This user has not added any information to their profile yet.
I have been a research scientist at Naver Labs Europe and a member of the Computer Vision team since the early 2020s. Before that I was a research scientist at Facebook AI (2017-2020) and Yahoo Research (2015-2017). For a full list of publications please visit my Google Scholar profile or my personal website.
My research interests include representation learning, video understanding, multi-modal learning and vision & language. My focus is currently on resource-constrained representation learning and learning adaptive multi-modal systems.
I am very passionate about making the research community tackle more socially impactful problems and co-lead the Computer Vision for Global Challenges (CV4GC) initiative.
I am passionate about traveling, photography, film, interactive visual arts and music; you can find more about my artistic endeavors on my personal website.
I grew up and lived in Greece until 2015 with brief breaks in Sweden, Spain and the United States. I got my PhD in 2014 from the National Technical University of Athens under the supervision of Dr. Yannis Avrithis. I lived for 5 years in California (San Francisco first and then Oakland), working as a research scientist at Yahoo Research (2015-2017) and Facebook AI (2017-2020). I currently live in Grenoble, France.
[September 2020] Area Chair @ CVPR 2021. I am proudly serving as an area chair for CVPR 2021.
[September 2020] Paper @ NeurIPS 2020. Hard Negative Mixing for Contrastive Learning. See also our Project Page.
[June 2020] Paper @ ECCV 2020. Learning to Generate Grounded Image Captions without Localization Supervision. (work done at Facebook AI)
[March 2020] Paper @ ICLR 2020. Decoupling Representation and Classifier for Long-Tailed Recognition. (work done at Facebook AI)
[March 2020] Workshop @ ICLR 2020. Lead organizer of the Computer Vision for Agriculture (CV4A) workshop.