase difference information between the mixed audio signal and a first audio signal, wherein the first audio signal is a pure audio signal corresponding to a first sound source in the mixed audio signal; and according to the first amplitude information, the first phase information, the amplitude difference information, and the phase difference information, determining the first audio signal. By means of the described process, the audio separation effect can be improved.

公开(公告)号：US20240265621A1

公开(公告)日：2024-08-08

申请号：US18165794

申请日：2023-02-07

Applicant: Lemon Inc.

Inventor： Hongyi Xu ,  Guoxian Song ,  Zihang Jiang ,  Jianfeng Zhang ,  Yichun Shi ,  Jing Liu ,  Wanchun Ma ,  Jiashi Feng ,  Linjie Luo

IPC: G06T15/08 ,  G06T3/40 ,  G06V40/16

CPC classification number: G06T15/08 ,  G06T3/4046 ,  G06T3/4053 ,  G06V40/176

Abstract: Technologies are described and recited herein for producing controllable synthesized images include a geometry guided 3D GAN framework for high-quality 3D head synthesis with full control on camera poses, facial expressions, head shape, articulated neck and jaw poses; and a semantic SDF (signed distance function) formulation that defines volumetric correspondence from observation space to canonical space, allowing full disentanglement of control parameters in 3D GAN training.

公开(公告)号：US12045912B2

公开(公告)日：2024-07-23

申请号：US17714920

申请日：2022-04-06

Applicant: Lemon Inc.

Inventor： Tianyang Xu ,  Xiaojie Li ,  Yuxi Zhang ,  Qingyu Chen ,  Peilin Li

IPC: G06T11/00 ,  G06F3/0482 ,  G06N3/08 ,  G06T7/246 ,  G06V40/10 ,  H04L65/60 ,  H04N5/265

CPC classification number: G06T11/00 ,  G06F3/0482 ,  H04L65/60 ,  H04N5/265 ,  G06F2203/04803 ,  G06N3/08 ,  G06T7/246 ,  G06T7/251 ,  G06T2200/24 ,  G06T2210/16 ,  G06V40/10

Abstract: The present disclosure describes techniques for social networking based on collecting asset items. Features may be extracted from an image comprising an object and captured by a camera. The object may be associated with a location. The location may be determined based on information indicating a position where the camera is located. The object may be recognized based at least in part on the features extracted from the image. An asset item may be displayed in response to recognizing the object.

公开(公告)号：US20240242736A1

公开(公告)日：2024-07-18

申请号：US18562230

申请日：2022-05-23

Applicant: Lemon Inc.

Inventor： Imran RASHID ,  Jordan SMITH ,  Fraser SMITH ,  Will HAWKINS ,  Edmund Philip Newton-Rex

IPC: G11B27/031

CPC classification number: G11B27/031

Abstract: The present invention relates to method for generating a video remix, the method comprising: receiving an input video; selecting at least one excerpt from the input video, wherein an audio signal of the selected excerpt includes at least one onset; determining a plurality of sub-sequences of the at least one excerpt; and rearranging the plurality of sub-sequences according to a predetermined pattern to form the video remix.

公开(公告)号：US12041386B2

公开(公告)日：2024-07-16

申请号：US17484338

申请日：2021-09-24

Applicant: Lemon Inc.

Inventor： Ye-Kui Wang

IPC: H04N19/46 ,  H04N7/01 ,  H04N19/105 ,  H04N19/107 ,  H04N19/172 ,  H04N19/30 ,  H04N19/70 ,  H04N19/91

CPC classification number: H04N7/01 ,  H04N19/105 ,  H04N19/107 ,  H04N19/172 ,  H04N19/30 ,  H04N19/46 ,  H04N19/70 ,  H04N19/91

Abstract: Systems, methods and apparatus for encoding, decoding or transcoding visual media data are described. One example method of processing visual media data includes performing a conversion between visual media data and a bitstream of the visual media data according to a format rule, wherein the format rule specifies whether and how a second type of supplemental enhancement information (SEI) message that is different from a first type of SEI message is included in the bitstream, and wherein the first type of the SEI message and the second type of the SEI message indicate a first type of dependent random access point (DRAP) picture and a second type of DRAP picture, respectively.

公开(公告)号：US20240233088A9

公开(公告)日：2024-07-11

申请号：US18543969

申请日：2023-12-18

Applicant: Lemon Inc.

Inventor： Yi MO ,  Michel JONES ,  Congxiao LIU ,  Jing GAO

IPC: G06T5/50 ,  G06T7/194 ,  G06V10/46

CPC classification number: G06T5/50 ,  G06T7/194 ,  G06V10/46 ,  G06T2207/20132 ,  G06T2207/20221

Abstract: The present disclosure provides a video generation method, an apparatus, a device and a medium, and the method includes: acquiring background images; acquiring an image to be segmented comprising a target object; performing image segmentation for the target object on the image to be segmented to obtain a contour image corresponding to the target object; using the contour image as a foreground image of a target display video; and cyclically flipping the background images, and generating the target display video by fusing the foreground image and the background images, in which the background images are being cyclically flipped in the target display video.