公开(公告)号：US12094044B2

公开(公告)日：2024-09-17

申请号：US17882102

申请日：2022-08-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kapil Sachdeva ,  Neha Agarwal

IPC: G06T13/40 ,  G06T19/00

CPC classification number: G06T13/40 ,  G06T19/006

Abstract: A method and a system for generation of an animation from a static image are provided. The system includes a scene and context analysis module which is configured to analyze the static image to determine a scene category, a plurality of objects, and a plurality of scene attributes. The scene and context analysis module is further configured to identify a user context. The system further includes an object correlator of an animation selection module which is configured to determine correlation among the plurality of objects based on the plurality of scene attributes. Further, a movement area identifier of the animation selection module is configured to analyze a movement area of the plurality of objects based on the correlation, the plurality of scene attributes and the scene category. An object prioritizer of the animation selection module is configured to prioritize at least one of the objects of the plurality of objects.

公开(公告)号：US11687583B2

公开(公告)日：2023-06-27

申请号：US17752515

申请日：2022-05-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ruchika Saxena ,  Kapil Sachdeva ,  Maneesh Jain ,  Arun Kumar Singh

IPC: G06F16/00 ,  G06F16/583 ,  G06F16/538 ,  G06F16/532

CPC classification number: G06F16/5846 ,  G06F16/532 ,  G06F16/538

Abstract: A system for retrieving information from an instructional document, includes a processor configured to: receive a query from a user; compare the query with one or more text sections in the instructional document; obtain, from the one or more text sections, top x text sections relevant to the query using a pre-trained encoder; compare the query with one or more images in the instructional document; obtain, from the images, top y images relevant to the query; generate top y image-text sections based on the top y images; obtain top k sections from the top x text sections and the top y image-text sections; obtain one or more most relevant sections from the top k sections using a domain-specific pre-trained encoder and a sequential classification model; and generate an answer based on the one or more most relevant sections and device context information using the domain-specific pre-trained encoder.