About me

I am a final year PhD candidate at CCDS, NTU, Singapore, under the SINGA scholarship by I2R, A*STAR. My PhD work is on Towards Semantic, Debiased and Moment Video Retrieval with Multi-modal Features under Prof. Joo Hwee Lim, Dr Hongyuan Zhu and Prof. Hanwang Zhang. During my PhD, I visited the University of Bristol, UK, under Prof. Michael Wray in Dima Damen’s group. I did my MSc under Prof. Ahmet Emir Dirik on vehicle detection. My working experiences vary from a start-up in Istanbul to Turkish Airlines Technology and an internship at the University of Valencia. I also advised two award-winning start-ups based in London and Istanbul. I am considering the opportunities for the next step.

Publications

#PhD Research 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 TBA

VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting
M Furkan Ilaslan, Ali Koksal, Kevin Qinghong Lin, Burak Satar, Mike Zheng Shou, Qianli Xu TBA

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

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

An Overview of Challenges in Egocentric Text-Video Retrieval
Burak Satar, Zhu Hongyuan, Hanwang Zhang, Joo-Hwee Lim
CVPR Workshop 2023, Joint Ego4d/EPIC Workshop (Oral presentation)
[Extended Abstract] [YouTube Ppt]

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

(✅ 3rd Place Award) Exploiting Semantic Role Contextualized Video Features
for Multi-Instance Video Retrieval
Burak Satar, Zhu Hongyuan, 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, Zhu Hongyuan, 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, Zhu Hongyuan, Xavier Bresson, Joo-Hwee Lim
ICIP 2021 Full Paper (Oral presentation) and ICCV Workshop 2021 (Oral presentation)
[arXiv] [(pseudo)Code] [YouTube Ppt]

#MSc Research

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

————————————————————————————————–

Previous News

05/2024: Volunteered at ACM Web Conference.
10/2023: Visited MaVi Research Group, University of Bristol, for three months under the supervision of Dr Michael Wray on video corpus moment retrieval.
05/2023: A poster presentation at Singapore Vision Day at NUS.
07/2022: Attended CIFAR DLRL Summer School.
06/2022: 3rd Place Award in EPIC-Kitchens Multi-Instance Retrieval Challenge, CVPR.
06/2022: Became a finalist in the Three Minute Thesis (3MT) @ NTU, representing CCDS.
01/2022: Successfully passed my Qualification Exam (QE).
12/2021: Volunteered in NeurIPS.
07/2021: Attended PAISS AI Summer School, and presented a poster.
2020: Started my PhD in the College of Computing and Data Science (CCDS), NTU.
08/2018: Successfully defended my MSc thesis.
06/2018: Got student travel award by European Neural Network Society to attend ICANN.

Burak Satar