Dahun Kim Ph.D Candidate Robotics and Computer Vision Lab., KAIST Email: mcahny [at] kaist.ac.kr, mcahny01 [at] gmail.com CV | Google Scholar | Github

I am a Ph.D Candidate at KAIST under professor In So Kweon.

I received B.S. and M.S degree in Electronic Engineering from KAIST in 2016 and 2018 respectively.

• Research Interests

• Deep Learning
  • Video understanding
  • Self supervised learning
  • Weakly supervised learning
• Computer Vision
  • Object recognition
  • Video processing / understanding
  • Image / Video segmentation

• International Publications

	Recurrent Temporal Aggregation Framework for Deep Video Inpainting Dahun Kim*, Sanghyun Woo*, Joon-Young Lee, In So Kweon IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2020 (* equal contribution)
	Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling Yunjae Jung, Dahun Kim, Sanghyun Woo, Kyungsu Kim, Sunjin Kim, In So Kweon Association for the Acvancement of Artificial Intelligence (AAAI), 2020
	Video Retargeting: Trade-off between Content Preservation and Spatio-temporal Consistency Donghyeon Cho, Yunjae Jung, Francois Rameau, Dahun Kim, Sanghyun Woo and In So Kweon ACM Multimedia (MM), 2019 [PDF]
	Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon ACM Multimedia (MM), 2019 [PDF]
	Deep Video Inpainting Dahun Kim*, Sanghyun Woo*, Joon-Young Lee, In So Kweon IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (* equal contribution) [PDF] [Project page] [Codes]
	Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence Dahun Kim*, Sanghyun Woo*, Joon-Young Lee, In So Kweon IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (* equal contribution) [PDF] [Project page] [Codes]
	Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles Dahun Kim, Donghyeon Cho, In So Kweon Association for the Acvancement of Artificial Intelligence (AAAI), 2019 (Oral) [PDF]
	Discriminative Feature Learning for Unsupervised Video Summarization Yunjae Jung, Donghyeon Cho, Dahun Kim, Sanghyun Woo, In So Kweon Association for the Acvancement of Artificial Intelligence (AAAI), 2019 (Oral) [PDF]
	LinkNet: Relational Embedding for Scene Graph Sanghyun Woo*, Dahun Kim*, Donghyeon Cho, In So Kweon Neural Information Processing Systems (NIPS), 2018 (* equal contribution) [PDF]
	Learning Image Representations by Completing Damaged Jigsaw Puzzles Dahun Kim, Donghyeon Cho, Donggeun Yoo, In So Kweon IEEE Winter Conference on Application of Computer Vision (WACV), 2018 (Oral) [PDF]
	Two Phase Learning for Weakly Supervised Object Localization Dahun Kim, Donghyeon Cho, Donggeun Yoo, In So Kweon IEEE International Conference on Computer Vision (ICCV), 2017 [PDF]

• Academic Activities

• Reviewer
  • IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2020.
  • Association for the Advancement of Artificial Intelligence (AAAI) 2020.
  • IEEE International Conf. on Computer Vision (ICCV) 2019.
  • IEEE Trans. on Neural Networks and Leardning Systems (TNNLS)

• Awards & Honors

• Awards and Honors
  • Microsoft Research Asia (MSRA) Fellowship 2019 Winner, Oct 2019.
  • Global Ph.D Fellowshp, National Research Foundation of Korea (about $20,000 + Full scholarship per year for 2+1 years).
  • 1st Place Winner in ECCV Chalearn LAP 2018 challenge track 2, Sep 2018.[PDF]
  • Honorable Mention, 25th HumanTech Paper Award, Samsung Electronics Co., Ltd. ($2,000), Feb 2019.
  • Bronze Prize, Best Paper Award, 25th IPIU 2019, Feb 2019.
  • International Computer Vision Summer School (ICVSS 2018), Jul 2018.