-
1.发明公开公开(公告)号：US20240221346A1
公开(公告)日：2024-07-04
申请号：US17800880
申请日：2022-01-29
Inventor： Zhigang WANG , Jian WANG , Hao SUN , Errui DING
IPC: G06V10/44 , G06T9/00 , G06V10/74 , G06V10/762 , G06V10/80
CPC classification number: G06V10/44 , G06T9/00 , G06V10/761 , G06V10/762 , G06V10/806
Abstract: The present disclosure provides a model training method and apparatus, a pedestrian re-identification method and apparatus, and an electronic device, and relates to the field of artificial intelligence, and specifically to computer vision and deep learning technologies, which can be applied to smart city scenarios. A specific implementation solution is: performing, by using a first encoder, feature extraction on a first pedestrian image and a second pedestrian image in a sample dataset, to obtain an image feature of the first pedestrian image and an image feature of the second pedestrian image; fusing the image feature of the first pedestrian image and the image feature of the second pedestrian image, to obtain a fused feature; performing, by using a first decoder, feature decoding on the fused feature, to obtain a third pedestrian image; and determining the third pedestrian image as a negative sample image of the first pedestrian image, and using the first pedestrian image and the negative sample image to train a first preset model to convergence, to obtain a pedestrian re-identification model. The embodiments of the present disclosure can improve the effect of the model in distinguishing between pedestrians with similar appearances but different identities.
-
2.发明公开公开(公告)号：US20230289402A1
公开(公告)日：2023-09-14
申请号：US18055393
申请日：2022-11-14
Inventor： Jian WANG , Xiangbo SU , Qiman WU , Zhigang WANG , Hao SUN , Errui DING , Jingdong WANG , Tian WU , Haifeng WANG
IPC: G06K9/62
CPC classification number: G06K9/62 , G06K9/6288
Abstract: Provided are a joint perception model training method, a joint perception method, a device, and a storage medium. The joint perception model training method includes: acquiring sample images and perception tags of the sample images; acquiring a preset joint perception model, where the joint perception model includes a feature extraction network and a joint perception network; performing feature extraction on the sample images through the feature extraction network to obtain target sample features; performing joint perception through the joint perception network according to the target sample features to obtain perception prediction results; and training the preset joint perception model according to the perception prediction results and the perception tags, where the joint perception includes executing at least two perception tasks.
-
公开(公告)号：US20230052389A1
公开(公告)日：2023-02-16
申请号：US17976662
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: extracting a plurality of first target features and one or more first motion features from an image feature of an image to be detected; fusing each first target feature and some of the first motion features to obtain enhanced first target features; fusing each first motion feature and some of the first target features to obtain enhanced first motion features; processing the enhanced first target features to obtain target information of a plurality of targets including human targets and object targets; processing the enhanced first motion features to obtain motion information of one or more motions, where each motion is associated with one human target and one object target; and matching the plurality of targets with the one or more motions to obtain a human-object interaction detection result.
-
公开(公告)号：US20220351493A1
公开(公告)日：2022-11-03
申请号：US17868630
申请日：2022-07-19
Inventor： Xiangbo SU , Qiman Wu , Shuai KANG , Jian WANG , Hao SUN
Abstract: A method and apparatus for detecting an object. The method includes: inputting a to-be-detected picture into a target detection model, marking at least one region of interest in the picture using the target detection model, and determining an initial confidence that each region of interest contains a preset target object; determining concentration information of an interferent in the picture; and determining, based on the concentration information and the initial confidence corresponding to the region of interest, a target confidence that the region of interest contains the preset target object.
-
公开(公告)号：US20220222941A1
公开(公告)日：2022-07-14
申请号：US17707657
申请日：2022-03-29
Inventor： Desen ZHOU , Jian WANG , Hao SUN
Abstract: A method for recognizing an action includes: obtaining a sequence for key points; extracting first space-time features corresponding to the sequence; obtaining a second space-time feature corresponding to a time granularity by performing feature extraction on the first space-time features based on the time granularity; and obtaining a target recognized action of the sequence based on second space-time features corresponding to time granularities.
-
Patent Agency Ranking
6.发明申请公开(公告)号：US20220139061A1
公开(公告)日：2022-05-05
申请号：US17576198
申请日：2022-01-14
Inventor： Jian WANG , Zipeng LU , Hao SUN , Zhiyong JIN , Errui DING
Abstract: Provided are a training method and apparatus for a human keypoint positioning model, a human keypoint positioning method and apparatus, a device, a medium and a program product. The training method includes determining an initial positioned point of each of keypoints; acquiring N candidate points of each keypoint according to a position of the initial positioned point; extracting a first feature image, and forming N sets of graph structure feature data according to the first feature image and the N candidate points; performing graph convolution on the N sets of graph structure feature data to obtain N sets of offsets; correcting initial positioned points of all the keypoints to obtain N sets of current positioning results; and calculating each set of loss values according to labeled true values of all the keypoints and each set of current positioning results, and performing supervised training on the positioning model.
-
公开(公告)号：US20220392101A1
公开(公告)日：2022-12-08
申请号：US17887740
申请日：2022-08-15
Inventor： Zipeng LU , Jian WANG , Hao SUN , Errui DING
IPC: G06T7/70 , G06T7/62 , G06V10/25 , G06V10/74 , G06V10/774
Abstract: A training method, a method of detecting a target image, an electronic device and a medium, which relate to the field of artificial intelligence technology, and in particular to fields of computer vision and deep learning. The method can include: generating an expanded sample image set for a target scene by using a mask image set and an initial sample image set, wherein the mask image set is acquired by parsing a predetermined image set, a target object in the target scene is interfered by another object or the target object in the target scene is cut off, and an image in the predetermined image set includes the target object in the target scene or the another object; and training, by using the initial sample image set and the expanded sample image set, a detection model for detecting the target object.
-
公开(公告)号：US20230102422A1
公开(公告)日：2023-03-30
申请号：US17807375
申请日：2022-06-16
Inventor： Desen ZHOU , Jian WANG , Hao SUN
Abstract: Provided is an image recognition method. The method includes determining subject decoded features of a to-be-detected image and an original interaction decoded feature of a subject interactive relationship in the to-be-detected image; determining subject decoded features associated with the original interaction decoded feature, and updating the original interaction decoded feature by using the associated subject decoded features so as to obtain a new interaction decoded feature; and according to the subject decoded features of the to-be-detected image and the new interaction decoded feature, determining at least two subjects to which the subject interactive relationship in the to-be-detected belongs.
-
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：US20220172376A1
公开(公告)日：2022-06-02
申请号：US17675979
申请日：2022-02-18
Inventor： Xiangbo SU , Jian WANG , Hao SUN
Abstract: The present disclosure provides a target tracking method, a target tracking device and an electronic apparatus. The target tracking method includes: inputting an ith image and an (i−1)th image in a to-be-detected video stream into a target deep learning model, i being an integer greater than 1; detecting a target in the ith image to obtain a first target detection box, and tracking the target in the (i−1)th image to obtain a tracking heatmap; and determining a target tracking result in accordance with the first target detection box, the tracking heatmap and the (i−1)th image.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.025 seconds)
