Zeynep Sonat Baltacı
I am a doctoral student in Imagine lab at ENPC, under the supervision of Mathieu Aubry. My work specializes in developing interpretable vision models for clustering and object discovery, with an application to digital humanities. Prior to my PhD, I received my M.Sc. degree from METU, with a focus on long-tailed image recognition under the supervision of Emre Akbaş and Sinan Kalkan.
News
- 04/2024 our work "Historical Printed Ornaments: Dataset and Tasks" is accepted to ICDAR 2024.
- 03/2024 presented on-going research on historical prints at Computing the Page Workshop.
- 11/2023 presented our work "Computer Vision and Historical Scientific Illustrations" at IAMAHA 2023.
- 05/2023 started my PhD in Imagine lab!
Publications
Historical Printed Ornaments: Dataset and Tasks
We propose a historical printed ornament dataset associated with three different tasks: clustering, element discovery and unsupervised change localization.
Computer Vision and Historical Scientific Illustrations
We present a semi-automatic interactive pipeline for scientific illustration extraction and introduce a new dataset of scientific illustrations.
Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation
We propose mask-aware IoU, an IoU variant for better anchor assignment to supervise instance segmentation methods.
Talks
- 03/2024 Workshop, Computing the Page, DHOX, 2024, on "Interpretable Computer Vision Analysis of Historical Prints".
- 11/2023 Conference, IAMAHA 2023, about "Computer Vision and Historical Scientific Illustrations".
Academic activities
- Tutor, DHAI, PSL (March 2024)
- Teaching assistant, DeepL, ENPC (Fall 2023)
- Research intern, ImageLab, METU (Summer 2016)
- Reviewer, ECCV (2024)
Contact
Feel free to reach out through sonat[dot]baltaci[at]enpc[dot]fr!