公开(公告)号：US12019679B2

公开(公告)日：2024-06-25

申请号：US17891486

申请日：2022-08-19

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jong Hee Kim ,  Hyung Il Kim ,  Jin Young Moon ,  Je Seok Ham

IPC: G06F16/00 ,  G06F16/735 ,  G06F16/738 ,  G06F16/78 ,  G06F40/279

CPC classification number: G06F16/7867 ,  G06F16/735 ,  G06F16/738 ,  G06F40/279

Abstract: Disclosed herein are a method and apparatus for searching for a video section by using a natural language. The method for searching for a video section includes: extracting keywords from a natural language sentence, when the natural language sentence is input; determining whether or not the extracted keywords are included in predefined context information; and deriving and providing a final search result. In addition, when the extracted keywords are included in the predefined context information, a search result is derived by performing a first method, and when the extracted keywords are not included in the predefined context information, a search result is derived by performing a second method.

公开(公告)号：US11527067B2

公开(公告)日：2022-12-13

申请号：US17088185

申请日：2020-11-03

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jin Young Moon ,  Yong Jin Kwon ,  Hyung Il Kim ,  Jong Youl Park ,  Kang Min Bae ,  Ki Min Yun

IPC: G06V20/40 ,  G06K9/62 ,  G06T7/20

Abstract: An electronic device according to an embodiment disclosed herein may include a memory including at least one instruction and a processor. By executing the at least one instruction, the processor may check feature information corresponding to a video and including at least one of an appearance-related feature value and a motion-related feature value from the video, calculate at least one of a starting score related to a starting point of an action instance, an ending score related to an ending point of an action instance, and a relatedness score between action instances on the basis of the feature information corresponding to the video, the action instances being included in the video, and generate an action proposal included in the video on the basis of the at least one score.

公开(公告)号：US11380133B2

公开(公告)日：2022-07-05

申请号：US16834500

申请日：2020-03-30

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hyung Il Kim ,  Yong Jin Kwon ,  Jin Young Moon ,  Jong Youl Park ,  Sung Chan Oh ,  Ki Min Yun ,  Jeun Woo Lee

IPC: G06V10/20 ,  G06V40/16 ,  G06V20/40

Abstract: A domain adaptation-based object recognition apparatus includes a memory configured to store a domain adaptation-based object recognition program and a processor configured to execute the program. The processor learns a generative model for generating a feature or an image similar to a gallery image on the basis of domain adaptation in association with an input probe image and learns an object recognition classification model by using a learning database corresponding to the gallery image and the input probe image, thereby performing object recognition using the input probe image.

公开(公告)号：US11935296B2

公开(公告)日：2024-03-19

申请号：US17411728

申请日：2021-08-25

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jin Young Moon ,  Hyung Il Kim ,  Jong Youl Park ,  Kang Min Bae ,  Ki Min Yun

IPC: G06V20/40

CPC classification number: G06V20/41 ,  G06V20/46 ,  G06V20/49

Abstract: Provided is an apparatus for online action detection, the apparatus including a feature extraction unit configured to extract a chunk-level feature of a video chunk sequence of a streaming video, a filtering unit configured to perform filtering on the chunk-level feature, and an action classification unit configured to classify an action class using the filtered chunk-level feature.