Özgür Kara

prof_pic.jpg

Health Care Engineering Systems Center

1206 W Clark St. UIUC

Urbana, IL, USA, 61801

I am a Computer Science PhD student at the University of Illinois Urbana-Champaign (UIUC), where I am advised by Professor James M. Rehg. My research is focused on advancing the capabilities of video generative AI.

My research builds the next generation of video AI by tackling three core challenges: efficiency, controllability, and safety. I design computationally efficient models for long-form video editing, develop frameworks that give users precise control over story and appearance, and build safe systems to protect visual media from unauthorized manipulation.

Before my PhD, I conducted research on continual learning to mitigate bias with Prof. Hatice Gunes (Affective Intelligence and Robotics Lab, University of Cambridge), on zero-shot learning with GANs with Prof. Zeynep Akata and Dr. Yongqin Xian (University of Tubingen), and on neural architecture search & image restoration with Prof. Ender Konukoglu (Computer Vision Lab, ETH Zurich).

I have since completed research internships at Adobe with Tobias Hinz in 2024 Summer (multi-shot video generation), and am currently at Google working with Du Tran (video generation).

I am open to opportunities for collaboration and am always interested in discussing new research ideas. Please feel free to contact me via email.

I always look for self-motivated students who want to focus on Generative AI related projects. Feel free to reach out to me if you are interested and located at UIUC.

:page_with_curl: Download my CV.

Education

  • PhD (Transferred): Computer Science - UIUC - 2024-Present
  • MSc, PhD: Machine Learning - Georgia Institute of Technology - 2022-2024
  • BSc: Electrical-Electronics Engineering - Bogazici University - 2018-2022
  • High School: Math and Science - Kadikoy Anadolu High School - 2013-2018

news

Aug-2025 The 7th edition of our workshop, CVEU (AI for Creative Visual Content Generation, Editing, and Understanding), where I serve as the co-organizer, has been conducted in SIGGRAPH 2025.
May-2025 Interning at Google Mountain View this summer!
Feb-2025 The project I worked on during my Adobe internship, “ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models”, has been accepted to CVPR 2025! Stay tuned!
Dec-2024 The 6th edition of our workshop, CVEU (AI for Creative Visual Content Generation, Editing, and Understanding), where I serve as the primary organizer, has been accepted for CVPR 2025. Stay tuned!
Sep-2024 2 papers have been submitted to CVPR’25. Stay tuned!

selected publications

  1. CVPR 2025
    shotadapter.jpg
    ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models
    Ozgur Kara, Krishna. K. Singh, Feng Liu, Duygu Ceylan, James M. Rehg, and Tobias Hinz
    CVPR, 2025
    ShotAdapter enables text-to-multi-shot video generation with minimal fine-tuning, providing users control over shot number, duration, and content through shot-specific text prompts, along with a multi-shot video dataset collection pipeline.
  2. In Submission
    diffvax.png
    Optimization-Free Image Immunization Against Diffusion-Based Editing
    Tarik C. Ozden*, Ozgur Kara*, Oguzhan Akcin, Kerem Zaman, Shashank Srivastava, Sandeep P. Chinchali, and James M. Rehg
    In Submission, 2024
    DiffVax is an optimization-free image immunization framework that effectively protects against diffusion-based editing, generalizes to unseen content, is robust against counter-attacks, and shows promise in safeguarding video content.
    arXiv Website
  3. In Submission to TPAMI
    social_survey.jpg
    Towards Social AI: A Survey on Understanding Social Interactions
    Sangmin Lee, Minzhi Li, Bolin Lai, Wenqi Jia, Fiona Ryan, Xu Cao, Ozgur Kara, Bikram Boote, Weiyan Shi, Diyi Yang, and James M. Rehg
    In Submission to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
    This is the first survey to provide a comprehensive overview of machine learning studies on social understanding, encompassing both verbal and non-verbal approaches.
    arXiv
  4. ECCVW 2024 (Oral)
    point_tracker.jpg
    Leveraging Object Priors for Point Tracking
    Bikram Boote, Anh Thai, Wenqi Jia, Ozgur Kara, Stefan Stojanov, James M. Rehg, and Sangmin Lee
    Instance-Level Recognition (ILR) Workshop at ECCV (Oral), 2024
    We propose a novel objectness regularization approach that guides points to be aware of object priors by forcing them to stay inside the the boundaries of object instances.
    arXiv Code
  5. CVPR 2024 (Highlight)
    cvpr_rave.jpg
    RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models
    Ozgur Kara, Bariscan Kurtkaya, Hidir Yesiltepe, James M. Rehg, and Pinar Yanardag
    CVPR (Highlight), 2024
    RAVE is a zero-shot, lightweight, and fast framework for text-guided video editing, supporting videos of any length utilizing text-to-image pretrained diffusion models.
    arXiv Demo Code Website
  6. IEEE FG 2024
    fg_slr.jpg
    Transfer Learning for Cross-dataset Isolated Sign Language Recognition in Under-Resourced Datasets
    Alp Kindiroglu*, Ozgur Kara*, Ogulcan Ozdemir, and Lale Akarun
    IEEE International Conference on Automatic Face and Gesture Recognition (IEEE FG), 2024
    This study provides a publicly available cross-dataset transfer learning benchmark from two existing public Turkish SLR datasets.
    arXiv Code
  7. CVPR 2022
    cvpr_isnasdip.JPG
    ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior
    Metin Ersin Arican*, Ozgur Kara*, Gustav Bredell, and Ender Konukoglu
    CVPR, 2022
    ISNAS-DIP is an image-specific Neural Architecture Search (NAS) strategy designed for the Deep Image Prior (DIP) framework, offering significantly reduced training requirements compared to conventional NAS methods.
    PDF Video Code
  8. IEEE TAC
    ieee_ac.JPG
    Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
    Nikhil Churamani, Ozgur Kara, and Hatice Gunes
    IEEE Transactions on Affective Computing, 2022
    we propose the novel use of Continual Learning (CL), in particular, using Domain-Incremental Learning (Domain-IL) settings, as a potent bias mitigation method to enhance the fairness of Facial Expression Recognition (FER) systems.
    PDF Code
  9. LEAP-HRI 2021
    leap_hri.JPG
    Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
    Ozgur Kara, Nikhil Churamani, and Hatice Gunes
    Workshop on Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI), 16th ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2021
    We propose the novel use of Continual Learning (CL) as a potent bias mitigation method to enhance the fairness of Facial Expression Recognition (FER) systems.
    PDF Code
  10. Nano Communication Networks
    nanocom.jpg
    Molecular index modulation using convolutional neural networks
    Ozgur Kara, Gokberk Yaylali, Ali Emre Pusane, and Tuna Tugcu
    Nano Communication Networks, 2022
    We propose a novel convolutional neural network-based architecture for a uniquely designed molecular multiple-input-single-output topology, aimed at mitigating the detrimental effects of molecular interference in nano molecular communication.
    PDF Code
  11. Brain Stimulation
    neuroweaver.JPG
    Neuroweaver: a platform for designing intelligent closed-loop neuromodulation systems
    Parisa Sarikhani, Hao-Lun Hsu, Ozgur Kara, Joon Kyung Kim, Hadi Esmaeilzadeh, and Babak Mahmoudi
    Brain Stimulation: Basic, Translational, and Clinical Research in Neuromodulation, 2021
    Our interactive platform enables the design of neuromodulation pipelines through a visually intuitive and user-friendly interface. (Google Summer of Code 2021 project)
    PDF Code