Avatar

Dawit Mureja

Ph.D Candidate

Electrical Engineering, KAIST


CV


I am a Ph.D. student co-advised by Professor In So Kweon and Professor Joon Son Chung , at Electrical Engineering, KAIST.

My research interests lie in the general areas of computer vision and machine learning with a particular focus on:

  • Image and video enhancement
  • Motion estimation
  • Video synthesis and compression
  • High-level video understanding
  • Video editing and summarization

Contact

  • dawitmureja [at] kaist.ac.kr

  • Room 3103, N24 (LG Innovation Hall), 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141

Education

  • Integrated M.S./ Ph.D. in Electrical Engineering

    Sep 2018 - Present

    KAIST, Korea

    Advisor: Prof. In So Kweon

  • B.S. (Magna Cum Laude) in Electrical Engineering

    Sep 2014 - Jul 2018

    KAIST, Korea

Research Experiences

Publications

  • Empirical study on using Adapters for debiased Visual Question Answering

    Jae Won Cho, Dawit Mureja Argaw, Yeongtaek Oh, Dong-Jin Kim, In So Kweon

    Computer Vision and Image Understanding (CVIU), 2023

    [ Paper ]

  • LEMMS: Label Estimation of Multi-feature Movie Segments

    Bartolomeo Vacchetti, Dawit Mureja Argaw, Tania Cequtelli

    International Conference on Computer Vision Workshops (ICCV-W), 2023

    [ Paper ]

  • Long-range Multimodal Pretraining for Movie Understanding

    Dawit Mureja Argaw, Joon-Young Lee, Markus Woodson, In So Kweon, Fabian Caba Heilbron

    International Conference on Computer Vision (ICCV), 2023

    [ Paper | Project ]

  • The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing

    Dawit Mureja Argaw, Fabian Caba Heilbron, Joon-Young Lee, Markus Woodson, In So Kweon

    European Conference on Computer Vision (ECCV), 2022

    Invited paper talk at Creative Video Editing and Understanding (CVEU) Workshop @ ECCV 2022

    [ Paper | Project ]

  • Long-term Video Frame Interpolation via Feature Propagation

    Dawit Mureja Argaw, In So Kweon

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

    [ Paper | Poster ]

  • Motion-blurred Video Interpolation and Extrapolation

    Dawit Mureja Argaw, Junsik Kim, Francois Rameau, In So Kweon

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

    [ Paper | Poster ]

  • Optical Flow Estimation from a Single Motion-blurred Image

    Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Jae Won Cho, In So Kweon

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

    Invited poster presentation at What is Motion For? (WiMF) Workshop @ ECCV 2022, Best Poster Award

    [ Paper | Poster ]

  • Blurry Video Compression: A Trade-off between Visual Enhancement and Data Compression

    Dawit Mureja Argaw, Junsik Kim, In So Kweon

    IEEE Winter Conference on Applications of Computer Vision (WACV), 2024

    [ Paper ]

  • Restoration of Video Frames from a Single Blurred Image with Motion Understanding

    Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Chaoning Zhang, In So Kweon

    IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR-W), 2021, Oral Presentation

    [ Paper ]

  • ResNet or DenseNet: Introducing Shortcuts to ResNet

    Chaoning Zhang*, Philipp Benz*, Dawit Mureja Argaw, Seokju Lee, Junsik Kim, Francois Rameau, Jean Charles Bazin, In So Kweon

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

    [ Paper ]

  • DeePTZ: Deep Self-Calibration for PTZ cameras

    Chaoning Zhang, Francois Rameau, Junsik Kim, Dawit Mureja Argaw, Jean Charles Bazin, In So Kweon

    IEEE Winter Conference on Applications of Computer Vision (WACV), 2020

    [ Paper ]

  • Revisiting Residual Networks with Nonlinear Shortcuts

    Chaoning Zhang, Francois Rameau, Seokju Lee, Junsik Kim, Philipp Benz, Dawit Mureja Argaw, Jean Charles Bazin, In So Kweon

    British Machine Vision Conference (BMVC), 2019, Spotlight Presentation

    [ Paper ]

  • Automatic spine segmentation from CT images using Convolutional Neural Network via redundant generation of class labels

    Dawit Mureja Argaw*, Malinda Vania*, Deukhee Lee (* equal contribution)

    Journal of Computational Design and Engineering (JCDE), Volume 6, Issue 2, 2019

    [ Paper ]

Awards & Honors

  • Top Reviewer Award, Conference on Neural Information Processing Systems (NeurIPS), 2023
  • Outstanding Reviewer Award, CVEU Workshop at ICCV, 2023
  • Outstanding Reviewer Award, International Conference on Computer Vision (ICCV), 2023
  • Best Poster Award, What is Motion For? (WiMF) Workshop @ ECCV 2022
  • Outstanding Reviewer Award, European Conference on Computer Vision (ECCV), 2022
  • Finalist, Qualcomm Innovation Fellowship Korea, 2021
  • Magna Cum Laude, KAIST Electrical Engineering Department, Aug 2018
  • Excellent Research Award, KAIST Undergraduate Research Participation (URP), Sep 2017
  • Dean’s List, KAIST School of Freshman, Feb 2015
  • KAIST Scholarship, Full scholarship for B.S., M.S. and Integrated M.S./Ph.D. programs, 2014-Present

Academic Activities

Student Volunteer

  • ICLR 2020, ICML 2020, NeurIPS 2020

Reviewer

  • ICLR 2024
  • WACV 2024
  • NeurIPS 2023
  • ICCV 2021, 2023
  • CVPR 2021, 2022, 2023, 2024
  • ECCV 2022
  • BMVC 2022, 2023
  • ICRA 2024
  • TPAMI