I am the Director of AI at Apziva. I received my PhD in Computer Engineering from Hacettepe University where I focused on multimodal comprehension of how-to instructions. Previously, I was a Group Lead at STM. I am interested in learning algorithms and work at the intersection of language and vision. I want to understand intelligence and help machines solve challenging problems.
2016: Our work on Turkish image description generation is featured on national TV.
Research
I am interested in machine intelligence and how machines learn. Broadly, I do research in Computer Vision and Natural Language Processing. More specifically, I am interested in the following research areas.
Procedural Reasoning Networks for Understanding Multimodal Procedures Mustafa Sercan Amac, Semih Yagcioglu, Aykut Erdem, and Erkut Erdem
[CoNLL19] [pdf] [project]
Detecting Cybersecurity Events from Noisy Short Text S. Yagcioglu, M. S. Seyfioglu, B. Citamak, B. Bardak, S. Guldamlasioglu, A. Yuksel and E. I. Tatli
[NAACL19] [pdf] [project]
RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes S. Yagcioglu, A. Erdem, E. Erdem, N. Ikizler-Cinbis
[EMNLP18] [pdf] [project]
TasvirEt: A Benchmark Dataset for Automatic Turkish Description Generation from Images M. E. Unal, B. Citamak, S. Yagcioglu, A. Erdem, E. Erdem, N. Ikizler-Cinbis, R. Cakici
[SIU16] [pdf] [project] Best Paper Award
A Distributed Representation Based Query Expansion Approach for Image Captioning S. Yagcioglu, E. Erdem, A. Erdem, R. Cakici
[ACL15] [pdf] [project]
City Scale Image Geolocalization via Dense Scene Alignment S. Yagcioglu, E. Erdem, A. Erdem
[WACV15] [pdf] [project]