-
公开(公告)号：US11841921B2
公开(公告)日：2023-12-12
申请号：US17112247
申请日：2020-12-04
Inventor： Xibin Song , Dingfu Zhou , Jin Fang , Liangjun Zhang
IPC: G06T7/50 , G06N20/00 , G06F18/214 , G06V10/42 , G06T3/40
CPC classification number: G06F18/214 , G06N20/00 , G06T3/40 , G06T7/50 , G06V10/42 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084
Abstract: The present application provides a model training method and apparatus, and a prediction method and apparatus, and it relates to fields of artificial intelligence, deep learning, image processing, and autonomous driving. The model training method includes: inputting a first sample image of sample images into a depth information prediction model, and acquiring depth information of the first sample image; acquiring inter-image posture information based on a second sample image of the sample images and the first sample image; acquiring a projection image corresponding to the first sample image, at least according to the inter-image posture information and the depth information; and acquiring a loss function by determining a function for calculating a similarity between the second sample image and the projection image, and training the depth information prediction model using the loss function.
-
公开(公告)号：US11836996B2
公开(公告)日：2023-12-05
申请号：US17209987
申请日：2021-03-23
Inventor： Xiaoqiang Zhang , Pengyuan Lv , Shanshan Liu , Chengquan Zhang
IPC: G06V10/70 , G06F40/10 , G06F18/20 , G06F18/213 , G06V20/62 , G06F40/284 , G06F40/205 , G06V30/148 , G06F18/21 , G06V30/262 , G06V10/764 , G06V10/82 , G06V30/10
CPC classification number: G06V20/62 , G06F18/2178 , G06F40/205 , G06F40/284 , G06V10/764 , G06V10/82 , G06V20/63 , G06V30/153 , G06V30/274 , G06V30/10
Abstract: The present disclosure discloses a method and apparatus for recognizing a text. The method comprises: acquiring images of a text area of an input image, the acquired images including a text centerline graph, a text direction offset graph, a text boundary offset graph, and a text character classification graph; extracting coordinates of feature points of a character center from the text centerline graph; sorting the extracted coordinates of the feature points based on the text direction offset graph to obtain a coordinate sequence of the feature points; determining a polygonal bounding box of the text area based on the coordinate sequence of the feature points of the character center and the text boundary offset graph; and determining a classification result of the feature points of the character center, based on the coordinate sequence of the feature points of the character center and the text character classification graph.
-
803.发明公开公开(公告)号：US20230377225A1
公开(公告)日：2023-11-23
申请号：US18121444
申请日：2023-03-14
Inventor： Chengquan ZHANG , Yuechen YU , Liang WU
CPC classification number: G06T11/60 , G06V20/62 , G06V10/82 , G06V30/19127 , G06V30/1918 , G06V30/1444 , G06V30/19147 , G06V40/10
Abstract: A method for training an image editing model includes steps described below. Covering processing is performed on a region of interest determined in an original image so that a background image sample is formed, and content corresponding to the region of interest is determined as a sample of content of interest; the background image sample and the sample of the content of interest are input into an image editing model; fusion processing is performed on a background image feature and a feature of the region of interest by using the image editing model so that a fusion feature is formed; an image reconstruction operation is performed according to the fusion feature by using the image editing model so that a reconstructed image is output; and optimization training is performed on the image editing model according to a loss relationship between the reconstructed image and the original image.
-
公开(公告)号：US11824714B2
公开(公告)日：2023-11-21
申请号：US17305863
申请日：2021-07-15
Inventor： Xin Zhao , Dayu Shen , Jingru Xie , Sheng Chen
IPC: H04L41/082 , H04L41/08
CPC classification number: H04L41/082 , H04L41/0886
Abstract: Provided are a method and apparatus for updating an edge node, a device, a medium and a program product which relate to the technical field of computers and in particular to the technical fields of edge computing, cloud computing and cloud services. In an embodiment, a module update instruction is received from a cloud server, where the module update instruction includes information about a to-be-updated module; an auxiliary unit or a master unit is used as a target module according to the information about the to-be-updated module, and the to-be-updated module is updated through the target module; and in a process of updating the to-be-updated module, data interaction is performed between the target module and the cloud server.
-
公开(公告)号：US11816443B2
公开(公告)日：2023-11-14
申请号：US17382829
申请日：2021-07-22
Inventor： Xiaojun Zhao , Meng Wang , Qingwei Huang
IPC: G06F40/35 , G06F16/332 , G06F40/279 , G06F11/34 , G06F18/22
CPC classification number: G06F40/35 , G06F11/3438 , G06F16/3325 , G06F16/3329 , G06F18/22 , G06F40/279
Abstract: The disclosure provides a method and an apparatus for generating a response, an electronic device, and a storage medium. The method includes: obtaining a current user request in a current conversation and historical coreference information in the current conversation; extracting content matching the current user request from the historical coreference information; updating the current user request based on the content to obtain an updated current user request; and generating a response of the current user request based on the updated current user request.
-
Patent Agency Ranking
公开(公告)号：US20230359483A1
公开(公告)日：2023-11-09
申请号：US17773874
申请日：2021-05-08
IPC: G06F9/48
CPC classification number: G06F9/48
Abstract: Provided are a method and apparatus for applet page rendering, an electronic device and a storage medium. The method for applet page rendering includes steps described below. Original incremental rendering is performed on an applet page based on a pre-obtained first drawing result of the applet page to obtain an original incremental rendering result of the applet page. Rendering is performed on the applet page based on the pre-obtained first drawing result of the applet page, the original incremental rendering result of the applet page and a pre-obtained initial incremental rendering result of the applet page.
-
公开(公告)号：US11810384B2
公开(公告)日：2023-11-07
申请号：US17172031
申请日：2021-02-09
Inventor： Shanshan Liu , Chengquan Zhang , Xuan Li , Mengyi En , Hailun Xu , Xiaoqiang Zhang
IPC: G06V30/414 , G06V30/24 , G06F18/21 , G06F18/214
CPC classification number: G06V30/414 , G06F18/214 , G06F18/2178 , G06V30/2504 , G06V2201/02
Abstract: The present application discloses a method and an apparatus for recognizing text content, and an electronic device, and relates to a text recognition technique in the field of computer technology. The specific implementation is as follows: acquiring a dial picture; detecting at least one text centerline and a bounding box corresponding to each text centerline in the dial picture; and recognizing text content in each line of text in the dial picture based on the at least one text centerline and the bounding box corresponding to each text centerline.
-
公开(公告)号：US11810319B2
公开(公告)日：2023-11-07
申请号：US17303896
申请日：2021-06-09
Inventor： Xiangbo Su , Jian Wang
CPC classification number: G06T7/73 , G06T7/62 , G06T7/70 , G06V10/25 , G06V10/462 , G06V10/48 , G06T2207/20084
Abstract: Provided are an image detection method and apparatus, a device, a storage medium and a computer program product, the method includes: performing feature extraction on an image to be detected to obtain a feature map; performing target detection on the feature map through a target branch network to obtain target detection information of candidate anchor boxes at a pixel position of the feature map; performing keypoint detection on the feature map through a keypoint branch network to obtain positions of keypoints in the candidate anchor boxes at the pixel position of the feature map, and generating heatmap groups of the candidate anchor boxes according to the positions of the keypoints; and obtaining information about a target object in the image to be detected and positions of keypoints of the target object according to the target detection information and the heatmap groups.
-
公开(公告)号：US20230342560A1
公开(公告)日：2023-10-26
申请号：US18121351
申请日：2023-03-14
Inventor： Ruiqing ZHANG , Hui LIU , Xiyang WANG , Zhongjun HE , Zhi LI , Hua WU
IPC: G06F40/47 , G06F40/166 , G06F40/30
CPC classification number: G06F40/47 , G06F40/166 , G06F40/30 , G06F40/247
Abstract: A text translation method is described that includes initially acquiring text. Thereafter, first text is determined in the initial text; and second text is determined according to the first text, where the second text is used for describing the first text. Additionally, initial text is translated to obtain initial translation text, and the second text is translated to obtain description translation text. Thereafter, the initial translation text is updated according to the description translation text to obtain target translation text of the initial text.
-
810.发明授权公开(公告)号：US11792407B2
公开(公告)日：2023-10-17
申请号：US17353329
申请日：2021-06-21
Inventor： Le Shi , Wenpeng Ding
IPC: H04N19/14 , H04N19/105 , H04N19/159 , H04N19/172
CPC classification number: H04N19/14 , H04N19/105 , H04N19/159 , H04N19/172
Abstract: A method, apparatus, device and medium for coding a video are provided. An implementation plan includes: determining an initial video frame structure based on a preset threshold for a B-frame number; in response to determining that the initial video frame structure meets a preset condition, shortening the initial video frame structure to obtain a candidate video frame structure set; determining a target video frame structure from the candidate video frame structure set; and performing video coding on video frames in a to-be-coded video frame sequence according to the target video frame structure.
-
-
-
-
-
-
-
-
-
Search Results
1986
records
(took 0.031 seconds)
