MSc. Informatics Student
Technical University of Munich
Biography
I am an MSc. Informatics student at TUM, with a focus on Computer Vision and NLP. My passion lies in bridging the gap between cutting-edge research and practical applications, consistently integrating state-of-the-art findings into real-world projects.
Interests
- Self-supervised Learning
- Unsupervised Learning
- Unsupervised (Video) Segmentation
- Image Generation and Manipulation Scene Graphs
Education
MSc. in Informatics, 2021 (Expected Graduation 05.24)
Technical University of Munich
BSc in Computer Science, 2020
Sabanci University
Skills
Languages
Python
C++
Technical
Computer VisionVideo Segmentation, Generative Models, Multimodal Learning
Geometric LearningScene Graph Generation, Graph Learning
Natural Language Processing
Named Entity Recognition, Question Answering
MERNBasic capabilities with React, Node.js, MongoDB and Redux
Experience
Master Thesis Student
- Surgical Video Analysis
Working Student
- Unsupervised Semantic Segmentation of Surgery Videos
Research Asssistant
- Understanding of Comic Scenes
- Unsupervised Object Detection in Comic Panels
- Emotion Recognition in Comic Panels
- Domain Adaptation with GANs
NLP Working Student
- Web Crawling with Selenium
- Corpora Generation and Text Preprocessing
- Worked on spell-checking and autocomplete services.
- Implemented Knowledge Graph with Neo4j
Projects
*
Research project on medical visual question answering problem. Explored capabilities of multi-modal Flamingo architecture and domain specific image and text encoders such as PubmedCLIP, PubmedBERT etc.
Worked on Emotion Recognition task on the Golden Age comics. Both text and image modalities are leveraged and fused to classify the emotion of the character.
Worked on Context-based Face Generation in Golden Age Comics (US Comics between the 1930s-1950s). The model predicts the masked face by giving consecutive comic book panels to the model with a randomly selected face masked at the last frame.
Explored capabilities Graph Neural Networks on organ mesh data. Used GNNs to predict Age, BMI, Sex, Height and weight of the patients.