Difference between revisions of "Daesik Kim"

From MIPAL
Jump to: navigation, search
 
(21 intermediate revisions by one user not shown)
Line 3: Line 3:
 
| style="width: 200px;" |[[file:kds.jpg | 200px]]
 
| style="width: 200px;" |[[file:kds.jpg | 200px]]
 
| <font size = 5> '''[[Daesik Kim]] (김대식)'''</font><br><br>
 
| <font size = 5> '''[[Daesik Kim]] (김대식)'''</font><br><br>
:서울대학교 융합과학부 석박사통합과정 (2014.09 ~ ) <br>
+
:서울대학교 융합과학부 석박사통합과정 졸업 (2014.09 ~ 2019.08) <br>
 
:포항공과대학교 산업경영공학과 졸업 (2007.08) <br>
 
:포항공과대학교 산업경영공학과 졸업 (2007.08) <br>
 
<br>
 
<br>
Line 14: Line 14:
 
== '''Research Interests''' ==
 
== '''Research Interests''' ==
  
Machine Learning, Generative Deep Learning Model, Multi-modal Deep Learning
+
* Machine Learning, Multi-modal Deep Learning, Knowledge based Deep learning
  
  
 
== '''Education''' ==
 
== '''Education''' ==
B.Sc. Industrial Engineering and Management, Pohang University of Science and Technology, 2007
+
* B.Sc. Industrial Engineering and Management, Pohang University of Science and Technology, 2007
  
  
 
== '''Employment''' ==
 
== '''Employment''' ==
  
System developer, Programmer(Powerbuilder, Oracle), Mega IT. 2002-2005
+
* System developer, Programmer(Powerbuilder, Oracle), Mega IT. 2002-2005
  
Assistant Manager ,Tresury department, Kookmin bank, 2007-2014
+
* Assistant Manager ,Tresury department, Kookmin bank, 2007-2014
  
 +
* Founder & CEO/CTO in '''[http://www.vdotdo.com V.DO]''', 2017~
  
 
== '''Publication''' ==
 
== '''Publication''' ==
  
Seo, J., Kim, D., Suh, B., & Lee, J. (2015, April). Design of a Smart TV Logging System Using Beacons and Smartphones. In Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems (pp. 2157-2162). ACM.
+
https://scholar.google.com/citations?user=YUcWWbEAAAAJ&hl=en
  
멀티모달 딥러닝을 이용한 음악 장르 분류. HCI KOREA 2016
+
* Seo, J., Kim, D., Suh, B., & Lee, J. (2015, April). "[https://dl.acm.org/citation.cfm?id=2732858&dl=ACM&coll=DL Design of a Smart TV Logging System Using Beacons and Smartphones]", In Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems (pp. 2157-2162). ACM.
  
Daesik Kim, Myunggi Lee and Nojun Kwak, "Matching Video Net: Memory-based embedding for video action recognition", International Joint Conference on Neural Networks 2017 (IJCNN2017), Anchorage, AK, May 2017.
+
* Seonhoon Kim, Daesik Kim and Bongwon Suh "[https://dl.acm.org/citation.cfm?id=2903686&dl=ACM&coll=DL Music Genre Classification using Multimodal Deep Learning]" Proceedings of HCI Korea '16
  
Sangkuk Lee, Daesik Kim, Myunggi Lee, Jihye Hwang and Nojun Kwak, "Where to Play: Retrieval of video segments using natural-language queries", arXiv, July 2017
+
* Daesik Kim, Myunggi Lee and Nojun Kwak, "[http://ieeexplore.ieee.org/document/7965886/ Matching Video Net: Memory-based embedding for video action recognition]", International Joint Conference on Neural Networks 2017 (IJCNN2017), Anchorage, AK, May 2017.
  
 +
* Sangkuk Lee, Daesik Kim, Myunggi Lee, Jihye Hwang and Nojun Kwak, "[https://arxiv.org/pdf/1707.00251.pdf Where to Play: Retrieval of video segments using natural-language queries]", arXiv, July 2017.
 +
 +
* Daesik Kim, Youngjoon Yoo, Jeesoo Kim, Sangkuk Lee and Nojun Kwak, "[http://openaccess.thecvf.com/content_cvpr_2018/papers/Kim_Dynamic_Graph_Generation_CVPR_2018_paper.pdf Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams]", The Thirtieth IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2018), accepted.
 +
 +
* Daesik Kim, Seonhoon Kim, and Nojun Kwak, "Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension", 57th Annual Meeting of the Association for Computational Linguistics (ACL2019), Florence, Italy. July 2019 (accepted, [https://arxiv.org/abs/1811.00232 arXiv]).
  
 
== '''Competition''' ==
 
== '''Competition''' ==
  
4th place of "Textbook Question Answering Challenge", CVPR 2017 Workshop on Visual Understanding Across Modalities
+
* 4th place of "Textbook Question Answering Challenge", CVPR 2017 Workshop on Visual Understanding Across Modalities
 +
 
 +
 
 +
== '''Teaching''' ==
 +
 
 +
* Tensorflow tutorial at OSIA (Aug. 2016)
 +
 
 +
* Tensorflow tutorial at CONTECH (Apr. 2017)
 +
 
 +
* Deeplearning class for artists at NABI artcenter (oct.~ dec. 2017, 8 weeks)

Latest revision as of 14:45, 21 October 2019

Kds.jpg Daesik Kim (김대식)

서울대학교 융합과학부 석박사통합과정 졸업 (2014.09 ~ 2019.08)
포항공과대학교 산업경영공학과 졸업 (2007.08)


Tel: +82-31-888-9579
e-mail: daesik.kim@snu.ac.kr


Research Interests

  • Machine Learning, Multi-modal Deep Learning, Knowledge based Deep learning


Education

  • B.Sc. Industrial Engineering and Management, Pohang University of Science and Technology, 2007


Employment

  • System developer, Programmer(Powerbuilder, Oracle), Mega IT. 2002-2005
  • Assistant Manager ,Tresury department, Kookmin bank, 2007-2014
  • Founder & CEO/CTO in V.DO, 2017~

Publication

https://scholar.google.com/citations?user=YUcWWbEAAAAJ&hl=en

  • Daesik Kim, Seonhoon Kim, and Nojun Kwak, "Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension", 57th Annual Meeting of the Association for Computational Linguistics (ACL2019), Florence, Italy. July 2019 (accepted, arXiv).

Competition

  • 4th place of "Textbook Question Answering Challenge", CVPR 2017 Workshop on Visual Understanding Across Modalities


Teaching

  • Tensorflow tutorial at OSIA (Aug. 2016)
  • Tensorflow tutorial at CONTECH (Apr. 2017)
  • Deeplearning class for artists at NABI artcenter (oct.~ dec. 2017, 8 weeks)