Adil Karjauv

Qualcomm AI Research. Amsterdam, Netherlands.

prof_pic_03.jpg

Hello, welcome to my personal page!

I am currently a Machine Learning Researcher and Engineer at Qualcomm AI Research working on efficient video generative AI. My work significantly contributed to the following:

  • First on-device deep-learning-based video denoising solution at high resolution (QHD and 4K at 30FPS) and an associated patent
  • Two papers (one accepted at ECCV 2024 and the other one is under review) and two patents about efficient video diffusion models
  • The fastest diffusion-based mobile video editing demo on-device (NeurIPS 2024 demo)

Prior to that, I completed a Master’s degree at KAIST in Robotics and Computer Vision (RCV) Lab under supervision of Prof. In So Kweon. My primary focus was on adversarial machine learning and its applications in multimedia. This work led to several publications in top-tier conferences and workshops such as CVPR, ICCV, NeurIPS, ICLR, and others.

I am always open to new opportunities and collaborations, so please feel free to reach out!

news

Nov 26, 2024 This page is now live!

selected publications

  1. Preprint
    MoViE: Mobile Diffusion for Video Editing
    Adil Karjauv*, Noor Fathima*, Ioannis Lelekas, Fatih Porikli, and 2 more authors
    Preprint, 2024
    PDF Website
  2. ECCV
    Object-Centric Diffusion for Efficient Video Editing
    Kumara Kahatapitiya, Adil Karjauv, Davide Abati, Fatih Porikli, and 2 more authors
    In European Conference on Computer Vision (ECCV), 2024
    PDF Website
  3. CVPR
    Investigating Top-k White-Box and Transferable Black-box Attack
    Chaoning Zhang, Philipp Benz, Adil Karjauv, Jae Won Cho, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    PDF
  4. ACM MM
    Towards Robust Deep Hiding Under Non-Differentiable Distortions for Practical Blind Watermarking
    Chaoning Zhang*, Adil Karjauv*, Philipp Benz*, and In So Kweon
    In Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), 2021
    Website
  5. ICCV
    Data-free Universal Adversarial Perturbation and Black-box Attack
    Chaoning Zhang*, Philipp Benz*, Adil Karjauv*, and In So Kweon
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021
    PDF
  6. NeurIPS
    UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging
    Chaoning Zhang*, Philipp Benz*, Adil Karjauv*, Geng Sun, and 1 more author
    Advances in Neural Information Processing Systems (NeurIPS), 2020
    PDF Code