公开(公告)号：US20220392205A1

公开(公告)日：2022-12-08

申请号：US17892669

申请日：2022-08-22

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Yipeng SUN ,  Rongqiao AN ,  Xiang WEI ,  Longchao WANG ,  Kun YAO ,  Junyu HAN ,  Jingtuo LIU ,  Errui DING

IPC: G06V10/80 ,  G06V10/77

Abstract: Embodiments of the present disclosure provide a method and apparatus for training an image recognition model based on a semantic enhancement, a method and apparatus for recognizing an image, an electronic device, and a computer readable storage medium. The method for training an image recognition model based on a semantic enhancement comprises: extracting, from an inputted first image being unannotated and having no textual description, a first feature representation of the first image; calculating a first loss function based on the first feature representation; extracting, from an inputted second image being unannotated and having an original textual description, a second feature representation of the second image; calculating a second loss function based on the second feature representation, and training an image recognition model based on a fusion of the first loss function and the second loss function.

公开(公告)号：US20230386168A1

公开(公告)日：2023-11-30

申请号：US18192393

申请日：2023-03-29

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Yipeng SUN ,  Mengjun CHENG ,  Longchao WANG ,  Xiongwei ZHU ,  Kun YAO ,  Junyu HAN ,  Jingtuo LIU ,  Errui DING ,  Jingdong WANG ,  Haifeng Wang

IPC: G06V10/42 ,  G06F16/583 ,  H04N19/176

CPC classification number: G06V10/42 ,  G06F16/5846 ,  H04N19/176

Abstract: A pre-training method for a Vision and Scene Text Aggregation model includes: acquiring a sample image-text pair; extracting a sample scene text from a sample image; inputting a sample text into a text encoding network to obtain a sample text feature; inputting the sample image and an initial sample aggregation feature into a visual encoding subnetwork and inputting the initial sample aggregation feature and the sample scene text into a scene encoding subnetwork to obtain a global image feature of the sample image and a learned sample aggregation feature; and pre-training the Vision and Scene Text Aggregation model according to the sample text feature, the global image feature of the sample image, and the learned sample aggregation feature.

公开(公告)号：US20230124389A1

公开(公告)日：2023-04-20

申请号：US17887690

申请日：2022-08-15

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Longchao WANG ,  Yipeng SUN ,  Kun YAO ,  Junyu HAN ,  Jingtuo LIU ,  Errui DING

IPC: G06V10/70 ,  G06V10/774

Abstract: A model determination method and electronic device is provided, and relates to the technical field of artificial intelligence and, in particular, to the field of computer visions and deep learning, and can be applied to image processing, image identification and other scenarios. A specific implementation solution includes an image sample and a text sample are acquired, wherein text data in the text sample is used for performing text description to target image data in the image sample; at least one image feature in the image sample is stored to a first queue, and at least text feature in the text sample is stored to a second queue; the first queue and the second queue are trained to obtain a first target model; and the first target model is determined as an initialization model for a second target model.

公开(公告)号：US20220292131A1

公开(公告)日：2022-09-15

申请号：US17826760

申请日：2022-05-27

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Ruibin BAI ,  Xiang WEI ,  Yipeng SUN ,  Kun YAO ,  Jingtuo LIU ,  Junyu HAN

IPC: G06F16/583 ,  G06V10/74 ,  G06V10/44 ,  G06F16/535

Abstract: A method, apparatus and system for retrieving an image is provided, the method comprises: detecting, in response to receiving a query request comprising a target image, a target subject from the target image; extracting a subject feature from the target subject if a confidence level of a detection box of the detected target subject is greater than a first threshold, the subject feature comprising an identical feature, a similar feature and a category; performing matching on the subject feature of the target image and a subject feature of a candidate image pre-stored in a database, to obtain a similarity score and an identicalness score of the candidate image; and selecting, according to the similarity score and the identicalness score, a predetermined number of candidate images as a search result for output.

公开(公告)号：US20210192725A1

公开(公告)日：2021-06-24

申请号：US17021114

申请日：2020-09-15

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Zhizhi GUO ,  Yipeng SUN ,  Jingtuo LIU ,  Junyu HAN ,  Duo YANG ,  Yue DANG ,  Huichao WANG

IPC: G06T7/00

Abstract: The present disclosure discloses a method, apparatus and electronic device for determining skin smoothness, which relates to the field of computer vision technologies. The specific implementation solution is as follows: when the skin smoothness is calculated, an image to be detected including a face area is obtained first, and then the image to be detected and a smoothness analysis mask image corresponding to the image to be detected are inputted into a deep learning model to obtain a plurality of feature vectors for indicating the skin smoothness of the face. Because the smoothness analysis mask image does not include preset factors including at least one of five sense organs, reflection and hair, the influence of the preset factors on the skin smoothness is avoided, so that the accuracy for the skin smoothness of the face is ensured to a certain extent.