Sk Telecom Company, Ltd.

Samsung Sds Co., Ltd.

Other

Geninus Inc.

Seung Ho Shin

Jae Hyun Kim

Se Won Woo

Dong Hyun Park

Gukchan Lim

Jae Hwang Yu

Jinsoo Jeon

Yong Woo Bae

Won Il Chang

Ku Ik Chung

Ikhwan Cho

Seong Won Park

Kyoung Jin Oh

Hak Soon Lee

Hyeong Been Park

Hyeyeun Lim

Jin Yong Han

Sol Yi Kim

Jong Suk Chung

Guk Chan Lim

Dong Youb Sinn

The present disclosure relates to a composition for improving molecular barcoding efficiency and a use thereof, and provided are a method for preparing a DNA library, a molecular barcoding method for nucleic acid sequencing, and a composition for preparing a DNA library. According to the method and composition, by using a barcode sequence arranged to include the position of a first nucleotide in an adapter on the basis of a terminal region of the adapter ligated with a DNA fragment, molecular barcoding switching can be reduced and the accuracy of nucleic acid sequencing can be improved.

Composition for improving molecular barcoding efficiency and use thereof

An apparatus of labeling for object detection according to an embodiment of the present disclosure includes an image selector that determines a plurality of labeling target images from among a plurality of unlabeled images, and determines a labeling order of the plurality of labeling target images, a feedback obtainer that obtains label inspection information on the plurality of labeling target images from a user, and a model trainer that learns the label inspection information input from the user by using the labeling target images, obtains a pseudo label for supervised learning based on a learning result using the label inspection information, and re-determines the labeling order of the labeling target images based on the pseudo label.

Apparatus and method of labeling for object detection

An image projection device includes: a panel unit configured to emit light rays; a projection optical system configured to receive the light rays emitted from the panel unit and to refract the light rays; a reflection unit having a reflection surface for receiving the light rays refracted by the projection optical system and reflecting the light rays; and a screen unit configured to display an image upon receiving the light rays reflected from the reflection surface. The panel unit, the projection optical system, the reflection unit, and the screen unit are arranged such that a distance of a shortest path among paths extending from the panel unit to the reflection unit through the projection optical system along a predetermined linear axis is longer than a distance of a longest path among paths extending from the reflection unit to the screen unit along the predetermined linear axis.

Image projection device

The present invention relates to a feed composition using perilla meal, in which the ratio of omega-3 (omega-3) fatty acid and omega-6 (omega-6) fatty acid is adjusted to 1:4 or less to obtain livestock products, such as meat or milk, containing a large amount of unsaturated fatty acid. More specifically, the present invention related to a feed composition using perilla meal to produce livestock products with the ratio of omega-3 to omega-6 fatty acids being 1:4 or less which is a recommended ratio of the World Health Organization (WHO).

Feed composition using perilla meal and method for producing thereof

An image segmentation model training apparatus according to a disclosed embodiment includes a predictor, which generates a plurality of original masks using an unlabeled original image set and a pre-trained image segmentation model, a label generator, which generates a synthesized image set based on the original image set and the plurality of original masks, and generates a plurality of pseudo labels based on the synthesized image set, a pre-processor, which generates a training image set by performing pseudo labeling on the original image set and the synthesized image set using the plurality of pseudo labels, and a model trainer, which further trains the image segmentation model based on the training image set.

Apparatus and method for training model for image segmentation

In accordance with an aspect of the present disclosure, there is provided a method for recognizing a pose performed by a pose recognition device. The method comprises, acquiring first position information on a portion and remaining portion of a body part which is a target of pose recognition, inputting the first position information on the remaining portion into a three-dimensional skeleton model, acquiring second position information on the remaining portion of the body part according to a calculation based on anatomical characteristics of the three-dimensional skeleton model, and recognizing the pose of the body part based on the first position information and the second position information.

Pose recognition method and device

Growing community of inventors

Seoul, South Korea

Seung Ho Shin