公开(公告)号：US20240395061A1

公开(公告)日：2024-11-28

申请号：US18671708

申请日：2024-05-22

Applicant: Lemon Inc. ,  Beijing Zitiao Network Technology Co., Ltd. ,  Institute of Automation Chinese Academy of Sciences

Inventor： Xiaojie JIN ,  Xingjian HE ,  Sihan CHEN ,  Fan MA ,  Zhicheng HUANG ,  Jing LIU ,  Jiashi FENG

IPC: G06V20/70 ,  G06V10/774 ,  G06V10/80 ,  G06V20/40

Abstract: The present disclosure provides a video processing method, apparatus, device, storage medium, and program product. The method includes: acquiring video data; obtaining, based on the video data, a temporal image feature with temporal information; determining, based on the temporal image feature, a target text feature in a set of text features that matches the temporal image feature; and obtaining, based on the target text feature, target text data corresponding to the video data.

公开(公告)号：US20230035995A1

公开(公告)日：2023-02-02

申请号：US17534222

申请日：2021-11-23

Applicant: LEMON INC.

Inventor： Jingna SUN ,  Weihong ZENG ,  Peibin CHEN ,  Xu WANG ,  Shen SANG ,  Jing LIU ,  Chunpong LAI

IPC: G06N3/08

Abstract: 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.

公开(公告)号：US20230034370A1

公开(公告)日：2023-02-02

申请号：US17532537

申请日：2021-11-22

Applicant: LEMON INC.

Inventor： Jingna SUN ,  Weihong ZENG ,  Peibin CHEN ,  Xu WANG ,  Chunpong LAI ,  Shen SANG ,  Jing LIU

IPC: G06K9/62 ,  G06K9/00 ,  G06F16/532

Abstract: 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.