-
公开(公告)号：US20240312097A1
公开(公告)日：2024-09-19
申请号：US18669294
申请日：2024-05-20
Applicant: Lemon Inc.
Inventor： Jie Meng , Tingwen Liao , Maryyann Crichton , Siding Chen , Vishnuvardhan Tanguturi
CPC classification number: G06T13/40 , G06F3/012 , G06T7/246 , G06T7/73 , G06T19/006 , G06T2207/30201 , G06T2219/024
Abstract: A computing system is provided comprising a processor is configured to execute an augmented reality avatar program to receive a second-user avatar-data object and second-user pose information, via a computer network, receive an image from a live image feed captured by a camera of the computing device, identify a virtual surface corresponding to a physical surface that appears in the image; calculate a position and a pose of a second-user avatar relative to the virtual surface based on the second-user pose information, render the second-user avatar-data object to thereby display the second-user avatar of the second user superimposed upon the image. The second-user avatar is anchored to the virtual surface according to the calculated position and pose of the second-user avatar. The virtual surface is world-locked to the physical surface in the image in a real world 3-D environment.
-
公开(公告)号：US12093512B2
公开(公告)日：2024-09-17
申请号：US18207009
申请日：2023-06-07
Applicant: Lemon Inc.
Inventor： Philip Anthony Sant , Dominic Blatchford , Neal Hart , Matthew White
IPC: G06F3/048 , G06F3/0484 , G06F16/438 , G06F16/683 , G06F16/783
CPC classification number: G06F3/0484 , G06F16/4387 , G06F16/683 , G06F16/783
Abstract: The field of the invention relates to methods, systems and computer program products for navigating digital media content, in particular for navigating digital media content using an interface abstracted from that digital media content instead of, or as a supplement to, traditional user interface controls. There is provided a method for presenting a user interface to an end user to facilitate the searching, browsing and/or navigation of digital media content, the method comprising the steps of: (a) analysing the digital media content to create “hooks” related to the digital media content, or retrieving “hooks” in the digital media content, and (b) replacing or augmenting a graphical or textual representation of the digital media content with the “hooks.”
-
公开(公告)号：US20240300958A1
公开(公告)日：2024-09-12
申请号：US18599116
申请日：2024-03-07
Applicant: BEIJING YOUZHUJU NETWORK TECHNOLOGY CO. LTD. , Lemon Inc.
Inventor： Yuwei Yang , Hao Zhou
IPC: C07D487/04 , A61K31/5025 , A61P11/00 , A61P35/00
CPC classification number: C07D487/04 , A61K31/5025 , A61P11/00 , A61P35/00
Abstract: The present invention provides a compound which is the compound represented by Formula A or a pharmaceutically acceptable salt thereof. The present invention further provides a pharmaceutical composition comprising the compound as described above and at least one pharmaceutically acceptable excipient. The present invention further provides the use of the compound as described above in the manufacture of a medicament for the treatment of at least one of inflammation, fibrotic disease and cancer. With the above aspects, the present invention provides a DDR1 inhibitor having both high inhibitory activity and high selectivity, and thus provides a novel solution for the treatment of DDR1-related diseases.
-
374.发明授权公开(公告)号：US12079902B2
公开(公告)日：2024-09-03
申请号：US18052862
申请日：2022-11-04
Applicant: Lemon Inc.
Inventor： Qing Yan , Bingchen Liu , Yizhe Zhu , Xiao Yang
Abstract: Systems and methods are provided that include a processor executing a program to process an initial image through a first diffusion stage to generate a final first stage image, wherein the first diffusion stage includes using a diffusion model, a gradient estimator model smaller than the diffusion model, and a text-image match gradient calculator. The processor further executes the program to process the final first stage image through a second diffusion stage to generate a final second stage image. The second diffusion stage includes, for a second predetermined number of iterations, inputting the final first stage image to through the diffusion model, back-propagate the image through the text-image match gradient calculator to calculate a second stage gradient against the input text, and update the final first stage image by applying the second stage gradient to the final first stage image.
-
公开(公告)号：US20240290016A1
公开(公告)日：2024-08-29
申请号：US18570533
申请日：2022-05-09
Applicant: Lemon Inc.
Inventor： Xiaojie JIN , Yan WANG
CPC classification number: G06T11/60 , G06V10/44 , G06V10/462 , G06V40/168
Abstract: The present disclosure relates to an image processing method, an apparatus, and a readable storage medium. The image processing method may obtain a multimedia resource with content continuity by: performing feature analysis on at least one image material to acquire a content feature set, where each content feature included in the content feature set is used for representing a content expressed by the image material in a corresponding particular dimension; next, acquiring an editing strategy of the at least one image material based on the content feature set and in accordance with a mapping relationship between different content features in the particular dimension and different operation modes of different editing operation types; and synthesizing the at least one image material according to each target editing operation mode included in the editing strategy.
-
Patent Agency Ranking
公开(公告)号：US20240289394A1
公开(公告)日：2024-08-29
申请号：US18572097
申请日：2022-06-02
Applicant: Lemon Inc.
Inventor： Han WANG , Hongyu XIONG , Yiqi FENG , Zhen LIU , Haocheng ZHANG , Bin LIU
IPC: G06F16/906 , G06F16/9535 , G06F16/958
CPC classification number: G06F16/906 , G06F16/9535 , G06F16/958
Abstract: The present disclosure relates to a web page classification method, apparatus, storage medium, and electronic device. The method comprises: acquiring feature information of a web page to be classified; respectively predicting, according to each piece of the feature information, a candidate web page category of the web page to be classified; and determining, from all the candidate web page categories, a target web page category to which the web page to be classified belongs. The candidate web page category of the web page to be classified is predicted by using various feature information of the web page to be classified, and the target web page category of the web page to be classified is further determined from the candidate web page categories, thereby improving the accuracy of web page classification.
-
公开(公告)号：US20240289316A1
公开(公告)日：2024-08-29
申请号：US18590595
申请日：2024-02-28
Applicant: Lemon Inc. , Douyin Vision Co., Ltd.
Inventor： Yuxiang Huang , Jian Lei , Wei Huang , Xinhao Zhang
CPC classification number: G06F16/2272 , G06F16/2365 , G06F16/2372
Abstract: The disclosure discloses a method, apparatus, device, medium and product for managing activity data within an application. The method includes: obtaining a queue message in a preset activity data reporting event message queue, and storing activity data corresponding to the queue message into a first preset database of at least one data storage space having a business association with the activity data; and managing the activity data according to duration of the activity data stored in the first preset database and/or a management operation of a user for the activity data; where the first preset database is a key-value database that meets a first preset storage performance standard.
-
公开(公告)号：US12072500B2
公开(公告)日：2024-08-27
申请号：US18153970
申请日：2023-01-12
Applicant: Lemon Inc.
Inventor： Runyu Liu , Bowei Zhang
CPC classification number: G02B27/0172 , G02B27/0093 , G02B27/0961 , H01S5/423
Abstract: An optical device is provided, including a body formed to have a concavity within which an eye box region is defined; and a plurality of addressable vertical cavity surface emitting laser (VCSEL) arrays arranged in the body of the optical device. The one or more VCSEL arrays comprise a plurality of VCSEL subarrays including independently addressable first and second VCSEL subarrays, which are controlled so as to power the first VCSEL subarray and not the second VCSEL subarray to illuminate only a first subregion of the eye box region, or to power the second VCSEL subarray and not the first VCSEL subarray to only illuminate a second subregion of the eye box region.
-
公开(公告)号：US20240281919A1
公开(公告)日：2024-08-22
申请号：US18567695
申请日：2022-09-22
Applicant: Lemon Inc.
Inventor： Jiali Pan , Haipeng Liu , Boyuan Hu , Anda Li
CPC classification number: G06T1/20 , G06T11/001 , G06T2210/56
Abstract: Embodiments of the present disclosure provide an effect processing method and apparatus. The method comprises: acquiring effect resource data comprising a self-defined effect logic, the effect logic being used for specifying at least one effect processor and at least two associated effect processing units included in each effect processor; generating the effect processor and the effect processing units according to the effect logic, the effect processing units being used for processing the particles through a shader of a GPU; according to an association relationship between the effect processing units, sequentially invoking the effect processing units to process particles corresponding to the effect processor, to obtain an effect picture, wherein the particles are display objects of geometry.
-
380.发明公开公开(公告)号：US20240274120A1
公开(公告)日：2024-08-15
申请号：US18568261
申请日：2022-09-16
Applicant: Lemon Inc.
Inventor： Dongyang Dai , Yuanzhe Chen , Li Chen , Yuping Wang , Qiao Tian , Ming Tu , Rui Xia , Yuxuan Wang
IPC: G10L13/027 , G10L25/18
CPC classification number: G10L13/027 , G10L25/18
Abstract: Provided are an audio synthesis method and apparatus, an electronic device, and a readable storage medium. In the present solution, conversion from a text to an audio having a target timbre is achieved by means of a pre-trained voice synthesis model, the voice synthesis model comprising a first feature extraction sub-model and a second feature extraction sub-model, wherein the first feature extraction sub-model outputs, according to an inputted text to be processed, an acoustic feature comprising a bottleneck feature; the second feature extraction sub-model outputs, according to the inputted first acoustic features, a Mel spectrum feature corresponding to the text to be processed; according to the Mel spectrum feature corresponding to the text to be processed, the target audio corresponding to the text to be processed is obtained, and the target audio has the target timbre.
-
-
-
-
-
-
-
-
-
Search Results
812
records
(took 0.06 seconds)
