Hello world, I'm Mert Kilickaya!

I'm a first year PhD. student at QUvA Lab, The University of Amsterdam (UvA). QUvA Lab is a collaborative effort between Qualcomm and UvA, which is directed by Max Welling, Arnold Smeulders and Cees Snoek. My research interest is at the intersection of vision and language. Specifically, I am interested in developing visual representations that can be utilized for image captioning, visual question answering and visual dialogue systems. If interested, please find my MSc. thesis here and my Curriculum Vitae here.


I completed my MSc. in Computer Science, at HUCVL, in 2016, where I've been supervised by Nazli Ikizler-Cinbis and Aykut Erdem . Before joining there, I completed my BSc. at Ankara University under the department of Electrical-Electronics Engineering.


In 2015 Summer, I worked as a Research intern at Laval University, Quebec City, Canada where I've been supervised by Jean-Fran├žois Lalonde. I did my BSc. internship as a Software Developer intern at Bytesnap Design, Birmingham, United Kingdom. I worked as a Research Assistant at the Hacettepe University, Ankara, Turkey between 2013 and 2016. I am now working as a PhD. researcher at the University of Amsterdam.


  1. M. Kilickaya, A.Erdem, N. Ikizler-Cinbis, E.Erdem. "Re-evaluating automatic metrics for image captioning." EACL, Valencia, 2017 (Oral). [PDF]
  2. M. Kilickaya, B. K. Akkus, R. Cakici, A.Erdem, N. Ikizler-Cinbis, E.Erdem. "Data-driven image captioning via salient region discovery." To appear in IET Computer Vision, 2017 (Journal). [PDF]
  3. M. Kilickaya, N. Ikizler-Cinbis, E.Erdem, A.Erdem. "Leveraging captions in the wild to improve object detection." ACL, Berlin, 2016, The 5th. Workshop on Vision and Language. [PDF]
  4. M. Kilickaya, U. Cinar, S. Ugurluoglu. "Efficient marble slab classification using simple features." VISAPP, Rome, 2016. [PDF]
  5. M. Kilickaya, E.Erdem, A.Erdem, N. Ikizler-Cinbis. "Data-driven image captioning with meta-class based retrieval." SIU, 22nd. IEEE, Trabzon, 2014, (in Turkish). [PDF]
  6. M. Kilickaya, Z. Telatar. "Recognizing human actions from still images." SIU, 21st. IEEE, Cyprus, 2013, (in Turkish). [PDF]