Mertcan Akçay
I am working as an Autonomous Systems Design Engineer at Aselsan. I am designing perception algorithms for autonomous unmanned ground vehicles. Previously, I worked as an Image Processing and AI Engineer at Plan-S Satellite and Space Technologies where I contributed to the imaging pipeline for a multi-spectral Earth observation satellite. I obtained my Master’s degree in Robotics, Systems and Control at ETH Zürich. I did my master thesis at Robotics and Perception Group, supervised by Prof. Davide Scaramuzza.
During my Master's, I did an internship at Disney Research | Studios and worked on multimodal machine learning architectures to detect audio-visual synchronization issues on in-the-wild videos. Previously, I obtained my Bachelor's degree in Electrical Engineering at Bilkent University and spent an exchange semester at NTU.
My interests are broadly computer vision and machine learning with a focus on robotics. You can view my CV here. Feel free to reach out if you want to chat about something!
Publications
-
DiVAS: Video and Audio Synchronization with Dynamic Frame Rates Computer Vision and Pattern Recognition (CVPR), 2024. Paper BibTeX
@InProceedings{Fernandez-Labrador_2024_CVPR, author = {Fernandez-Labrador, Clara and Ak\c{c}ay, Mertcan and Abecassis, Eitan and Massich, Joan and Schroers, Christopher}, title = {DiVAS: Video and Audio Synchronization with Dynamic Frame Rates}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26846-26854} } -
3D Segmentation of Humans in Point Clouds with Synthetic Data International Conference on Computer Vision (ICCV), 2023. Paper BibTeX Project Code
@inproceedings{takmaz20233d, title={3D segmentation of humans in point clouds with synthetic data}, author={Takmaz, Ay{\c{c}}a and Schult, Jonas and Kaftan, Irem and Ak{\c{c}}ay, Mertcan and Leibe, Bastian and Sumner, Robert and Engelmann, Francis and Tang, Siyu}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={1292--1304}, year={2023} }
