About me

I make Vision-Language Models (VLMs) culturally aware, starting with Southeast Asia, one of the world’s most culturally diverse regions. I am a Research Scientist at Singapore Management University (SMU), working with Prof Chong-Wah Ngo on multimodal reasoning across image, video, audio and text.

EMNLP 2025 AAAI 2025 🏆 Joint 3rd Place, CVPR'22 Challenge 4 Oral Presentations SINGA Scholar 🤗 Benchmark Dataset

I am actively looking for collaborators and student interns on culturally-aware multimodal AI. Book a 30-minute chat or email me.

I obtained my PhD from the College of Computing and Data Science (CCDS) at Nanyang Technological University (NTU) in Singapore, supported by the SINGA scholarship from the Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR). My doctoral research focused on Towards Semantic, Debiased and Moment Video Retrieval with Multi-modal Features conducted under the supervision of Prof. Joo-Hwee Lim, Dr Hongyuan Zhu and Prof. Hanwang Zhang. During my PhD studies, I had the opportunity to visit the University of Bristol, in the UK, collaborating with Dr Michael Wray in Dima Damen’s research group. I completed my Master’s degree under the guidance of Prof. Ahmet Emir Dirik, specializing in vehicle detection. My professional experience spans roles at a start-up in Istanbul, Turkish Airlines Technology, and an internship at the University of Valencia. Additionally, I have provided advisory support to two award-winning start-ups located in London and Istanbul.

Work with me

Research collaborators: cultural reasoning and grounding benchmarks, culturally-aware VLMs, Southeast Asia datasets. Book a 30-minute chat.
Students: internships and research mentorship at SMU on multimodal AI. Email me with your CV and a short note on what you would like to work on.
Industry & talks: invited talks, media, and projects on cultural AI evaluation. Email me or book a slot.

Selected Publications

Seeing Culture: A Benchmark for Visual Reasoning and Grounding
Burak Satar*, Zhixin Ma*, Patrick Amadeus Irawan, Wilfried Ariel Mulyawan, Jing Jiang, Ee-Peng Lim, Chong-Wah Ngo (* equal contribution)
EMNLP 2025 Main Conference
A two-stage benchmark where models must first reason about a cultural artifact, then visually ground it, exposing systematic gaps in how VLMs handle Southeast Asian cultural context.
[Project Website] [Paper] [arXiv] [Code] [🤗 Dataset]

Seeing Culture Benchmark teaser

Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo-Hwee Lim
BMVC 2023
Shows that text-video retrieval models exploit clip length as a shortcut, and mitigates the bias with causal intervention.
[arXiv] [YouTube Ppt] [Project Page]

Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval
Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo-Hwee Lim
🏆 Joint 3rd Place, EPIC-Kitchens Challenge @ CVPR 2022 Workshop
Took joint 3rd place in the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge.
[Technical Report] [(pseudo)Code]

All Publications

Research during Post-Doctoral Work

Cultural Moment Benchmark: Evaluating Video Cultural Reasoning and Grounding in Southeast Asia
Burak Satar, Zhixin Ma, Cheng Yu-Tong, Huy Hoang Tran, Phuong Anh Nguyen, Chong-Wah Ngo
Under peer review. arXiv preprint coming soon

Retrieval Augmented Reasoning Segmentation in Cultural Context
Zhixin Ma*, Burak Satar*, Patrick Amadeus Irawan, Wilfried Ariel Mulyawan, Phuong Anh Nguyen, Chong-Wah Ngo
(Under development)

Research during Doctoral Study

PhD Research Topic 3: Multimodal and Generative Video/Moment Retrieval

Video Corpus Moment Retrieval in Long Ego-centric Videos with LLM and Audio Fusion
Burak Satar, Joo-Hwee Lim, Hanwang Zhang, M Furkan Ilaslan, Hongyuan Zhu, Michael Wray
(Under development)

VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting
Muhammet Furkan Ilaslan, Ali Köksal, Kevin Qinghong Lin, Burak Satar, Mike Zheng Shou, Qianli Xu
AAAI 2025 Full Paper
[arXiv] [Dataset Link] [Github]

PhD Research Topic 2: Debiased Text-to-Video Retrieval

Structural Causal Model
Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo-Hwee Lim
BMVC 2023 Full Paper, (Poster presentation)
[arXiv] [YouTube Ppt] [Project Page]

An Overview of Challenges in Egocentric Text-Video Retrieval
Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo-Hwee Lim
CVPR Workshop 2023, Joint Ego4D/EPIC Workshop (Oral presentation)
[Extended Abstract] [YouTube Ppt]

PhD Research Topic 1: Semantic Text-to-Video Retrieval

(✅ Joint 3rd Place Award) Exploiting Semantic Role Contextualized Video Features
for Multi-Instance Text-Video Retrieval
Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo-Hwee Lim
CVPR Workshop 2022, Epic-Kitchens-100 MIR Challenge under Joint Ego4D/EPIC Workshop
[Technical Report] [(pseudo)Code]

Architecture

RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval
Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo-Hwee Lim
[arXiv 2022 Preprint] [(pseudo)Code]

Overview of our model on text-to-video retrieval

Semantic Role Aware Correlation Transformer for Text to Video Retrieval
Burak Satar, Hongyuan Zhu, Xavier Bresson, Joo-Hwee Lim
ICIP 2021 Full Paper (Oral presentation) and ICCV Workshop 2021 (Oral presentation)
[arXiv] [(pseudo)Code] [YouTube Ppt]

Research during Master’s Study

Detection and classification method
Deep Learning Based Vehicle Make-Model Classification
Burak Satar, Ahmet Emir Dirik
ICANN 2018 Full Paper (Oral presentation)
[arXiv] [Code]

Burak Satar