公开(公告)号：US11755638B2

公开(公告)日：2023-09-12

申请号：US17465408

申请日：2021-09-02

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Haotian Zhang ,  Allan Jepson ,  Iqbal Ismail Mohomed ,  Konstantinos Derpanis ,  Ran Zhang ,  Afsaneh Fazly

IPC: G06F16/00 ,  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.

公开(公告)号：US12153621B2

公开(公告)日：2024-11-26

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

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.

公开(公告)号：US20240169732A1

公开(公告)日：2024-05-23

申请号：US18227560

申请日：2023-07-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Mikita DVORNIK ,  Isma Hadji ,  Ran Zhang ,  Konstantinos Derpanis ,  Richard Wildes ,  Animesh Garg ,  Allan Douglas Jepson

IPC: G06V20/40 ,  G06F16/735 ,  G06F16/783 ,  G06V10/77 ,  G06V10/86 ,  G09B5/06

CPC classification number: G06V20/46 ,  G06F16/735 ,  G06F16/7844 ,  G06V10/7715 ,  G06V10/86 ,  G06V20/48 ,  G09B5/065

Abstract: The present disclosure provides methods, apparatuses, and computer-readable media for step discovery and localization in an instructional video. In some embodiments, the method includes extracting, from the instructional video using a transformer model, a plurality of step slots corresponding to a plurality of procedure steps depicted in the instructional video, matching, using an order-aware sequence-to-sequence alignment model, a plurality of video segments of the instructional video to the plurality of step slots, generating a temporally-ordered plurality of video segments from the plurality of video segments, receiving a user query requesting a procedure step, selecting, from the plurality of video segments of the instructional video, a corresponding video segment corresponding to the requested procedure step, and providing, in response to the user query, the corresponding video segment and the matching textual step description of the corresponding video segment.

公开(公告)号：US11545145B2

公开(公告)日：2023-01-03

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: G10L15/16 ,  G10L15/197 ,  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：US20220269719A1

公开(公告)日：2022-08-25

申请号：US17465408

申请日：2021-09-02

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Haotian ZHANG ,  Allan Jepson ,  Iqbal Ismail Mohomed ,  Konstantinos Derpanis ,  Ran Zhang ,  Afsaneh Fazly

IPC: 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.