The broad goal of my research is to explore better ways to understand, interpret and manipulate visual data*. My research interests span a diverse set of topics, ranging from image editing to visual saliency estimation, and to multimodal learning for integrated vision and language.

I am an Associate Professor of Computer Engineering at Koç University. I’m also affiliated with KUIS AI Center. Before joining Koç University, I was with Hacettepe University, where I was one of the directors of the Computer Vision Lab. I received my PhD degree from the Computer Engineering Department of METU in 2008. During my PhD studies, I spent a summer at Virginia Tech as a visiting researcher, and a semester at MIT as a visiting scholar. I did my postdoc at Ca’Foscari University of Venice in Italy.

I'm looking for motivated MSc/PhD students. Also, don't hesitate to contact me, if you're an undergrad wanting to get into AI and has a desire to learn!

Highlights and News
Mar 2024 Our work on sequential compostional generalization in multimodal models accepted to NAACL 2024 as an oral presentation.
Jan 2024 Our work on evaluating zero-shot linguistic and temporal understanding capabilities of video-language models accepted to ICLR 2024.
Aug 2023 Our work on 360-degree video saliency prediction accepted to BMVC 2023.
Jul 2023 Our paper on video editing is accepted to ICCV 2023: "VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs". Read more about our paper at our project website.
Jul 2023 Our work on StyleGAN and CLIP-based text-guided image manipulation work has been accepted for publication in ACM Transactions on Graphics. We will be presenting our work at SIGGRAPH Asia 2023 at Sydney.
Jun 2023 I received a gift fund from Adobe Research to work on text-guided image synthesis and editing. I will be collaborating with Duygu Ceylan of Adobe Research and Erkut Erdem in this exciting project. Thanks Adobe!
May 2023 We are organizing the first Workshop on Muiltimodal, Multilingual NLG (MM-NLG) at INLG/SIGDial 2023 in September 2023.
Apr 2023 BIG-bench paper has been accepted for publication in Transactions on Machine Learning Research.
Feb 2022 Our work on omnidirectional image quality assessment got accepted to ICASSP 2023.
Nov 2022 We ranked 2nd in the euphemism detection shared task organized by the Figurative Language Processing workshop at EMNLP 2022.
Sep 2022 Our work on language-guided video manipulation accepted to BMVC 2022.
Jun 2022 Our work on language-guided image analysis received the best paper award at 5th Multimodal Learning and Applications Workshop.
Feb 2022 I was appointed to an Associate Editor of IEEE Transactions on Image Processing (IEEE-TIP).
older items

Funding
Principal Investigator TUBITAK 1001 The Support Program for Scientific and Technological Research Projects Award #120E501, 2021-2024 · project page
TUBITAK 1003 Primary Subjects R&D Funding Program Award# 116E685, 2017-2020 · project page
TUBITAK 3501 Career Development Program Award #113E497, 2014-2017 · project page
Co-Investigator TUBITAK 1007 Public Institutions Research Funding Program Award #114G028, 2016-2019 · project page
TUBITAK 1001 The Support Program for Scientific and Technological Research Projects Award #113E116 and European Union under European Cooperation in Science and Technology (COST) Programme: ICT COST IC1037 Action, 2014-2017 · project page
TUBITAK 3501 Career Development Program: Award #112E146, 2012-2015 · project page
Donations Adobe Research Gift, 2023
Adobe Research Gift, 2020
NVIDIA Hardware Donation Grant (Tesla K40 GPU), 2016

Selected Publications

Sequential Compositional Generalization in Multimodal Models

Sequential Compositional Generalization in Multimodal Models
Semih Yagcioglu, Osman Batur Ince, Aykut Erdem, Erkut Erdem, Desmond Elliott, Deniz Yuret
NAACL 2024.
pdf · project page (with code)

HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks

HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
Burak Ercan, Onur Eker, Canberk Saglam, Aykut Erdem, Erkut Erdem
IEEE Transactions on Image Processing, March 2024.
pdf · project page (with code)

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
Ilker Kesen, Andrea Pedrotti, Mustafa Dogan, Michele Cafagna, Emre Can Acikgoz, Letitia Parcalabescu, Iacer Calixto, Anette Frank, Albert Gatt, Aykut Erdem, Erkut Erdem
ICLR 2024.
pdf · project page (with code)

Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers

Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers
Osman İnce, Tanin Zeraati, Semih Yagcioglu, Yadollah Yaghoobzadeh, Erkut Erdem, and Aykut Erdem
Findings of EMNLP 2023, Singapore, December 2023..
pdf · project page (with code)

VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs

VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
Moayed Haji Ali, Andrew Bond, Tolga Birdal, Duygu Ceylan, Levent Karacan, Erkut Erdem, Aykut Erdem
ICCV 2023.
pdf · project page (with code)

CLIP-guided StyleGAN Inversion for Text-driven Real Image Editing

CLIP-guided StyleGAN Inversion for Text-driven Real Image Editing
Ahmet Canberk Baykal, Abdul Basit Anees, Duygu Ceylan, Erkut Erdem, Aykut Erdem, Deniz Yuret
ACM Transactions on Graphics, Vol. 42, Issue 5, Article 172, August 2023.
pdf · project page (with data and code)

Burst Photography for Learning to Enhance Extremely Dark Images

Burst Photography for Learning to Enhance Extremely Dark Images
Ahmet Serdar Karadeniz, Erkut Erdem, Aykut Erdem
IEEE Transactions on Image Processing, November 2021.
pdf · project page (with code)

SLAMP: Stochastic Latent Appearance and Motion Prediction

SLAMP: Stochastic Latent Appearance and Motion Prediction
Adil Kaan Akan, Erkut Erdem, Aykut Erdem, Fatma Guney
ICCV 2021.
pdf · project page (with code)

mustGAN: multi-stream Generative Adversarial Networks for MR Image Synthesis

mustGAN: multi-stream Generative Adversarial Networks for MR Image Synthesis
Mahmut Yurt, Salman UH Dar, Aykut Erdem, Erkut Erdem, Kader K. Oguz, Tolga Cukur
Medical Image Analysis, Vol. 70, May 2021.
pdf

Belief Regulated Dual Propagation Nets for Learning Action Effects on Articulated Multi-Part Objects

Cross-lingual Visual Pre-training for Multimodal Machine Translation
Ozan Caglayan, Menekse Kuyu, Mustafa Sercan Amac, Pranava Madhyastha, Erkut Erdem, Aykut Erdem, Lucia Specia
EACL 2021.
pdf · project page (with data and code)

Belief Regulated Dual Propagation Nets for Learning Action Effects on Articulated Multi-Part Objects

Belief Regulated Dual Propagation Nets for Learning Action Effects on Articulated Multi-Part Objects
Ahmet E. Tekden, Aykut Erdem, Erkut Erdem, Mert Imre, M. Yunus Seker and Emre Ugur
ICRA 2020.
pdf · video

Manipulating Attributes of Natural Scenes via Hallucination

Manipulating Attributes of Natural Scenes via Hallucination
Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem
ACM Transactions on Graphics, Vol. 39, Issue 1, Article 7, February 2020.
pdf · project page (with data and code) · two minute papers

Procedural Reasoning Networks for Understanding Multimodal Procedures

Procedural Reasoning Networks for Understanding Multimodal Procedures
Mustafa Sercan Amac, Semih Yagcioglu, Aykut Erdem, and Erkut Erdem
CoNLL 2019
pdf · project pages (with code)

Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks

Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks
Salman Ul Hassan Dar, Mahmut Yurt, Levent Karacan, Aykut Erdem, Erkut Erdem, Tolga Çukur
IEEE Trans. Med. Imag., Vol. 38, Issue 10, pp. 2375-2388, October 2019.
pdf

RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes

RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes
Semih Yagcioglu, Aykut Erdem, Erkut Erdem, and Nazli Ikizler-Cinbis
EMNLP 2018
pdf · project pages (with data and leaderboard)

Two-Stream Convolutional Networks for Dynamic Saliency Prediction

Spatio-Temporal Saliency Networks for Dynamic Saliency Prediction
Cagdas Bak, Aysun Kocak, Erkut Erdem, Aykut Erdem
IEEE Trans. Multimed., Vol. 20, Issue 7, pp. 1688-1698, July 2018.
pdf

Re-evaluating Automatic Metrics for Image Captioning

Re-evaluating Automatic Metrics for Image Captioning
Mert Kilickaya, Aykut Erdem, Nazli Ikizler-Cinbis, and Erkut Erdem
EACL 2017
pdf · slides

Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts

Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem
arXiv preprint arXiv:1612.00215
pdf

Deformable Part-based Tracking by Coupled Global and Local Correlation Filters

Deformable Part-based Tracking by Coupled Global and Local Correlation Filters
Osman Akin, Erkut Erdem, Aykut Erdem, Krystian Mikolajczyk
J Vis Commun Image Represent 2016
pdf

An Objective Deghosting Quality Metric for HDR Images

TasvirEt: A Benchmark Dataset for Automatic Turkish Description Generation from Images
Mesut Erhan Unal, Begum Citamak, Semih Yagcioglu, Aykut Erdem, Erkut Erdem, Nazli Ikizler Cinbis, Ruket Cakici
SIU 2016
pdf (in Turkish) · project page · Turkish captions for Flickr8K dataset

An Objective Deghosting Quality Metric for HDR Images

An Objective Deghosting Quality Metric for HDR Images
Okan Tarhan Tursun, Ahmet Oguz Akyuz, Aykut Erdem, Erkut Erdem
EG 2016
pdf · project page (with code) · experiment page

The State of the Art in HDR Deghosting: A Survey and Evaluation

The State of the Art in HDR Deghosting: A Survey and Evaluation
Okan Tarhan Tursun, Ahmet Oguz Akyuz, Aykut Erdem and Erkut Erdem
EG STAR 2015
pdf · project page

Structure-Preserving Image Smoothing via Region Covariances

Structure-Preserving Image Smoothing via Region Covariances
Levent Karacan, Erkut Erdem and Aykut Erdem
SIGGRAPH Asia 2013
pdf · project page (with code)

Graph Transduction as a Non-Cooperative Game

Graph Transduction as a Non-Cooperative Game
Aykut Erdem and Marcello Pelillo
Neural Comput 2012
pdf · code

all publications

My Erdös number is 3 (via 1. Arun Kumar Jagota, 2. Marcello Pelillo)

Associate Professor
KUIS AI Center
Department of Computer Engineering
Koç University


aerdem@ku.edu.tr
profile
@aykuterdemml

College of Engineering ENG Z12
Koç University
Rumelifeneri Yolu
Istanbul, Turkey TR-34450
+90 (212) 338-0916

Office hours: Thu 11-12am


Curriculum vitae · all publications


Teaching (2024-2025)
Fall COMP201 · COMP541
Spring COMP201 · COMP547
previous courses


Talks and travel
2 Oct ICCV 2023
12 Dec SIGGRAPH Asia 2023
7 May ICLR 2024
3 Dec SIGGRAPH Asia 2024
10 Dec NeurIPS 2024

a curated list of resources for grad students

PhD students
Andrew Yong Xern Bond
Muhammed Burak Kizil
Ismail Cetin
Hakan Capuk

MSc students
Doga Kukul
Suleyman Yildirim
Yusuf Bayindir
Ali Kerem Ozturk

Former Students
Burak Ercan (PhD) 2024
Aysun Kocak (PhD) 2023
Semih Yagcioglu (PhD) 2023
Kemal Cizmeciler (PhD) 2022
Bora Celikkale (PhD) 2020
Levent Karacan (PhD) 2019
Yasin Kavak (PhD) 2017
Osman Akin (PhD) 2016

Emre Can Acikgoz (MSc) 2024
Osman Batur Ince (MSc) 2024
Burak Can Biner, (MSc) 2023
Nafiseh Jabbari Tofighi, (MSc) 2023
Ahmed Imam Shah, (MSc) 2023
Mert Cokelek (MSc) 2023
Abdul Basit Anees (MSc) 2023
Ahmet Canberk Baykal (MSc) 2022
Tayfun Ates (MSc) 2020
Ahmet Serdar Karadeniz (MSc) 2020
Emre Boran (MSc) 2020
Menekse Kuyu (MSc) 2020
Begum Citamak (MSc) 2020
Mehmet Gunel (MSc) 2018
Goksu Erdogan (MSc) 2018
Burcak Asal (MSc) 2017
Cagdas Bak (MSc) 2016
Mert Kilickaya (MSc) 2016
Tugrul Erdogan (MSc) 2015


Our research is made possible through generous support by The Scientific and Technological Research Council of Turkey (TUBITAK) and NVIDIA Corporation.


Some books I've read and enjoyed

Page design courtesy of Michael Bernstein