Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

China Mobile Communications Corporation

Kun Yao

Hao Sun

Junyu Han

Jingtuo Liu

Errui Ding

Haifeng Wang

Zhibin Hong

Chengquan Zhang

Jingdong Wang

Yipeng Sun

Pengyuan Lv

Yi Liu

Jing Yang

Tingting Zhao

Tian Wu

Xiaoyan Wang

Shanshan Liu

Xiameng Qin

Tianshu Hu

Ju Huang

Yuanzhang Chang

Mengyi En

Qunyi Xie

Xiongwei Zhu

Liang Wu

Hanqi Guo

Shengxian Zhu

Xiangda Yan

Zihan Ni

Meina Qiao

Yangliu Xu

Longchao Wang

Mengjun Cheng

Jieting Xue

Jiakang Shi

Xusheng Zeng

Shihu Li

Ruixue Liu

The present disclosure provides a character recognition model training method and apparatus, a character recognition method and apparatus, a device and a medium, relating to the technical field of artificial intelligence, and specifically to the technical fields of deep learning, image processing and computer vision, which can be applied to scenarios such as character detection and recognition technology. The specific implementing solution is: partitioning an untagged training sample into at least two sub-sample images; dividing the at least two sub-sample images into a first training set and a second training set; where the first training set includes a first sub-sample image with a visible attribute, and the second training set includes a second sub-sample image with an invisible attribute; performing self-supervised training on a to-be-trained encoder by taking the second training set as a tag of the first training set, to obtain a target encoder.

Character recognition model training method and apparatus, character recognition method and apparatus, device and storage medium

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.

Pre-training method, image and text retrieval method for a vision and scene text aggregation model, electronic device, and storage medium

The disclosure provides a method and a device for processing information, an electronic device, and a storage medium, belonging to a field of artificial intelligence including computer vision, deep learning, and natural language processing. In the method, the computing device recognizes multiple text items in the image. The computing device classifies multiple text items into a first set of name text items and a second set of content text items based on semantics of the text items. The computing device performs a matching operation between the first set and the second set based on a layout of the text items in the image, and determines matched name-content text items. The matched name-content text items include a name text item in the first set and a content text item matching the name text item and in the second set. The computing device outputs the matched name-content text items.

Method and device for processing information, electronic device, and storage medium

A method and apparatus for processing an image, a device and a storage medium are provided. An implementation of the method includes: acquiring a template image, the template image including at least one region of interest; determining a first feature map corresponding to each region of interest in the template image; acquiring a target image; determining a second feature map of the target image; and determining at least one region of interest in the target image according to the first feature map and the second feature map.

Method and apparatus for processing image, device and storage medium

A text recognition method includes: acquiring an image including text information, the text information including M characters, M being a positive integer greater than 1; performing text recognition on the image to acquire character information about the M characters; recognizing reading direction information about each character in accordance with the character information about the M characters, the reading direction information being used to indicate a next character corresponding to a current character in a semantic reading order; and ranking the M characters in accordance with the reading direction information about the M characters to acquire a text recognition result of the text information.

Text recognition method and device, and electronic device

Embodiments of the present disclosure provide a method for training a face fusion model and an electronic device. The method includes: performing a first face changing process on a user image and a template image to generate a reference template image; adjusting poses of facial features of the template image based on the reference template image to generate a first input image; performing a second face changing process on the template image to generate a second input image; inputting the first input image and the second input image into a generator of an initial face fusion model to generate a fused face area image; and inputting the fused image and the template image into a discriminator of the initial face fusion model to obtain a result, and performing backpropagation correction on the initial face fusion model based on the result to generate a face fusion model.

Method and apparatus for training face fusion model and electronic device

The present disclosure provides a video blending method, apparatus, electronic device and readable storage medium, and relates to computer vision technologies. A specific implementation solution is as follows: obtaining a predicted 3D face mesh of a facial image in each video frame images of the user video according to each video frame image of a user video and each video frame image of a template video; obtaining a predicted texture of the predicted 3D face mesh according to a user texture of a user 3D face mesh of the facial image in each video frame image of the user video and a template texture of a template 3D face mesh of the facial image in each video frame image of the template video; obtaining a rendered facial image of the predicted 3D face mesh according to the predicted 3D face mesh, the predicted texture and user face posture, and template face posture; performing blending processing for the rendered facial image and each video frame image of the template video to obtain a blended video frame image after the blending; performing synthesis processing for the blended video frame image to obtain a blended video.

Video blending method, apparatus, electronic device and readable storage medium

A method, an electronic device and a storage medium for expression driving are disclosed. The method may include: performing facial key point detection on a driven character in a first image to obtain a first facial key point sequence; performing the following processing for each second image of a plurality of second images obtained successively: performing facial key point detection on a driving character in the second image to obtain a second facial key point sequence; obtaining a difference between the second facial key point sequence and an expressionless key point sequence which has been determined previously according to an analysis on the second facial key point sequence for a previous second image, and performing expression drive rendering on the driven character based on the difference and the first facial key point sequence. The technical solution may enhance flexibility, interactivity, accuracy etc.

Method, apparatus, electronic device and storage medium for expression driving

A traffic control method, a network side device and a terminal are provided. The traffic control method includes steps of: determining a matching relationship between vehicles and roads in accordance with vehicle data of all vehicles on the roads forming an intersection, and sending traffic control signals to the vehicles meeting a certain condition in accordance with the matching relationship between the vehicles and the roads. With such technical solution, it is able to control the vehicles moving toward the intersection without any traffic light control system, thereby reducing the risk of traffic accidents there.

Traffic control method, network side device and terminal

Growing community of inventors

Beijing, China

Kun Yao