Search Results for author: Tae Soo Kim

Found 13 papers, 1 papers with code

Interactive Children’s Story Rewriting Through Parent-Children Interaction

no code implementations In2Writing (ACL) 2022 Yoonjoo Lee, Tae Soo Kim, Minsuk Chang, Juho Kim

Storytelling in early childhood provides significant benefits in language and literacy development, relationship building, and entertainment.

One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations

no code implementations9 May 2024 Yoonjoo Lee, Kihoon Son, Tae Soo Kim, Jisu Kim, John Joon Young Chung, Eytan Adar, Juho Kim

Based on these findings, we present design implications that, instead of regarding LLM output inconsistencies as a drawback, we can reveal the potential inconsistencies to transparently indicate the limitations of these models and promote critical LLM usage.

EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria

no code implementations24 Sep 2023 Tae Soo Kim, Yoonjoo Lee, Jamin Shin, Young-Ho Kim, Juho Kim

By simply composing prompts, developers can prototype novel generative applications with Large Language Models (LLMs).

Language Modelling Large Language Model

ELVIS: Empowering Locality of Vision Language Pre-training with Intra-modal Similarity

no code implementations11 Apr 2023 Sumin Seo, Jaewoong Shin, Jaewoo Kang, Tae Soo Kim, Thijs Kooi

Deep learning has shown great potential in assisting radiologists in reading chest X-ray (CXR) images, but its need for expensive annotations for improving performance prevents widespread clinical application.

Phrase Grounding

LMCanvas: Object-Oriented Interaction to Personalize Large Language Model-Powered Writing Environments

no code implementations27 Mar 2023 Tae Soo Kim, Arghya Sarkar, Yoonjoo Lee, Minsuk Chang, Juho Kim

However, these interfaces provide limited support for writers to create personal tools for their own unique tasks, and may not comprehensively fulfill a writer's needs -- requiring them to continuously switch between interfaces during writing.

Language Modelling Large Language Model

Did You Get What You Paid For? Rethinking Annotation Cost of Deep Learning Based Computer Aided Detection in Chest Radiographs

no code implementations30 Sep 2022 Tae Soo Kim, Geonwoon Jang, Sanghyup Lee, Thijs Kooi

As deep networks require large amounts of accurately labeled training data, a strategy to collect sufficiently large and accurate annotations is as important as innovations in recognition methods.

Video-based assessment of intraoperative surgical skill

no code implementations13 May 2022 Sanchit Hira, Digvijay Singh, Tae Soo Kim, Shobhit Gupta, Gregory Hager, Shameema Sikder, S. Swaroop Vedula

The neural network approach using attention mechanisms also showed high sensitivity and specificity.


SAFCAR: Structured Attention Fusion for Compositional Action Recognition

no code implementations3 Dec 2020 Tae Soo Kim, Gregory D. Hager

We present a general framework for compositional action recognition -- i. e. action recognition where the labels are composed out of simpler components such as subjects, atomic-actions and objects.

Action Recognition Time Series +1

DASZL: Dynamic Action Signatures for Zero-shot Learning

no code implementations8 Dec 2019 Tae Soo Kim, Jonathan D. Jones, Michael Peven, Zihao Xiao, Jin Bai, Yi Zhang, Weichao Qiu, Alan Yuille, Gregory D. Hager

There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large.

Action Detection Activity Detection +3

Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition

no code implementations22 Nov 2017 Jingxuan Hou, Tae Soo Kim, Austin Reiter

Based on the findings from the model interpretation analysis, we propose a targeted refinement technique, which can generalize to various other recognition models.

3D Action Recognition Decoder +3

Interpretable 3D Human Action Analysis with Temporal Convolutional Networks

1 code implementation14 Apr 2017 Tae Soo Kim, Austin Reiter

In this work, we propose to use a new class of models known as Temporal Convolutional Neural Networks (TCN) for 3D human action recognition.

Action Analysis Multimodal Activity Recognition +1

Cannot find the paper you are looking for? You can Submit a new open access paper.