About me
I am a final year PhD candidate at NTU, Singapore, under the SINGA scholarship by A*STAR. My PhD work is on Towards Semantic, Debiased and Moment Video Retrieval with Multi-modal Features under Prof. Joo Hwee Lim and Dr Hongyuan Zhu from I2R, A*STAR and Prof. Hanwang Zhang from SCSE, NTU.
During my PhD, I was also a visiting researcher at 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. I have various working experiences, from a start-up in Istanbul to the industry (Turkish Airlines Technology) and a university internship during my MSc (Univeristy of Valencia). I also advised two award-winning start-ups.
Recent News
- 07/2024: Expected date to submit the PhD Thesis.
- 2024: Our recent work, Enhancing Video Corpus Moment Retrieval in Long Ego-centric Videos with LLM and Audio Fusion, is under review.
- 10/2023: Visited MaVi Research Group, University of Bristol, for three months under the supervision of Dr Michael Wray on video corpus moment retrieval.
- 08/2023: A recent work is accepted to BMVC 2023.
Publications
Enhancing 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 review
————————————————————————————————–
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
Under review
————————————————————————————————–
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]
————————————————————————————————–
Exploiting Semantic Role Contextualized Video Features
for Multi-Instance Video Retrieval (3rd Place Award)
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]
————————————————————————————————–
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]
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]
————————————————————————————————–
Deep Learning Based Vehicle Make-Model Classification
Burak Satar, Ahmet Emir Dirik
ICANN 2018 Full Paper (Oral presentation)
[arXiv] [Code]
Previous News
- 06/2023: An extended abstract is accepted to Ego4d/EPIC Workshop at CVPR 2023.
- 05/2023: A poster presentation at Singapore Vision Day at NUS.
- 07/2022: Attended CIFAR DLRL Summer School.
- 06/2022: Got 3rd Place Award in EPIC-Kitchens Multi-Instance Retrieval Challenge, CVPR.
- 06/2022: Became a finalist in the Three Minute Thesis (3MT) @ NTU, representing SCSE.
- 01/2022: Successfully passed my Qualification Exam (QE).
- 12/2021: Volunteered in NeurIPS.
- 09/2021: Our first paper is also accepted by an ICCV Workshop.
- 07/2021: Attended PAISS AI Summer School, and presented a poster.
- 05/2021: One paper accepted by ICIP.
- 01/2020: Started to do PhD in School of Computer Science and Engineering, NTU.
- 08/2018: Successfully defended my MSc thesis.
- 06/2018: One paper accepted by ICANN, with student travel award.