公开(公告)号：US20250086758A1

公开(公告)日：2025-03-13

申请号：US18728042

申请日：2023-01-13

Applicant: Lemon Inc.

Inventor： Yichun SHI ,  Xiao YANG ,  Xiaohui SHEN

IPC: G06T5/60 ,  G06T5/50

Abstract: The present disclosure provides an image processing method and device. The image processing method includes: performing, by an encoder and a first model, multiple iterations on an initial image to obtain a target image feature corresponding to the initial image; and performing, by a second model, image reconstruction based on the target image feature to obtain a reconstructed image of the initial image, both of the first model and the second model being neural networks for image reconstruction, wherein in the multiple iterations, an image feature extracted by the first model in the image reconstruction and an output image of the first model are feedback information for the encoder to assist the encoder in encoding the initial image.

公开(公告)号：US20250086257A1

公开(公告)日：2025-03-13

申请号：US18957333

申请日：2024-11-22

Applicant: Beijing Youzhuju Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Xiaojun Xu ,  Jinghan Jia ,  Hang Li ,  Yuanshun Yao

IPC: G06F21/16 ,  G06F40/289

Abstract: Embodiments of the present disclosure provide a solution for watermark processing. A method includes: dividing at least one portion of a n original text for watermark embedding into a plurality of original text segments; determining, for an original text segment of the plurality of original text segments, a target symbol from a symbol sequence in watermark information; converting, based on respective target symbols determined for the plurality of original text segments, the plurality of original text segments into a plurality of watermarked text segments by using a set of language models for watermark embedding, the set of language models corresponding to a set of symbol values respectively; and generating a watermarked text for the original text based on the plurality of watermarked text segments.

公开(公告)号：US20250078857A1

公开(公告)日：2025-03-06

申请号：US18241138

申请日：2023-08-31

Applicant: Lemon Inc.

Inventor： Wei Tsung LU ,  Ju-Chiang WANG

IPC: G10L21/0308 ,  G10L25/18 ,  G10L25/30

Abstract: The present disclosure describes techniques for implementing improved audio source separation. A complex spectrum X is split into a plurality of K bands along a frequency axis by applying band-split operations on the complex spectrum X. The complex spectrum is a time-frequency representation of audio signals. Each of the plurality of K bands is denoted as Xk, k=1, . . . , K. Each band Xk comprises one or more frequency bins. Each individual multilayer perceptron is applied to each band Xk to extract latent representations and obtain outputs Hk0. A time-domain transformer and a frequency-domain transformer are applied on a stacked representation H0. Time-domain and frequency-domain transformers are repeatedly applying in an interleaved manner for L times to obtain HL output from the transformer blocks. The HL is input into a multi-band mask estimation sub-model. A complex ideal ratio mask is generated based on outputs from the multi-band mask estimation sub-model.

公开(公告)号：US20250077318A1

公开(公告)日：2025-03-06

申请号：US18818440

申请日：2024-08-28

Applicant: Lemon Inc.

Inventor： Hua LIU ,  Yueyue XIONG

IPC: G06F9/54

Abstract: The embodiments of the present disclosure describe a method for sharing data between a cross-end container and a native runtime environment, a device and a medium. And the method includes: acquiring or updating, by the cross-end container or the native runtime environment, target data, and saving the target data to a shared storage region in the native runtime environment respectively in a first data format corresponding to the cross-end container and a second data format corresponding to the native runtime environment; and accessing, by the native runtime environment or the cross-end container, the shared storage region, and reading the target data in the second data format or the first data format respectively corresponding to the native runtime environment or the cross-end container.

公开(公告)号：US20250077245A1

公开(公告)日：2025-03-06

申请号：US18817627

申请日：2024-08-28

Applicant: Lemon Inc.

Inventor： Hua LIU ,  Lei MA

IPC: G06F9/448

Abstract: Embodiments of the present disclosure provide a method and apparatus for executing program service logic, a device and a medium. The method includes: dividing a plurality of logic blocks included in a target program into a plurality of service logic block sets according to a service to which a logic block belongs; concatenating the plurality of the service logic block sets into a service logic chain which is used for executing respective service logic block set in sequence according to an order of the respective service logic block in the service logic chain. Through the method of the present disclosure, service processing logics of different services can be decoupled, which is convenient for distinguishing and maintaining the processing logics of different services and avoiding the mutual interference of the processing logics of different services during execution.

公开(公告)号：US12243292B2

公开(公告)日：2025-03-04

申请号：US17929449

申请日：2022-09-02

Applicant: Lemon Inc.

Inventor： Shuo Cheng ,  Wanchun Ma ,  Linjie Luo

IPC: G06K9/62 ,  G06N3/0455 ,  G06N3/09 ,  G06V10/44 ,  G06V10/764 ,  G06V10/766 ,  G06V10/774 ,  G06V10/776 ,  G06V10/778 ,  G06V10/82 ,  G06V10/96 ,  G06V40/16

Abstract: Systems and methods for multi-task joint training of a neural network including an encoder module and a multi-headed attention mechanism are provided. In one aspect, the system includes a processor configured to receive input data including a first set of labels and a second set of labels. Using the encoder module, features are extracted from the input data. Using a multi-headed attention mechanism, training loss metrics are computed. A first training loss metric is computed using the extracted features and the first set of labels, and a second training loss metric is computed using the extracted features and the second set of labels. A first mask is applied to filter the first training loss metric, and a second mask is applied to filter the second training loss metric. A final training loss metric is computed based on the filtered first and second training loss metrics.

公开(公告)号：US12243142B2

公开(公告)日：2025-03-04

申请号：US18534233

申请日：2023-12-08

Applicant: LEMON INC.

Inventor： Stacey Dsylva ,  Qiang Chen ,  Alessandro Fantini ,  Harald Buchmann

IPC: G06T13/40 ,  G06F3/04883 ,  G06T7/73 ,  G06V10/25 ,  G06V40/16

Abstract: The embodiment of the disclosure relates to a touch animation display method and apparatus, device, and medium, wherein the method includes the following steps: identifying a human body key point position on a human body in an existing video frame; according to a predetermined motion mode, acquiring a display position of a target object in the existing video frame; according to the human body key point position and the display position, judging whether a preset touch condition is satisfied; if the touch condition is satisfied, adjusting a motion mode of the target object according to a target key point position. Therefore, by displaying the target object in the video frame, the touch motion during interaction with a user is simulated in real time, the interestingness of video display is improved, and the user's interaction experience is improved.

公开(公告)号：US20250056084A1

公开(公告)日：2025-02-13

申请号：US18711497

申请日：2022-11-18

Applicant: LEMON INC.

Inventor： Xiaojie JIN ,  Weibo GONG ,  Quanwei HUANG ,  Xiaohui SHEN

IPC: H04N21/431 ,  G06V10/42 ,  G06V10/44 ,  H04N21/81 ,  H04N21/845

Abstract: The embodiments of the present disclosure provide a video generation method, an apparatus, an electronic device, a storage medium, a computer program product and a computer program, the method including: obtaining a plurality of video segments; determining feature information corresponding to the plurality of video segments; according to the feature information and a plurality of pre-stored rendering effects, determining an effect combination to be added; the rendering effects being animation, special effects or a transition; and generating a target video according to the plurality of video segments and the effect combination to be added.

公开(公告)号：US12219184B2

公开(公告)日：2025-02-04

申请号：US18417071

申请日：2024-01-19

Applicant: Lemon Inc.

Inventor： Weston Bell-Geddes ,  August Yadon ,  Yu Qin ,  Guan-Bai Chen

IPC: H04N21/2187 ,  H04N5/45 ,  H04N21/466

Abstract: A method for live streaming recommended content from a content request includes live streaming a first content from a first user side, activating a live reaction at the first user side, and providing the content request at a second user side when the live reaction is enabled. The method also includes determining a second content, sending the content request indicating the second content, and receiving a confirmation at the second user side indicating the content request being sent. The method further includes receiving, at the first user side, the content request sent from the second user side, approving the content request at the first user side, and after the content request is approved, live streaming from the first user side, the second content corresponding to the content request.

公开(公告)号：US12217466B2

公开(公告)日：2025-02-04

申请号：US17519711

申请日：2021-11-05

Applicant: Lemon Inc.

Inventor： Jing Liu ,  Chunpong Lai ,  Guoxian Song ,  Linjie Luo

IPC: G06K9/00 ,  G06N3/08 ,  G06T9/00 ,  G06T11/60

Abstract: Systems and methods directed to controlling the similarity between stylized portraits and an original photo are described. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be blended with latent vectors that best represent a face in the original user portrait image. The resulting blended latent vector may be provided to a generative adversarial network (GAN) generator to generate a controlled stylized image. In examples, one or more layers of the stylized GAN generator may be swapped with one or more layers of the original GAN generator. Accordingly, a user can interactively determine how much stylization vs. personalization should be included in a resulting stylized portrait.