-
公开(公告)号：US20220180569A1
公开(公告)日：2022-06-09
申请号：US17542002
申请日：2021-12-03
Inventor： Joo-Young LEE , Se-Yoon JEONG , Hyoung-Jin KWON , Dong-Hyun KIM , Youn-Hee KIM , Jong-Ho KIM , Ji-Hoon DO , Jin-Soo CHOI , Tae-Jin LEE
IPC: G06T9/00
Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a binary mask. An encoding method includes generating a latent vector using an input image, generating a selected latent vector component set using a binary mask, and generating a main bitstream by performing entropy encoding on the selected latent vector component set. A decoding method includes generating a selected latent vector component set including one or more selected latent vector components by performing entropy decoding on a main bitstream and generating the latent vector in which the one or more selected latent vector components are relocated by relocating the selected latent vector component set in the latent vector.
-
12.发明申请公开(公告)号：US20170194002A1
公开(公告)日：2017-07-06
申请号：US15193216
申请日：2016-06-27
Inventor： Dong-Hyun KIM
IPC: G10L15/30 , G10L15/07 , G10L15/16 , G10L15/02 , G10L15/183
CPC classification number: G10L15/30 , G10L15/02 , G10L15/183
Abstract: A voice recognition terminal, a voice recognition server, and a voice recognition method for performing personalized voice recognition. The voice recognition terminal includes a feature extraction unit for extracting feature data from an input voice signal, an acoustic score calculation unit for calculating acoustic model scores using the feature data, and a communication unit for transmitting the acoustic model scores and state information to a voice recognition server in units of one or more frames, and receiving transcription data from the voice recognition server, wherein the transcription data is recognized using a calculated path of a language network when the voice recognition server calculates the path of the language network using the acoustic model scores.
-
公开(公告)号：US20240372982A1
公开(公告)日：2024-11-07
申请号：US18292869
申请日：2022-07-26
Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE , HANBAT NATIONAL UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION
Inventor： Woong LIM , Hyoung-Jin KWON , Dong-Hyun KIM , Youn-Hee KIM , Jong-Ho KIM , Ji-Hoon DO , Joo-Young LEE , Se-Yoon JEONG , Jin-Soo CHOI , Tae-Jin LEE , Hae-Chul CHOI , Dae-Hyeok GWON , Hee-Ji HAN
IPC: H04N19/105 , H04N19/176 , H04N19/88
Abstract: Disclosed therein are a method, an apparatus, and a storage medium for image encoding/decoding. Templating matching is used for prediction for a target block. Prediction information to be applied to encoding of the target block is determined, and prediction for the target block that uses the determined prediction information is performed. The prediction information includes a list and multiple candidates in the list. When the multiple candidates in the list are configured, template matching between blocks may be used. A candidate selected from among multiple candidates configured using template matching is used for prediction for the target block.
-
公开(公告)号：US20240232582A1
公开(公告)日：2024-07-11
申请号：US18491172
申请日：2023-10-20
Inventor： Dong-Hyun KIM , Nam-Hyeong KIM , Sang-Hun KIM , Yo-Han LIM
IPC: G06N3/0455 , H04L9/00
CPC classification number: G06N3/0455 , H04L9/008
Abstract: Disclosed herein are an apparatus and method for a secure online deep-learning model service. A client apparatus for the secure online deep-learning model service includes memory in which a secure input network and a secure output network generated in advance based on a deep-learning model provided from a server and at least one program are recorded and a processor for executing the program. The program may perform generating an input vector by passing user data through the secure input network, transmitting the input vector to the server, receiving an output vector acquired by passing the input vector through the hidden network of the deep-learning model from the server, and generating output data by passing the received output vector through the secure output network.
-
Patent Agency Ranking
15.发明申请公开(公告)号：US20230052774A1
公开(公告)日：2023-02-16
申请号：US17782568
申请日：2020-12-07
Inventor： Youn-Hee KIM , Seung-Hyun CHO , Hyunsuk KO , Hyoung-Jin KWON , Dong-Hyun KIM , Jong-Ho KIM , Joo-Young LEE , Se-Yoon JEONG , Tae-Jin LEE , Jin-Soo CHOI
IPC: H04N19/30 , H04N19/119 , H04N19/17 , H04N19/147 , H04N19/14 , H04N19/42
Abstract: Disclosed herein are a video-decoding method and apparatus and a video encoding method and apparatus, and more particularly a method and an apparatus which perform region-differential image encoding/decoding using a recovered image. In accordance with an encoding method according to an embodiment, a recovered low-quality image is generated by performing encoding on an original image and a recovered high-quality image is generated using the recovered low-quality image. An image is segmented into multiple regions, and encoded reconstruction information for generating a reconstructed high-quality image is generated by performing encoding on the image.
-
16.发明申请公开(公告)号：US20230044217A1
公开(公告)日：2023-02-09
申请号：US17517211
申请日：2021-11-02
Inventor： Dong-Hyun KIM , Sang-Hun KIM
IPC: G06F3/0488 , G06F3/16 , G10L15/22 , G10L15/26
Abstract: Disclosed herein are a text input apparatus for improving speech recognition performance and a method using the same. The text input method may include arranging all characters on an input screen including multiple key input areas in consideration of usage frequency of respective characters and usage association between the characters, setting input schemes for all the characters in consideration of positions of the multiple key input areas and positions of characters arranged in each key input area, and inputting characters through touch-based input corresponding to the input schemes.
-
公开(公告)号：US20220201295A1
公开(公告)日：2022-06-23
申请号：US17557819
申请日：2021-12-21
Inventor： Youn-Hee KIM , Dong-Hyun KIM , Ji-Hoon DO , Se-Yoon JEONG , Hyoung-Jin KWON , Jong-Ho KIM , Joo-Young LEE , Jin-Soo CHOI , Tae-Jin LEE
IPC: H04N19/119 , H04N19/14 , H04N19/105 , H04N19/176 , G06N3/04
Abstract: Disclosed herein are a method, an apparatus, and a storage medium for image encoding/decoding using prediction. Multiple candidate prediction images are derived, and a final prediction image is generated using the multiple prediction images. The multiple candidate prediction images may be respectively generated using different methods. The multiple candidate prediction images may be generated using neural networks. Here, the multiple candidate prediction images may be respectively derived using different values for a specific coding parameter. Multiple neural networks may use different values for the specific coding parameter. Various coding parameters related to image encoding and/or decoding may be used for embodiments.
-
公开(公告)号：US20220094977A1
公开(公告)日：2022-03-24
申请号：US17479811
申请日：2021-09-20
Inventor： Dong-Hyun KIM , Ji-Hoon DO , Youn-Hee KIM , Se-Yoon JEONG , Hyoung-Jin KWON , Jong-Ho KIM , Joo-Young LEE , Jin-Soo CHOI , Tae-Jin LEE
IPC: H04N19/593 , H04N19/11 , H04N19/176 , H04N19/436 , H04N19/136 , H04N19/184 , G06N3/04
Abstract: Disclosed herein are a method, an apparatus, and a storage medium for image encoding/decoding. An intra-prediction mode for the target block is derived, and intra-prediction for the target block that uses the derived intra-prediction mode is performed. The intra-prediction mode for the target block is derived using an artificial neural network, and an MPM list for the target block is derived using information about the target block, pieces of information about blocks adjacent to the target block, and the artificial neural network. The artificial neural network outputs one or more available intra-prediction modes. Further, the artificial neural network outputs match probabilities for one or more candidate intra-prediction modes, and each of the match probabilities for the candidate intra-prediction modes indicates a probability that the corresponding candidate intra-prediction mode matches the intra-prediction mode for the target block.
-
公开(公告)号：US20240406436A1
公开(公告)日：2024-12-05
申请号：US18697343
申请日：2022-09-29
Inventor： Dong-Hyun KIM , Se-Yoon JEONG , Hyoung-Jin KWON , Youn-Hee KIM , Jong-Ho KIM , Ji-Hoon DO , Joo-Young LEE , Woong LIM , Jin-Soo CHOI , Tae-Jin LEE
IPC: H04N19/52 , H04N19/109 , H04N19/139 , H04N19/176 , H04N19/573
Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding. In typical image encoding/decoding methods, a decoder-side motion information derivation method may be limitedly used. Therefore, the improvement of encoding efficiency attributable to the decoder-side motion information derivation method may also be limited. In embodiments, a motion information search method used in inter-prediction is disclosed. With the use of various motion search methods, encoding efficiency in inter-prediction may be improved.
-
-
-
-
-
-
-
-
Search Results
19
records
(took 0.02 seconds)
