Jing Xia Liu

20220375024, Nov 24, 2022

May 14, 2021

17/321384

- Grand Cayman, KY
Guoxian SONG - Singapore, SG
Jing LIU - Los Angeles CA, US
Wanchun MA - Los Angeles CA, US

G06T 3/00
G06T 11/00
G06T 5/00
G06K 9/62
G06N 3/04
G06N 3/08

Systems and method directed to an inversion-consistent transfer learning framework for generating portrait stylization using only limited exemplars. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be provided to a generative adversarial network (GAN) generator to generate a stylized image. In examples, the variational autoencoder is trained using a plurality of images while keeping the weights of a pre-trained GAN generator fixed, where the pre-trained GAN generator acts as a decoder for the encoder. In other examples, a multi-path attribute aware generator is trained using a plurality of exemplar images and learning transfer using the pre-trained GAN generator.

20230061012, Mar 2, 2023

Nov 8, 2022

18/053476

- Beijing, CN
- Los Angeles CA, US
Xuchen SONG - Los Angeles CA, US
Jianchao YANG - Los Angeles CA, US
Guohui WANG - Los Angeles CA, US
Zhili CHEN - Los Angeles CA, US
Linjie LUO - Los Angeles CA, US
Xiao YANG - Los Angeles CA, US
Haoze LI - Los Angeles CA, US
Jing LIU - Los Angeles CA, US

G06T 19/00
G06T 19/20
G06V 40/16
G06V 40/20
G10L 15/02
G10L 25/63

An image processing method and apparatus for augmented reality, an electronic device and a storage medium, including: acquiring a target image in response to an image acquiring instruction triggered by a user, where the target image includes a target object; acquiring an augmented reality model of the target object, and outputting the augmented reality model in combination with the target object; acquiring target audio data selected by the user, and determining an audio feature with temporal regularity according to the target audio data; and driving the augmented reality model according to the audio feature and a playing progress of the target audio data when outputting the target audio data.

20230030740, Feb 2, 2023

Nov 22, 2021

17/532480

- Grand Cayman, KY
Peibin CHEN - Beijing, CN
Weihong ZENG - Beijing, CN
Xu WANG - Beijing, CN
Shen SANG - Los Angeles CA, US
Jing LIU - Los Angeles CA, US
Chunpong LAI - Los Angeles CA, US

G06K 9/62

The present disclosure relates to an image annotating method, classification method and machine learning model training method, and to the field of computer technologies. The image annotating method includes: generating an image tag vector of image to be annotated, according to a plurality of attributes for image annotating and multiple tags corresponding to each of the attributes; annotating an image category to which the image to be annotated belongs, according to vector similarity between the image tag vector and an category tag vector of each of a plurality of image categories, the category tag vector being generated according to the multiple tags corresponding to each of the attributes.

20230033303, Feb 2, 2023

Nov 17, 2021

17/529192

- Grand Cayman, KY
Peibin CHEN - Beijing, CN
Weihong ZENG - Beijing, CN
Xu WANG - Beijing, CN
Jing LIU - Los Angeles CA, US
Chunpong LAI - Los Angeles CA, US
Shen SANG - Los Angeles CA, US

G06K 9/00
G06K 9/62

A method is provided for evaluating an effect of classifying a fuzzy attribute of an object, the fuzzy attribute referring to an attribute, a boundary between two similar ones of a plurality of categories of which is blurred, wherein the method includes: generating a similarity-based ranked confusion matrix, which comprises: based on similarities of K categories of the fuzzy attribute of the object, ranking the K categories, where K is an integer greater than or equal to 2, generating a K×K all-zero initialization matrix, wherein an abscissa and an ordinate of the initialization matrix respectively represent predicted values and true values of the similarity-based ranked categories of the fuzzy attribute, and based on the true values and the predicted values of the category of the fuzzy attribute for the multiple object samples, updating values of corresponding elements in the initialization matrix; and displaying the similarity-based ranked confusion matrix.

20230034370, Feb 2, 2023

Nov 22, 2021

17/532537

- Grand Cayman, KY
Weihong ZENG - Beijing, CN
Peibin CHEN - Beijing, CN
Xu WANG - Beijing, CN
Chunpong LAI - Los Angeles CA, US
Shen SANG - Los Angeles CA, US
Jing LIU - Los Angeles CA, US

G06K 9/62
G06K 9/00
G06F 16/532

An image processing method includes acquiring a set of image samples for training an attribute recognition model, wherein the set of image samples includes a first subset of image samples with category labels and a second subset of image samples without category labels; training a sample prediction model using the first subset of image samples, and predicting categories of the image samples in the second subset of image samples using the trained sample prediction model; determining a category distribution of the set of image samples based on the category labels of the first subset of image samples and the predicted categories of the second subset of image samples; and acquiring a new image sample if the determined category distribution does not conform to the expected category distribution, and adding the acquired new image sample to the set of image samples.

20230035131, Feb 2, 2023

Nov 24, 2021

17/534681

- Grand Cayman, KY
Peibin CHEN - Beijing, CN
Weihong ZENG - Beijing, CN
Xu WANG - Beijing, CN
Jing LIU - Los Angeles CA, US
Chunpong LAI - Los Angeles CA, US
Shen SANG - Los Angeles CA, US

G06V 10/764
G06V 10/82
G06V 10/72
G06N 3/08

The present disclosure provides a training method and device for an image identifying model, and an image identifying method. The training method comprises: obtaining image samples of a plurality of categories; inputting image samples of each category into a feature extraction layer of the image identifying model to extract a feature vector of each image sample; calculating a statistical characteristic information of an actual distribution function corresponding to each category according to the feature vector of each image sample of the each category; establishing an augmented distribution function corresponding to the each category according to the statistical characteristic information; obtaining augmented sample features of the each category based on the augmented distribution function; and inputting feature vectors of the image samples and the augmented sample features into a classification layer of the image identifying model for supervised learning.

20230035995, Feb 2, 2023

Nov 23, 2021

17/534222

- Grand Cayman, KY
Weihong ZENG - Beijing, CN
Peibin CHEN - Beijing, CN
Xu WANG - Beijing, CN
Shen SANG - Los Angeles CA, US
Jing LIU - Los Angeles CA, US
Chunpong LAI - Los Angeles CA, US

G06N 3/08

The present disclosure relates to method, apparatus and storage medium for object attribute classification model training. There proposes a method of training a model for object attribute classification, comprising steps of: acquiring binary class attribute data related to a to-be-classified attribute on which an attribute classification task is to be performed, wherein the binary class attribute data includes data indicating whether the to-be-classified attribute is “Yes” or “No” for each of at least one class label; and pre-training the model for object attribute classification based on the binary class attribute data.

20230036366, Feb 2, 2023

Nov 30, 2021

17/538938

- Grand Cayman, KY
Weihong ZENG - Beijing, CN
Peibin CHEN - Beijing, CN
Xu WANG - Beijing, CN
Shen SANG - Los Angeles CA, US
Jing LIU - Los Angeles CA, US
Chunpong LAI - Los Angeles CA, US

G06V 40/16
G06V 10/82
G06N 3/04

The present disclosure relates to an image attribute classification method, apparatus, electronic device, medium, and program product. The present disclosure enables inputting the image to a feature extraction network to obtain a feature map after feature extraction and N times down-sampling, wherein at least one attribute of the image occupies a second rectangular position area in the feature map after N times down-sampling; calculating a mask function of the at least one attribute of the feature map after N times down-sampling based on the second rectangular position area; obtaining a feature corresponding to the at least one attribute by dot multiplying the feature map after N times down-sampling with the mask function; and inputting the obtained feature corresponding to the at least one attribute to the corresponding attribute classifier for attribute classification.