公开(公告)号：US20240383679A1

公开(公告)日：2024-11-21

申请号：US18391759

申请日：2023-12-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Young Wook Kim ,  Seung Gyu Kang ,  Hyun Jae Kang ,  Sang Min Kim ,  Jae Sung Byun ,  Yong-Jun Ahn ,  Hyun Woo Lee ,  Jeong Hun Lim ,  Jun Hyuk Chang

IPC: B65G1/04 ,  B61B3/02

Abstract: A ceiling storage system includes a first support rail and a second support rail that extend in a first direction; a first driving rail that extends in the first direction and is parallel to the first support rail and the second support rail; a second driving rail movably coupled to the first support rail, the second support rail, and the first driving rail, where the second driving rail is configured to move along the first support rail, the second support rail, and the first driving rail; a transfer vehicle movably coupled to the second driving rail and configured to move along the second driving rail; and a connection device that connects the first driving rail and the second driving rail to each other, where the connection device and the second driving rail are rotatable around a first axis that is parallel to the first direction.

公开(公告)号：US20240354997A1

公开(公告)日：2024-10-24

申请号：US18430369

申请日：2024-02-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Dimitar Petkov Dinev ,  Siddarth Ravichandran ,  Hyun Jae Kang ,  Ondrej Texler ,  Anthony Sylvain Jean-Yves Liot ,  Sajid Sadi

IPC: G06T9/00 ,  G06T3/40 ,  G06T11/00 ,  G06V10/771

CPC classification number: G06T9/00 ,  G06T3/40 ,  G06T11/00 ,  G06V10/771

Abstract: Generating images includes generating encoded data by encoding input data into a latent space. The encoded data is decoded through a first decoder having first decoder layers by processing the encoded data through one or more of the first decoder layers. The encoded data is decoded through a second decoder having second decoder layers by processing the encoded data through one or more of the second decoder layers. An updated feature map is generated by replacing at least a portion of a feature map output from a selected layer of the first decoder layers with at least a portion of a feature map output from a selected layer of the second decoder layers. An image is generated by further decoding the updated feature map through one or more additional layers of the first decoder layers.

公开(公告)号：US20240013464A1

公开(公告)日：2024-01-11

申请号：US18296202

申请日：2023-04-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Siddarth Ravichandran ,  Dimitar Petkov Dinev ,  Ondrej Texler ,  Ankur Gupta ,  Janvi Chetan Palan ,  Hyun Jae Kang ,  Anthony Sylvain Jean-Yves Liot ,  Sajid Sadi

IPC: G06T13/40 ,  G06T13/20 ,  G06T5/50 ,  G06T7/13 ,  G06T7/73 ,  G06V10/74

CPC classification number: G06T13/40 ,  G06T13/205 ,  G06T5/50 ,  G06T7/13 ,  G06T7/73 ,  G06V10/761 ,  G06T2207/20081 ,  G06T2207/20221 ,  G06T2207/30201

Abstract: Multimodal disentanglement can include generating a set of silhouette images corresponding to a human face, the generating undoing a correlation between an upper portion and a lower portion of the human face depicted by each silhouette image. A unimodal machine learning model can be trained with the set of silhouette images. As trained, the unimodal machine learning model can generate synthetic images of the human face. The synthetic images generated by the unimodal machine learning model once trained can be used to train a multimodal rendering network. The multimodal rendering network can be trained to generate a voice-animated digital human. Training the multimodal rendering network can be based on minimizing differences between the synthetic images and images generated by the multimodal rendering network.

公开(公告)号：US10909371B2

公开(公告)日：2021-02-02

申请号：US15841157

申请日：2017-12-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Stanislaw Antol ,  Abhijit Bendale ,  Simon J. Gibbs ,  Won J. Jeon ,  Hyun Jae Kang ,  Jihee Kim ,  Bo Li ,  Anthony S. Liot ,  Lu Luo ,  Pranav K. Mistry ,  Zhihan Ying

IPC: G06K9/00 ,  G06N20/00 ,  G06F11/30 ,  G06F11/34 ,  G06K9/32 ,  G06K9/62 ,  G06K9/66 ,  G06N3/08 ,  G06N5/02 ,  G06T11/00 ,  G06T19/00 ,  H04L29/08 ,  H04L29/06 ,  G06F3/14

Abstract: A method includes retrieving, by a device, contextual information based on at least one of an image, the device, user context, or a combination thereof. At least one model is identified from multiple models based on the contextual information and at least one object recognized in an image based on at least one model. At least one icon is displayed at the device. The at least one icon being associated with at least one of an application, a service, or a combination thereof providing additional information.

公开(公告)号：US20180204061A1

公开(公告)日：2018-07-19

申请号：US15875393

申请日：2018-01-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Stanislaw Antol ,  Abhijit Bendale ,  Simon J. Gibbs ,  Won J. Jeon ,  Hyun Jae Kang ,  Jihee Kim ,  Bo Li ,  Anthony S. Liot ,  Lu Luo ,  Pranav K. Mistry ,  Zhihan Ying

IPC: G06K9/00 ,  G06K9/66 ,  G06K9/62 ,  G06F11/34 ,  G06K9/32

Abstract: One embodiment provides a method comprising classifying one or more objects present in an input comprising visual data by executing a first set of models associated with a domain on the input. Each model corresponds to an object category. Each model is trained to generate a visual classifier result relating to a corresponding object category in the input with an associated confidence value indicative of accuracy of the visual classifier result. The method further comprises aggregating a first set of visual classifier results based on confidence value associated with each visual classifier result of each model of the first set of models. At least one other model is selectable for execution on the input based on the aggregated first set of visual classifier results for additional classification of the objects. One or more visual classifier results are returned to an application running on an electronic device for display.

公开(公告)号：US20240221260A1

公开(公告)日：2024-07-04

申请号：US18342721

申请日：2023-06-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Dimitar Petkov Dinev ,  Ondrej Texler ,  Siddarth Ravichandran ,  Janvi Chetan Palan ,  Hyun Jae Kang ,  Ankur Gupta ,  Anil Unnikrishnan ,  Anthony Sylvain Jean-Yves Liot ,  Sajid Sadi

IPC: G06T13/40 ,  G06T13/20 ,  G06T19/20 ,  G06V40/16 ,  G06V40/20

CPC classification number: G06T13/40 ,  G06T13/205 ,  G06T19/20 ,  G06V40/174 ,  G06V40/20 ,  G06T2219/2004

Abstract: Synthesizing speech and movement of a virtual human includes capturing supplemental data generated by a transducer. The supplemental data specifies one or more attributes of a user. The capturing is performed in substantially real-time with the user providing input to a conversational platform. A behavior determiner generates behavioral data based on the supplemental data and an audio response generated by the conversational platform in response to the input to the conversation platform. Based on the behavioral data and the audio response, a rendering network generates a video rendering of a virtual human engaging in a conversation with the user, the video rendering synchronized with the audio response.

公开(公告)号：US20230406623A1

公开(公告)日：2023-12-21

申请号：US18163588

申请日：2023-02-02

Applicant: Samsung Electronics Co., Ltd.

Inventor： Young Wook Kim ,  Seung Gyu Kang ,  Hyun Jae Kang ,  Sang Min Kim ,  Yong-Jun Ahn ,  Sang Kyung Lee ,  Hyun Woo Lee ,  Jeong Hun Lim ,  Jun Hyuk Chang

IPC: B65G1/04 ,  B65G47/90

CPC classification number: B65G1/0457 ,  B65G1/0464 ,  B65G47/905 ,  B65G49/07

Abstract: Provided is a ceiling storage system for increasing storage capacity by utilizing a ceiling space inside a fab. The ceiling storage system includes a first overhead rack including a plurality of storage positions for storing a plurality of articles; first and second support rails above the first overhead rack and extending in one direction; a first driving rail above the first overhead rack and in parallel with the first and second support rails; a second driving rail coupled to the first and second support rails and the first driving rail and moving along the first and second support rails and the first driving rail; and a first transport vehicle including a carriage coupled to the second driving rail and moving along the second driving rail, and a hoist and a hand unit installed on the carriage and for loading and unloading the articles to and from the first overhead rack.

公开(公告)号：US20230394732A1

公开(公告)日：2023-12-07

申请号：US17967872

申请日：2022-10-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Siddarth Ravichandran ,  Anthony Sylvain Jean-Yves Liot ,  Dimitar Petkov Dinev ,  Ondrej Texler ,  Hyun Jae Kang ,  Janvi Chetan Palan ,  Sajid Sadi

IPC: G06T13/40 ,  G06T17/20 ,  G06T7/70 ,  G10L15/25

CPC classification number: G06T13/40 ,  G06T17/20 ,  G06T7/70 ,  G10L15/25 ,  G06T2207/30201

Abstract: Creating images and animations of lip motion from mouth shape data includes providing, as one or more input features to a neural network model, a vector of a plurality of coefficients. Each vector of the plurality of coefficients corresponds to a different mouth shape. Using the neural network model, a data structure output specifying a visual representation of a mouth including lips having a shape corresponding to the vector is generated.

公开(公告)号：US20230394715A1

公开(公告)日：2023-12-07

申请号：US17967868

申请日：2022-10-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ondrej Texler ,  Dimitar Petkov Dinev ,  Ankur Gupta ,  Hyun Jae Kang ,  Anthony Sylvain Jean-Yves Liot ,  Siddarth Ravichandran ,  Sajid Sadi

IPC: G06T11/00 ,  G06T13/00 ,  G06T7/70

CPC classification number: G06T11/00 ,  G06T13/00 ,  G06T7/70 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: Image generation using a hierarchical, model-based system includes generating a first region of an image using a first neural network model. The first region of the image is provided to a second neural network model as input. A second region of the image is generated using the second neural network model. The second region of the image shares a boundary with at least a portion of the first region of the image.

公开(公告)号：US10553429B2

公开(公告)日：2020-02-04

申请号：US15355360

申请日：2016-11-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Boo Hyun Ham ,  Hyun Jae Kang ,  Sung Sik Park ,  Yong Kug Bae ,  Kwang Sub Yoon ,  Bum Joon Youn ,  Hyun Chang Lee

IPC: H01L21/312 ,  H01L21/033 ,  H01L23/544

Abstract: A method of forming a pattern of a semiconductor device includes forming a mask and a sacrificial layer on a substrate, etching the sacrificial layer in a first area of the substrate to form first units, each having a first width and a first distance from an adjacent unit, etching the sacrificial layer in a second area of the substrate to form second units, each having a second width equal to the first distance and being spaced apart from an adjacent unit by a second distance equal to the first width, forming a spacer conformally covering the first and second units, the spacer having a first thickness and being merged between the second units, removing a portion of the spacer on upper surfaces of the first and second units, and etching the mask in a region from which first and second units have been removed.