Dong-Jin Kim (김동진)

Ph.D.

Robotics and Computer Vision Lab.

School of Electrical Engineering

Korea Advanced Institute of Science and Technology (KAIST)

Daejeon, South Korea.

Email : djkim [at] icsi.berkeley.edu / djnjusa [at] gmail.com

Office : Room 211, N1 ITC Building

Phone: (+82)-42-350-5465

[CV] [linkedin] [Google Scholar]

I will be joining International Computer Science Institute (ICSI) at UC Berkeley as a Postdoctoral Scholar under the supervision of Prof. Stella Yu. I received my B.S., M.S., and Ph.D. degrees advised by Prof. In So Kweon in the School of Electrical Engineering (EE) from KAIST (Korea Advanced Institute of Science and Technology) of South Korea in 2015, 2017, and 2021, respectively. I was a student internship with researchers Xiao Sun and Steve Lin in Visual Computing Group, the Microsoft Research Asia (MSRA) from June 2019 to November 2019. I received the Silver Prize of Samsung Humantech awards and Qualcomm Innovation award as the 1st author.

Research Interests

  • Scene Understanding

  • Language and Vision

  • Human Behavior Recognition

  • Data Issues in Deep Learning

News

Sep. 2021. One paper is accepted to TPAMI.

Aug. 2021. One paper is accepted to TIP.

Jul. 2021. One paper is accepted in ICCV 2021 (Oral).

Jul. 2020. One paper is accepted in ECCV 2020.

Education

  • Ph.D. (Mar 2017 ~ Aug 2021)

Electrical Engineering, KAIST (Advisor : In So Kweon)

Dissertation: High-level Scene Understanding with Relational and Linguistic Priors

  • M.S. (Mar 2015 ~ Feb 2017)

Electrical Engineering, KAIST (Advisor : In So Kweon)

Thesis : Disjoint Multi-task Learning between Heterogeneous Action and Caption Data

  • B.S. (Mar 2011 ~ Feb 2015)

Electrical Engineering, KAIST

Selected Publications

"Single-Modal Entropy based Active Learning for Visual Question Answering"

{Dong-Jin Kim*, Jae Won Cho*}, Jinsoo Choi, Yunjae Jung, and In So Kweon (* Co-first authors)

British Machine Vision Conference (BMVC), 2021.

[PDF]

"Dense Relational Image Captioning via Multi-task Triple-Stream Networks"

Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi, and In So Kweon.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted. (Impact Factor 16.389)

[PDF] [Project] [Dataset] [code]

"ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection"

Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, and In So Kweon,

IEEE Transactions on Image Processing (TIP), 2021. (Impact Factor 10.856)

[PDF] [Project] [code]

"LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation"

Inkyu Shin, Dong-Jin Kim, Jae Won Cho, Sanghyun Woo, KwanYong Park, and In So Kweon

IEEE International Conference on Computer Vision (ICCV), 2021. (Oral) (3% accept rate)

[PDF]

  • Winner of Qualcomm Innovation Fellowship 2021.

"MCDAL: Maximum Classifier Discrepancy for Active Learning"

{Jae Won Cho*, Dong-Jin Kim*}, Yunjae Jung, and In So Kweon (* Co-first authors)

arXiv, 2021.

[PDF]

"Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning"

YoungTaek Oh, Dong-Jin Kim, and In So Kweon.

arXiv, 2021.

[PDF] [code]

"Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation"

Jae Won Cho, Dong-Jin Kim, Yunjae Jung, Jinsoo Choi, and In So Kweon

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) Multimodal Learning and Applications Workshop, 2021.

[PDF]

  • Also presented at "Visual Question Answering Workshop" and "VizWiz Grand Challenge Workshop" in conjunction with CVPR 2021.

"Detecting Human-Object Interactions with Action Co-occurrence Priors"

Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, and In So Kweon,

European Conference on Computer Vision (ECCV), 2020. (27% accept rate)

[PDF] [Project] [code] [Slides] [Video] [Poster]

  • Received Silver Prize, 26th Samsung Humantech Paper Awards (Top 1.6%)

  • Also presented at "The 2nd workshop on Video Turing Test: Toward Human-Level Video Story Understanding" in conjunction with ECCV 2020.

"Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach"

Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, and In So Kweon.

International Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019. (23.8% accept rate)

[PDF] [Project] [Slides] [Poster]

  • Also, presented at "Language&Vision " and "Visual Question Answering and Dialog " Workshops in conjunction with CVPR 2019, and "CLVL: 3rd Workshop on Closing the Loop Between Vision and Language" in conjunction with ICCV 2019.

"Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning"

Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, and In So Kweon.

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019. (25.2% accept rate)

[PDF] [Project] [Dataset] [code] [Slides] [Poster]

  • Received Qualcomm Innovation Award 2019.

  • Also presented at "Language&Vision" and "Visual Question Answering and Dialog" Workshops in conjunction with CVPR 2019.

"Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks"

Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, Youngjin Yoon, and In So Kweon.

IEEE Winter Conference on Applications of Computer Vision (WACV), 2018. (Oral)

[PDF]

Honors & Awards

  • CVPR Doctoral Consortium. Jun 2021

IEEE CVPR 2021.

  • Silver Prize, 26th Samsung Humantech Paper Awards (Top 1.6%), 2020 [certificate]

"Detecting Human-Object Interactions with Action Co-occurrence Prior"

Samsung Electronics Co., Ltd.

"Dense Relational Image Captioning via Multi-task Triple-Stream Networks"

Qualcomm Inc.

  • Certificate

International Computer Vision Summer School (ICVSS 2018) [certificate]

Sicily, Italy

Reviewer Experiences

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020, 2021, 2022

  • IEEE International Conference on Computer Vision (ICCV) 2021

  • Conference on Neural Information Processing Systems (NeurIPS) 2020, 2021

  • International Conference on Machine Learning (ICML) 2021

  • International Conference on Learning Representations (ICLR) 2022

  • Annual Meeting of the Association for Computational Linguistics (ACL) 2022

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2021)

  • IEEE Transactions on Image Processing (TIP) (2020)

  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) (2020)

  • Association for the Advancement of Artificial Intelligence (AAAI) 2021, 2022

  • Winter Conference on Applications of Computer Vision (WACV) 2021, 2021

  • Asian Conference on Computer Vision (ACCV) 2020

  • Neurocomputing Journal (2020)

  • The Visual Computer Journal (2020)

  • ETRI Journal (2019)

Teaching Experiences

  • TA for "Circuit Theory" (Spring 2016)

  • TA for "Introduction to Electronics Design Lab" (Fall 2016)

  • TA for "Electronics Design Lab" (Spring 2017)

  • TA for "My Life and Career in EE 2" (Fall 2017)

  • TA for "Advanced Topics in Deep Learning for Robotics and Vision" (Spring 2018, Spring 2019)

  • TA for "Computer Vision" (Fall 2018)

  • TA for "Multiple View Geometry" (Spring 2020)

  • Tutor for "Programming Structure for Electrical Engineering" (Fall 2015, Spring 2017)

  • Tutor for "Signals and System" (Fall 2017)

  • Tutor for "Circuit Theory" (Fall 2018)