Scholar
Maria Parelli
Google Scholar ID: ipSS2ToAAAAJ
PhD student, University of Tübingen & IMPRS-IS
Citations & Impact
Citations
252
H-index
6
i10-index
5
Publications
9
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- 1. HOLD: Category-agnostic 3d reconstruction of interacting hands and objects from video (CVPR 2024); 2. Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes (BMVC 2023, Oral Presentation); 3. CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes (CVPR Workshops 2023); 4. Interpretable visual question answering via reasoning supervision (ICIP 2023); 5. Spatio-temporal graph convolutional networks for continuous sign language recognition (ICASSP 2022); 6. Exploiting 3d hand pose estimation in deep learning-based sign language recognition from rgb videos (ECCV Workshops 2020).
Research Experience
- 1. ML Engineer/Researcher at Deeplab, working on interpretable vision-language understanding.
Education
- 1. Ph.D., University of Tübingen, Autonomous Vision Group, supervised by Prof. Andreas Geiger, co-supervised by Federico Tombari, Michael Niemeyer, and Michael Oechsle (from Google Zurich); 2. M.Sc., Data Science, ETH Zurich, supervised by Prof. Otmar Hilliges; 3. Diploma, Electrical and Computer Engineering, National Technical University of Athens, supervised by Prof. Petros Maragos.
Background
- Research interests: Computer vision, deep learning, and generative AI. Focus area: 3D generative modeling.
