Skip to main content

Dongjin Kim

Hanyang University · 情報科学

研究室紹介

Professor Dongjin Kim's research lab specializes in computer vision, artificial intelligence, and smart materials, with a strong focus on relational understanding in visual scenes, event-driven simulation, and energy-harvesting technologies. The lab develops advanced AI models for dense relational captioning and multi-task learning to enhance image and behavior understanding, while also pioneering novel materials and devices such as electroluminescent polymers and piezoelectric energy harvesters. Their work bridges fundamental AI research with practical applications in human-computer interaction, autonomous systems, and sustainable energy solutions. The lab emphasizes data efficiency, structural priors (like part-of-speech tagging), and real-time simulation for complex physical systems.

image captioningrelational understandingenergy harvestingevent-driven simulationmulti-task learning

Research Overview

Papers
210
Total Citations
1,295
Papers (5y)
68
Primary Field
情報科学

Research Output Trend

Figures are computed from collected data and may differ slightly.

Publications per year (5y)
68total
2022
2023
2024
2025
2026
Citations per year (5y)
297total
20222023202420252026

Selected Papers

15
1
Book Chapter|112 citations·2020
Detecting Human-Object Interactions with Action Co-occurrence Priors
Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, In So Kweon
SJR Q2Lecture notes in computer science
Computer Vision and Pattern RecognitionComputer Science
2
Preprint|92 citations·2019
Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon

Our goal in this work is to train an image captioning model that generates more dense and informative captions. We introduce "relational captioning," a novel image captioning task which aims to generate multiple captions with respect to relational information between objects in an image. Relational captioning is a framework that is advantageous in both diversity and amount of information, leading to image understanding based on relationships. Part-of-speech (POS, i.e. subject-object-predicate ca

Computer Vision and Pattern RecognitionComputer Science
3
Article|70 citations·1998
Fast collision detection among multiple moving spheres
Dong-Jin Kim, Leonidas Guibas, Sung-Yong Shin
SJR Q1IEEE Transactions on Visualization and Computer Graphics

This paper presents an event-driven approach that efficiently detects collisions among multiple ballistic spheres moving in the 3D space. Adopting a hierarchical uniform space subdivision scheme, we are able to trace the trajectories of spheres and their time-varying spatial distribution. We identify three types of events to detect the sequence of all collisions during our simulation: collision, entering, and leaving. The first type of event is due to actual collisions, and the other two types o

Computer Vision and Pattern RecognitionComputer Science
4
Article|39 citations·2021
Dense Relational Image Captioning via Multi-Task Triple-Stream Networks
Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi, In So Kweon
SJR Q1IEEE Transactions on Pattern Analysis and Machine Intelligence

We introduce dense relational captioning, a novel image captioning task which aims to generate multiple captions with respect to relational information between objects in a visual scene. Relational captioning provides explicit descriptions for each relationship between object combinations. This framework is advantageous in both diversity and amount of information, leading to a comprehensive image understanding based on relationships, e.g., relational proposal generation. For relational understan

Computer Vision and Pattern RecognitionComputer Science
5
Preprint|29 citations·2018
Disjoint Multi-task Learning Between Heterogeneous Human-Centric Tasks
Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, Young‐Jin Yoon, In So Kweon

Human behavior understanding is arguably one of the most important mid-level components in artificial intelligence. In order to efficiently make use of data, multi-task learning has been studied in diverse computer vision tasks including human behavior understanding. However, multitask learning relies on task specific datasets and constructing such datasets can be cumbersome. It requires huge amounts of data, labeling efforts, statistical consideration etc. In this paper, we leverage existing si

Computer Vision and Pattern RecognitionComputer Science
6
Article|22 citations·1996
Synthesis of a New Class of Processable Electroluminescent Poly(cyanoterephthalylidene) Derivative with a Tertiary Amine Linkage
Dong-Jin Kim, Sunghyun Kim, Taehyoung Zyung, Jang‐Joo Kim, Iwhan Cho, Sam Kwon Choi
SJR Q1Macromolecules

ADVERTISEMENT RETURN TO ISSUEPREVCommunication to the...Communication to the EditorNEXTSynthesis of a New Class of Processable Electroluminescent Poly(cyanoterephthalylidene) Derivative with a Tertiary Amine LinkageDong-Jin Kim, Sung-Hyun Kim, Taehyoung Zyung, Jang-Joo Kim, Iwhan Cho, and Sam Kwon ChoiView Author Information Department of Advanced Materials Engineering, Korea Advanced Institute of Science and Technology, P.O. Box 201, Cheongryang, Seoul, Korea, Department of Chemistry, Korea Adv

Electrical and Electronic EngineeringEngineering
7
Article|18 citations·2015
Selective current collecting design for spring-type energy harvesters
Dong-Jin Kim, Hee Seok Roh, Yeon‐Tae Kim, Kwangsoo No, Seungbum Hong
SJR Q1RSC Advances

We designed and fabricated a high performance spring-type piezoelectric energy harvester that selectively collects current from the inner part of a spring shell.

Mechanical EngineeringEngineering
8
Article|16 citations·2021
ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection
Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, In So Kweon
arXiv (Cornell University)OA

A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution. The lack of positive labels can lead to low classification accuracy for these classes. Towards addressing this issue, we observe that there exist natural correlations and anti-correlations among human-object interactions. In this paper, we model the correlations as action co-occurrence matri

Computer Vision and Pattern RecognitionComputer Science
9
Preprint|14 citations·2020
Detecting Human-Object Interactions with Action Co-occurrence Priors
Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, In So Kweon
arXiv (Cornell University)OA

A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution. The lack of positive labels can lead to low classification accuracy for these classes. Towards addressing this issue, we observe that there exist natural correlations and anti-correlations among human-object interactions. In this paper, we model the correlations as action co-occurrence matrices and

Computer Vision and Pattern RecognitionComputer Science
10
Article|14 citations·1996
Synthesis and Characterization of Novel Amine-Contained Electroluminescent Polymer
Dong-Jin Kim, Sunghyun Kim, Jihoon Lee, Sujin Kang, Hwan-Kyu Kim, Taehyoung Zyung, Iwhan Cho, Sam‐Kwon Choi
Molecular crystals and liquid crystals science technology. Section A, Molecular crystals and liquid crystals/Molecular crystals and liquid crystals science and technology. Section A, Molecular crystals and liquid crystals

Abstract A new type of processable electroluminescent polymer containing tertiary amine linkage was prepared by typical Wittig reaction between bis(4-formylphenyl) n-butylamine and diphosphonium salt. The resulting polymer was highly soluble in common organic solvents so that it could be spun-cast onto glass plate coated with ITO electrode to give highly transparent homogeneous thin film. The molecular weight of the polymer determined by gel permeation chromatography using polystyrene standards

Electrical and Electronic EngineeringEngineering
11
Article|14 citations·2006
The definition of basic TEDS of IEEE 1451.4 for sensors for an electronic tongue and the proposal of new template TEDS for electrochemical devices
Jeong‐Do Kim, Dong-Jin Kim, Hyung‐Gi Byun, Yu-Kyung Ham, Woosuk Jung, Dongwon Han, Jun‐Seok Park, Hyo-Lin Lee
SJR Q1Talanta
Computer Networks and CommunicationsComputer Science
12
Article|10 citations·1998
Hydrogen transport through anodic WO3 films
Dong-Jin Kim, Su‐Il Pyun
SJR Q1Electrochimica Acta
Materials ChemistryMaterials Science
13
Article|8 citations·2014
A birthmark-based method for intellectual software asset management
Dong-Jin Kim, Jeongoh Moon, Seong-je Cho, Jongmoo Choi, Minkyu Park, Sangchul Han, Lawrence Chung

The software industry has been increasingly aware of the need to employ copyright protection techniques against software piracy or illegal distribution. Recently, as the value of software as intellectual property grows, so does the rate of global software piracy. Software piracy is a real threat to software industry. Moreover, Pirated software is more vulnerable to attacks since such software is less likely to be supported with critical security patches and updates. In this paper, we propose a b

Signal ProcessingComputer Science
14
Article|8 citations·2013
Measuring similarity of windows applications using static and dynamic birthmarks
Dong-Jin Kim, Yongman Han, Seong-je Cho, Hae-Young Yoo, Jinwoon Woo, Yunmook Nah, Minkyu Park, Lawrence Chung

A software birthmark is unique, as certain native characteristics of a program, hence can be used to measure the similarity between programs. In general, a static software birthmark does not need program execution, but is more vulnerable to attacks by semantic-preserving transformations. A dynamic software birthmark is applicable to packed executables, but cannot cover all the possible program paths. In this paper, we propose a novel effective technique to measure the similarity of Microsoft Win

Information SystemsComputer Science
15
Article|8 citations·2014
C-Rank and its variants: A contribution-based ranking approach exploiting links and content
Dong-Jin Kim, Sang‐Chul Lee, Ho-Yong Son, Sang‐Wook Kim, Jae Bum Lee
SJR Q1Journal of Information Science

This paper addresses the problem in Web page ranking of effectively combining link and content information with efficiency high enough to be applicable to real-world search engines. Unlike previous surfer models, our approach is based on the viewpoint of a Web page author. Based on this viewpoint, we formulate the concept of contribution score, which indicates the amount to which a term in each page is utilized by other pages. To improve efficiency without loss of effectiveness, we exploit the e

Information SystemsComputer Science

Research Areas

Computer Vision and Pattern RecognitionInformation SystemsComputer Networks and CommunicationsSignal ProcessingArtificial IntelligenceCultural Studies

Dongjin Kimの研究をNubintでさらに深く

この研究室の論文をアプリで開き、AIと共に読み、要約し、引用しましょう。