I am a PhD candidate in Computer Vision at the University of Amsterdam, supervised by Marcel Worring. My main area of interest is instance retrieval, learning with noisy labels, and vision + language tasks. I am also highly interested in AI for Creativity, more specifically for dance and I am open to collaborations in this research direction.
My background is in Computer Science with a specialization in Cyber Security (MSc 2014, Eindhoven University of Technology) and Mathematics (BSc 2012, Utrecht University). Besides, I have a background in Theater and Dance Studies (BA 2012, Utrecht University).
Sarah Ibrahimi, Arnaud Sors, Rafael Sampaio de Rezende, Stéphane Clinchant Learning with Label Noise for Image Retrieval by Selecting Interactions, (WACV 2022) [Link].
Sarah Ibrahimi, Nanne van Noord, Tim Alpherts, Marcel Worring Inside Out Visual Place Recognition, (BMVC 2021) [Link].
Nikolaos-Antonios Ypsilantis, Noa Garcia, Guangxing Han, Sarah Ibrahimi, Nanne van Noord, Giorgos Tolias, Instance-level Recognition for Artworks: The Met Dataset, (NeurIPS 2021, Datasets and Benchmarks Track) [Link].
Sarah Ibrahimi Composition, Performance and Evaluation: A Dance Education Framework for AI Systems, (ICCC 2021) [Link].
Nils Hulzebosch, Sarah Ibrahimi, Marcel Worring, Detecting CNN-Generated Facial Images in Real-World Scenarios, (CVPRW 2020) [PDF].
David Stap, Maurits Bleeker, Sarah Ibrahimi, Maartje ter Hoeve, Conditional Image Generation and Manipulation for User-Specified Content, (CVPRW 2020) [PDF].
Sarah Ibrahimi, Nanne van Noord, Zeno Geradts, Marcel Worring, Deep Metric Learning for Cross-Domain Fashion Instance Retrieval, (ICCVW 2019) [PDF].
Sarah Ibrahimi, Shuo Chen, Devanshu Arya, Arthur Câmara, Yunlu Chen, Tanja Crijns, Maurits van der Goes, Thomas Mensink, Emiel van Miltenburg, Daan Odijk, William Thong, Jiaojiao Zhao, Pascal Mettes. Interactive Exploration of Journalistic Video Footage through Multimodal Semantic Matching, (ACM Multimedia 2019) [Link].
Sarah Ibrahimi, Boris Škorić, Jan-Jaap Oosterwijk, Riding the saddle point: asymptotics of the capacity-achieving simple decoder for bias-based traitor tracing, EURASIP Journal on Information Security 2014, 2014:12 [Link].