Minseong Kim

HIVE: Hierarchical identification in visual entomology for pest recognition

Minseong Kim, Jin Hyeok Choi, Junyoung Park, Olga Frunze et autres

HIVE: Hierarchical identification in visual entomology for pest recognition

Minseong Kim, Jinhyeok Choi, Junyoung Park, Olga Frunze et autres

Highlights• We present HIVE, a benchmark of 2M pest images annotated across 19 taxonomic levels.• Models trained on HIVE improve real-world pest recognition and capture key traits.• Pretraining on HIVE improves downstream performance across pest benchmarks.• Image embeddings from HIVE-pretrained models enable …

kr (code pays fourni par la source)

From study design to executable code: automating target trial emulation with large language models

Hanjae Kim, Minseong Kim, Seonji Kim, Seng Chan You

Objective: Implementing target trial emulation (TTE) studies as standardized, reproducible analytic workflows is technically demanding. We developed Text-guided Health-study Estimation and Specification Engine Using Strategus (THESEUS), which uses large language models (LLMs) to translate free-text study descriptions into structured analytic specifications and …

kr, us (code pays fourni par la source)

Validation of Formative Feedback Scale in University Classes

Minseong Kim

본 연구는 대학교육에서 자기조절적이고 성찰적인 학습자로 성장하는데 도움을 주는 피드백의 역할을 ‘형성적 피드백’으로 규정하고, 형성적 피드백 실천을 안내하기 위해 ‘대학수업에서의 형성적 피드백 척도’를 개발하고 타당화 하는 것을 목표로 한다. 이를 위해 피드백에 대한 선행연구 및 효과적인 피드백 대학수업 사례에 대한 근거이론 연구 …

Relevance Analysis between SDGs and Achievement Standards of the 2022 Revised Elementary Practical Arts Curriculum

Minseong Kim, Sangwon Lee

이 연구는 2022 개정 초등 실과교육과정의 성취기준에서 지속가능발전목표(SDGs)를 분석하여 학교 현장에서 ESD가 체계적으로 이루어지도록 기초자료를 제공하는데 있다. 연구 목적을 달성하기 위해 선행연구와 초등 실과교육과정 성취기준을 분석하여 관련 있는 SDGs의 세부목표를 추출하였다. 이를 바탕으로 분석 준거와 틀을 마련하여 실과교육 영역의 내용과 비교 ‧ …

Physics Teacher Agency for Physics Education

Minseong Kim

In the field of middle and high school physics education, teachers must succeed in both “physics education” and “physics as education.” This is because the school classroom is not just a time for learning physics, but also a time for connecting physics …

Compact Image-Style Transfer: Channel Pruning on the Single Training of a Network

Minseong Kim, Hyun‐Chul Choi

Recent image-style transfer methods use the structure of a VGG feature network to encode and decode the feature map of the image. Since the network is designed for the general image-classification task, it has a number of channels and, accordingly, requires a …

kr (code pays fourni par la source)

Total Style Transfer with a Single Feed-Forward Network

Minseong Kim, Hyun‐Chul Choi

The development of recent image style transfer methods allows the quick transformation of an input content image into an arbitrary style. However, these methods have a limitation that the scale-across style pattern of a style image cannot be fully transferred into a …

kr (code pays fourni par la source)

Identifying the Characteristics of Teachers Providing Effective Feedback using Latent Class Analysis

Gyueun Kim, Dongjoo Lee, Minseong Kim

Optimizing TensorFlow Performance by Reconstructing the Convolution Routine

Minseong Kim, Kyu Hyun Choi, Yoonah Paik, Seon Wook Kim

Using deep learning, we can currently build computational models composed of multiple processing layers to learn representations of data. Convolutional neural networks (CNNs) have been widely adopted to achieve significant performance in image recognition and classification. TensorFlow, an open-source deep learning framework …

Uncorrelated feature encoding for faster image style transfer

Minseong Kim, Hyun‐Chul Choi

kr (code pays fourni par la source)

Brick partition problems in three dimensions

Ilkyoo Choi, Minseong Kim, Kiwon Seo

A $d$-dimensional brick is a set $I_1\times \cdots \times I_d$ where each $I_i$ is an interval. Given a brick $B$, a brick partition of $B$ is a partition of $B$ into bricks. A brick partition $\mathcal{P}_d$ of a $d$-dimensional brick is $k$-piercing …

kr (code pays fourni par la source)