Dr. Ronak did his M.Tech(ICT) at DAIICT between 2012 and 2014, and completed his PhD from Universitat Oberta de Catalunya, Spain in 2019.

He is now a researcher and engineer specializing in Generative Models, Multimodal Learning, and Applied Machine Learning. Based in Berlin, he currently works at 404-GEN.

With a career spanning both academia and industry, Ronak has led innovative projects such as Font Generation and Drag-based Image Editing during his tenure at Picsart. At present, his work centers on developing multimodal models that validate synthetic 3D assets, ensuring their quality and usability.

During his postdoctoral research, Ronak contributed to the ICONOGRAPHICS and FotoMarburg projects, which applied cutting-edge computer vision techniques to the computational analysis of paintings and artworks. These projects addressed key research questions in the field of digital computational humanities, bridging technology and art in novel ways.

In the field of computational humanities, images of artworks and their contexts are core to understanding the underlying semantic information. However, the highly complex and sophisticated representation of these artworks makes it difficult, even for the experts, to analyze the scene. From the computer vision perspective, the task of analyzing such artworks can be divided into sub-problems by taking a bottom-up approach. In this talk, we focus on the core tasks of computer vision (object detection, pose estimation and gesture recognition) and how to approach research questions in Computational Humanities with data and models' perspective.