-
公开(公告)号：US20230051232A1
公开(公告)日：2023-02-16
申请号：US17976673
申请日：2022-10-28
Inventor： Desen ZHOU , Jian WANG , Hao SUN
Abstract: A human-object interaction detection method, a neural network and a training method therefor is provided. The human-object interaction detection method includes: performing first target feature extraction on an image feature of an image; performing first interaction feature extraction on the image feature; processing a plurality of first target features to obtain target information of a plurality of detected targets; processing one or more first interaction features to obtain motion information of a motion, human information of a human target corresponding to each motion, and object information of an object target corresponding to each motion; matching the plurality of detected targets with one or more motions; and updating human information of a corresponding human target based on target information of a detected target matching the corresponding human target, and updating object information of a corresponding object target based on target information of a detected target matching the corresponding object target.
-
公开(公告)号：US20230048495A1
公开(公告)日：2023-02-16
申请号：US17974183
申请日：2022-10-26
Inventor： Qunyi XIE , Xiameng QIN , Mengyi EN , Dongdong ZHANG , Ju HUANG , Yangliu XU , Yi CHEN , Kun YAO
IPC: G06V30/413 , G06V10/764 , G06V10/24 , G06V10/75 , G06V30/414
Abstract: A method and a platform of generating a document, an electronic device, and a storage medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision and deep learning technologies, and may be applied to a text recognition scenario and other scenarios. The method includes: performing a category recognition on a document picture to obtain a target category result; determining a target structured model matched with the target category result; and performing, by using the target structured model, a structure recognition on the document picture to obtain a structure recognition result, so as to generate an electronic document based on the structure recognition result, wherein the structure recognition result includes a field attribute recognition result and a field position recognition result.
-
163.发明申请公开(公告)号：US20230024680A1
公开(公告)日：2023-01-26
申请号：US17957275
申请日：2022-09-30
Inventor： Xinjiang LU , Dejing DOU
Abstract: A method of determining a regional land usage property, an electronic device and a storage medium, which relate to a field of an information technology, in particular to a field of a deep learning. The method includes: acquiring a human interaction information between a plurality of regions at a specified time; updating an initial representation vector of each of the regions according to the human interaction information, so as to obtain an embedding representation vector of each of the regions; selecting a target region from the regions, and selecting a plurality of static neighbor regions within a preset range around the target region; generating a feature map of the target region according to the embedding representation vector of the target region and the embedding representation vectors of the plurality of static neighbor regions; and predicting a land usage property of the target region by using the feature map.
-
公开(公告)号：US20230023290A1
公开(公告)日：2023-01-26
申请号：US17814666
申请日：2022-07-25
Inventor： Bin He
Abstract: Disclosed are a method for managing a function based on an engine, an electronic device and a medium, which relate to a field of computer technologies, and particularly to a field of artificial intelligence (AI) technologies such as cloud computing, big data and deep learning. The technical solution includes: generating a function creating request, in which the function creating request comprises Java Archive File (JAR) package path information; sending the function creating request to a coordinate machine node of the engine; obtaining, by the coordinate machine node based on the JAR package path information, a JAR package; copying the JAR package to a plug-in directory corresponding to each worker node of at least one worker node of the engine; and performing, by a daemon thread, registration and loading of a function corresponding to the JAR package in the plug-in directory.
-
公开(公告)号：US20230020022A1
公开(公告)日：2023-01-19
申请号：US17885882
申请日：2022-08-11
Inventor： Shanshan LIU , Meina QIAO , Liang WU , Chengquan ZHANG , Kun YAO
Abstract: A method of recognizing a text, which relates to a field of an artificial intelligence technology, in particular to a field of computer vision and deep learning technology, and may be applied to optical character recognition or other applications. The method includes: acquiring a plurality of image sequences by continuously scanning a document; performing an image stitching, so as to obtain a plurality of successive frames of stitched images corresponding to the plurality of image sequences respectively, an overlapping region exists between each two successive frames of stitched images; performing a text recognition based on the plurality of successive frames of stitched images, so as to obtain a plurality of corresponding recognition results; and performing a de-duplication on the plurality of recognition results based on the overlapping region between each two successive frames of stitched images, so as to obtain a text recognition result for the document.
-
Patent Agency Ranking
公开(公告)号：US20230015313A1
公开(公告)日：2023-01-19
申请号：US17656160
申请日：2022-03-23
Inventor： Chuanqiang Zhang , Ruiqing Zhang , Zhongjun He , Zhi Li , Hua Wu
IPC: G06F40/58 , G06F40/279
Abstract: Disclosed are a translation method, a classification model training method, a device and a storage medium, which relate to the field of computer technologies, particularly to the field of artificial intelligence such as natural language processing and deep learning. The translation method includes: obtaining a current processing unit of a source language text based on a segmented word in the source language text; determining a classification result of the current processing unit with a classification model; and in response to determining that the classification result is the current processing unit being translatable separately, translating the current processing unit to obtain translation result in a target language corresponding to the current processing unit.
-
167.发明申请公开(公告)号：US20230014427A1
公开(公告)日：2023-01-19
申请号：US17933180
申请日：2022-09-19
Inventor： Biao Cao , Meng Wang , Yongqiang Yang
Abstract: A global secondary index method for a distributed database, includes: obtaining original data to be written in response to a database writing request; writing the original data into the distributed database; performing global secondary index processing on the original data written into the distributed database to obtain global secondary index data; establishing global secondary index tables between the global secondary index data and data table primary keys in the distributed database; and writing the global secondary index tables into an index shards based on an asynchronous processing manner.
-
公开(公告)号：US20230011678A1
公开(公告)日：2023-01-12
申请号：US17935233
申请日：2022-09-26
Inventor： Yang Xue , Zijing Liu , Xiaomin Fang , Fan Wang , Jingzhou He
Abstract: Provided is a method for predicting protein-protein interaction. Also provided are an electronic device and a non-transitory computer readable storage medium.
-
公开(公告)号：US20230010160A1
公开(公告)日：2023-01-12
申请号：US17945415
申请日：2022-09-15
Inventor： Shuai CHEN , Qi WANG , Hu YANG , Feng HE , Zhifan FENG , Chunguang CHAI , Yong ZHU
Abstract: Disclosed are a method for processing multimodal data using a neural network, a device, and a medium, and relates to the field of artificial intelligence and, in particular to multimodal data processing, video classification, and deep learning. The neural network includes: an input subnetwork configured to receive the multimodal data to output respective first features of a plurality of modalities; a plurality of cross-modal feature subnetworks, each of which is configured to receive respective first features of two corresponding modalities to output a cross-modal feature corresponding to the two modalities; a plurality of cross-modal fusion subnetworks, each of which is configured to receive at least one cross-modal feature corresponding to a corresponding target modality and other modalities to output a second feature of the target modality; and an output subnetwork configured to receive respective second features of the plurality of modalities to output a processing result of the multimodal data.
-
公开(公告)号：US20230004721A1
公开(公告)日：2023-01-05
申请号：US17655770
申请日：2022-03-21
Inventor： Shuai Zhang , Lijie Wang , Xinyan Xiao , Yue Chang
IPC: G06F40/30 , G06F40/211 , G06F40/284
Abstract: Disclosed are a method for training a semantic representation model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the field of artificial intelligence, such as a natural language processing technology, a deep learning technology, or the like. The method for training a semantic representation model includes: obtaining an anchor sample based on a sentence, and obtaining a positive sample and a negative sample based on syntactic information of the sentence; processing the anchor sample, the positive sample and the negative sample using the semantic representation model respectively, so as to obtain an anchor-sample semantic representation, a positive-sample semantic representation and a negative-sample semantic representation; constructing a contrast loss function based on the anchor-sample semantic representation, the positive-sample semantic representation, and the negative-sample semantic representation; and training the semantic representation model based on the contrast loss function.
-
-
-
-
-
-
-
-
-
Search Results
1470
records
(took 0.049 seconds)
