公开(公告)号：US20170171121A1

公开(公告)日：2017-06-15

申请号：US15373591

申请日：2016-12-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ran ZHANG ,  Qinghua WU ,  Xiaoyan LOU

IPC: H04L12/58

CPC classification number: H04L51/066 ,  H04L51/04 ,  H04L51/046

Abstract: A device and a method for providing user-customized content are provided. The method, performed by the device, of providing information regarding at least one primary chat window includes: acquiring a plurality of messages included in at least one primary chat window; determining that a specific event has occurred, based on the acquired plurality of messages; generating a secondary chat window for informing a user of the device about the occurred event; and displaying guidance information about the occurred event in the secondary chat window.

公开(公告)号：US20210375273A1

公开(公告)日：2021-12-02

申请号：US17080378

申请日：2020-10-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Federico FANCELLU ,  Akos KADAR ,  Ran ZHANG ,  Afsaneh FAZLY

IPC: G10L15/197 ,  G10L15/16 ,  G06N3/04

Abstract: An utterance in any of various languages is processed to derive a predicted label using a generated grammar. The grammar is suitable for deriving meaning of utterances from several languages (polyglot). The utterance is processed by an encoder using word embeddings. The encoder and a decoder process the utterance using the polyglot grammar to obtain a machine-readable result. The machine-readable result is well-formed based on accounting for re-entrances of intermediate variable references. A machine then takes action on the machine-readable result. Ambiguity is reduced by the decoder by the well-formed machine-readable result. Sparseness of the generated polyglot grammar is reduced by using a two-pass approach including placeholders which are ultimately replaced by edge labels.

公开(公告)号：US20240144652A1

公开(公告)日：2024-05-02

申请号：US18201521

申请日：2023-05-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Bojie MA ,  Mikita DVORNIK ,  Ran ZHANG ,  Konstantinos DERPANIS ,  Afsaneh FAZLY

IPC: G06V10/771 ,  G06V10/774 ,  G06V10/80

CPC classification number: G06V10/771 ,  G06V10/774 ,  G06V10/80

Abstract: The present disclosure provides methods, apparatuses, and computer-readable mediums for performing data augmentation. In some embodiments, a method of performing data augmentation by a device includes obtaining a plurality of images from a dataset. The method further includes computing, for each image of the plurality of images, a corresponding saliency map based on a gradient of a full loss function of that image. The method further includes selecting, from a subset of arrangements of a plurality of possible arrangements, a rearrangement offset that maximizes an overall saliency of a resulting image combining the plurality of images. The method further includes generating, using the rearrangement offset and a plurality of mixing ratios, a new mixed image from the plurality of images and a new mixed label from corresponding labels of the plurality of images. The method further includes augmenting the dataset with the new mixed image and the new mixed label.

公开(公告)号：US20230394079A1

公开(公告)日：2023-12-07

申请号：US18453838

申请日：2023-08-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Haotian ZHANG ,  Allan JEPSON ,  Iqbal Ismail MOHOMED ,  Konstantinos DERPANIS ,  Ran ZHANG ,  Afsaneh FAZLY

IPC: G06F16/535 ,  G06N20/00

CPC classification number: G06F16/535 ,  G06N20/00

Abstract: A method of personalized image retrieval includes obtaining a natural language query including a name; replacing the name in the natural language query with a generic term to provide an anonymized query and named entity information; obtaining a plurality of initial ranking scores and a plurality of attention weights corresponding to a plurality of images using a trained scoring model that inputs the anonymized query and the plurality of images; obtaining a plurality of delta scores corresponding to the plurality of images using a re-scoring model that inputs the plurality of attention weights and the named entity information; and obtaining a plurality of final ranking scores by modifying the plurality of initial ranking scores based on the plurality of delta scores. The trained scoring model performs semantic based searching and the re-scoring model determines a probability that faces detected in the plurality of images correspond to the name.