Erkut Erdem

Professor, Hacettepe University
Chair, Department of Artificial Intelligence and Data Engineering

I work on computer vision and multimodal learning, with current interests in generative AI, video understanding and generation, computational imaging, and language-grounded visual reasoning.

Google Scholar Profile

Curriculum vitae

Current

Department Chair
Artificial Intelligence & Data Engineering

Research Fellow
KUIS AI

Research

Generative AI
Computer Vision
Multimodal Learning
Computational Imaging
Event-based Vision

Contact

erkut@cs.hacettepe.edu.tr
x.com/erkuterdem

Faculty of Computer and Information Sciences
Dept. of AI and Data Engineering
Office No. 112
Hacettepe University, Beytepe Campus
06800 Çankaya, Ankara, Türkiye

Students

6 M.Sc. students currently supervised

Current and former students

Background

Hacettepe University
Faculty Member · 2010–present

École Nationale Supérieure des Télécommunications
Postdoctoral Researcher · 2009–2010

Middle East Technical University
Ph.D. 2008 · M.Sc. 2003 · B.Sc. 2001

University of California, Los Angeles
Visiting Researcher · 2007

Virginia Tech
Visiting Researcher · 2004

I am looking for motivated MSc/PhD students. Scholarships are available for suitable research projects.

Selected research

A small selection of recent work, emphasizing publications in leading computer vision, machine learning, and graphics venues.

LAMP teaser showing language-driven object and camera motion planning

CVPR 2026

LAMP: Language-Assisted Motion Planning for Controllable Video Generation

M. B. Kizil, E. Sanli, N. J. Mitra, E. Erdem, A. Erdem, D. Ceylan

pdf/project page

SalViT360-AV architecture for audio-visual saliency prediction in 360-degree video

IEEE TPAMI 2026

Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360° Videos

M. Cokelek, H. Ozsoy, N. Imamoglu, C. Ozcinar, I. Ayhan, E. Erdem, A. Erdem

pdf/project page

GaussianVideo teaser comparing video reconstruction quality and efficiency

ICCV 2025

GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting

A. Bond, J.-H. Wang, L. Mai, E. Erdem, A. Erdem

pdf/project page

CLIPAway comparison for diffusion-based object removal

NeurIPS 2024

CLIPAway: Harmonizing Focused Embeddings for Removing Objects via Diffusion Models

Y. Ekin, A. B. Yildirim, E. E. Caglar, A. Erdem, E. Erdem, A. Dundar

pdf/project page

HyperGAN-CLIP applications in domain adaptation, synthesis, and manipulation

SIGGRAPH Asia 2024

HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation

A. B. Anees, A. C. Baykal, M. B. Kizil, D. Ceylan, E. Erdem, A. Erdem

pdf/project page

ViLMA benchmark for linguistic and temporal grounding in video-language models

ICLR 2024

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

I. Kesen, A. Pedrotti, M. Dogan, M. Cafagna, E. C. Acikgoz, L. Parcalabescu, I. Calixto, A. Frank, A. Gatt, A. Erdem, E. Erdem

pdf/project page

HyperE2VID dynamic neural network for event-based video reconstruction

IEEE TIP · 2024

HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks

B. Ercan, O. Eker, C. Saglam, A. Erdem, E. Erdem

pdf/project page

Full publication list

Projects & funding

Selected externally funded research projects, with recent work centered on multimodal models, generative AI, event-based vision, and computational imaging.

Developing Multimodal Large Language Models for Healthcare and Remote Sensing

Principal Investigator

3 years (2025-2028) · TUBITAK 2247-A - National Outstanding Researchers Program (Award# 123C542)

project page

Seeing Through Events: End-to-End Approaches to Event-Based Vision Under Extremely Low-Light Conditions

Principal Investigator

3 years (2022-2025) · TUBITAK 1001 - Support Program for Scientific and Technological Research Projects (Award# 121E454)

project page

Developing A Multimodal Large Language Model for Digital Pathology

Co-Investigator

3 years (2025-2028) · TUBITAK 1001 - Support Program for Scientific and Technological Research Projects (Award# 125E190)

Seeing the Invisible: End-to-End Approaches for Hyperspectral Image Enhancement and Synthesis

Co-Investigator

30 months (2023-2026) · TUBITAK 1001 - Support Program for Scientific and Technological Research Projects (Award# 123E385)

Earlier funded projects

A Multimodal and Multilingual Framework for Video Captioning

Principal Investigator

2 years (2018-2020) · TUBITAK and British Council - Newton-Katip Çelebi Fund Institutional Links Grant Programme (Award# 217E054)

project page

Using Synthetic Data for Deep Person Re-Identification

Principal Investigator

2 years (2018-2020) · TUBITAK 1001 - Support Program for Scientific and Technological Research Projects (Award# 217E029)

project page

Understanding Images and Visualizing Text: Semantic Inference and Retrieval by Integrating Computer Vision and Natural Language Processing

Principal Investigator

3 years (2014-2017) · TUBITAK 1001 - 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 )

ICT COST IC1037 Action project page

The Use of Multiple Cues and Contextual Knowledge in Computer Vision

Principal Investigator

3 years (2012-2015) · TUBITAK 3501 - Career Development Program (Award# 112E146)

project page

Quality Assessment of 360-Degree Videos Guided by Audio-Visual Saliency

Co-Investigator

3 years (2021-2024) · TUBITAK 1001 - Support Program for Scientific and Technological Research Projects (Award# 120E501)

Summarization Approaches Towards Interpreting Big Visual Data

Co-Investigator

3 years (2017-2020) · TUBITAK 1003 - Primary Subjects R&D Funding Program (Award# 116E685)

project page

City-Wide Video Surveillance System

Co-Investigator

3 years (2016-2019) · TUBITAK 1007 - Public Institutions Research Funding Program (Award# 114G028)

project page

Students

Current graduate students and former advisees.

Ph.D.

M.Sc.

Desmin Alpaslan
Can Ali Ates
Emre Coban
Abdullah Enes Ergun
Uygar Mutlu
Tuncer Sivri

Former students

Onur Eker (Ph.D., 2026)
Burak Ercan (Ph.D., 2024)
Aysun Kocak (Ph.D., 2023)
Semih Yagciogly (Ph.D., 2023)
Kemal Cizmeciler (Ph.D., 2022)
Bora Celikkale (Ph.D., 2020)
Levent Karacan (Ph.D., 2019)
Yasin Kavak (Ph.D., 2017)
Osman Akin (Ph.D., 2016)
Damla Akcaoglu (M.Sc., 2026)
Tolga Ozdemir (M.Sc., 2026)
Mustafa Dogan (M.Sc., 2024)
Tayfun Ates (M.Sc., 2021)
Ahmet Serdar Karadeniz (M.Sc., 2020)
Menekse Kuyu (M.Sc., 2020)
Begum Citamak (M.Sc., 2020)
Goksu Erdogan (M.Sc., 2018)
Mehmet Gunel (M.Sc., 2018)
Cagdas Bak (M.Sc., 2016)
Hasan Tugrul Erdogan (M.Sc., 2015)

Teaching

Current courses and an archive of previously taught undergraduate and graduate courses.

Current courses

BBM202: Algorithms (Spring 2026)
AIN434/BBM444: Fundamentals of Computational Photography (Spring 2026)

Previously taught courses

Past

Undergraduate

AIN311: Fundamentals of Machine Learning (Fall 2024, Fall 2023, Fall 2022, Fall 2021)
BBM101: Introduction to Programming I (Fall 2019, Fall 2017, Fall 2016, Fall 2015, Fall 2014, Fall 2013, Fall 2011, Fall 2010)
BBM202: Algorithms (Spring 2025, Spring 2024, Spring 2023, Spring 2022, Spring 2021, Spring 2020, Spring 2019, Spring 2018, Spring 2017, Spring 2016, Spring 2015, Spring 2014, Spring 2013)
BBM341: Systems Programming (Fall 2012, Spring 2012)
BBM413: Fundamentals of Image Processing (Fall 2018, Fall 2017, Fall 2016, Fall 2015, Fall 2014, Fall 2013, Fall 2012, Fall 2011, Fall 2010)
BBM406: Fundamentals of Machine Learning (Spring 2021)
AIN434/BBM444: Fundamentals of Computational Photography (Spring 2025, Spring 2024, Spring 2023, Spring 2022)

Graduate

CMP784: Deep Learning (Fall 2024, Fall 2023, Fall 2022, Fall 2021)
CMP717: Image Processing (Fall 2020, Spring 2020, Spring 2019, Spring 2018, Spring 2017, Spring 2016, Spring 2015, Spring 2014, Spring 2013, Spring 2012)
BIL722: Advanced Topics in Computer Vision (Fall 2012)
BIL741 - Advanced Analysis of Algorithms (Spring 2011)
BSB663: Image Processing (Spring 2013)
BCO511: Computer Graphics (Spring 2012)

Erkut Erdem

Recent news

Selected research

LAMP: Language-Assisted Motion Planning for Controllable Video Generation

Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360° Videos

GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting

CLIPAway: Harmonizing Focused Embeddings for Removing Objects via Diffusion Models

HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation

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

HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks

Projects & funding

Developing Multimodal Large Language Models for Healthcare and Remote Sensing

Seeing Through Events: End-to-End Approaches to Event-Based Vision Under Extremely Low-Light Conditions

Developing A Multimodal Large Language Model for Digital Pathology

Seeing the Invisible: End-to-End Approaches for Hyperspectral Image Enhancement and Synthesis

A Multimodal and Multilingual Framework for Video Captioning

Using Synthetic Data for Deep Person Re-Identification

Understanding Images and Visualizing Text: Semantic Inference and Retrieval by Integrating Computer Vision and Natural Language Processing

The Use of Multiple Cues and Contextual Knowledge in Computer Vision

Quality Assessment of 360-Degree Videos Guided by Audio-Visual Saliency

Summarization Approaches Towards Interpreting Big Visual Data

City-Wide Video Surveillance System

Students

Ph.D.

M.Sc.

Teaching

Current courses

Past

Undergraduate

Graduate