Mariya Hendriksen

I'm a current research intern with the Game Intelligence team at Microsoft Research Cambridge, and a final-year Ph.D. student at the University of Amsterdam, where I work on Multimodal Machine Learning in the context of Information Retrieval. I am interested in multimodal representation learning, cross-modal retrieval, and post-training.

I am supervised by Maarten de Rijke and Paul Groth, and mentored by Andrew Yates.

I hold a Master’s in Artificial Intelligence (KU Leuven) and a Bachelor's in Computational Linguistics (Novosibirsk State University). During my studies, I had the opportunity to intern at Google's Gemini team, Bloomberg AI, Amazon Alexa, LIIR at KU Leuven, and ETH Zurich.

I was born in Ukraine and grew up in the Far North of Siberia, Russia. My background motivated my commitment to building diverse and inclusive workspaces. As such, I am a mentor within the Inclusive AI initiative.

Feel free to reach out for research discussions, collaborations or just to have a chat!

Email / Scholar / Twitter / Github

News

Publications

(Jul 2024) Paper 'Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning.' accepted at TMLR.
(Dec 2023) Paper 'Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control' accepted at ECIR 2024.
(Nov 2023) Published the paper 'Multimodal Learned Sparse Retrieval for Image Suggestion' as part of our team's participation in TREC 2023 AToMiC.
(Dec 2022) Our paper 'Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study' accepted at ECIR 2023.
(Jul 2022) Published the paper 'Unimodal vs. Multimodal Siamese Networks for Outfit Completion' as part of the Fashion Outfits Challenge at SIGIR 2022 Workshop on eCommerce.
(Dec 2021) The work 'Multimodal Retrieval in E-commerce: from Categories to Images, Text, and Back' got accepted at the ECIR 2022 Doctoral Consortium.
(Nov 2021) Our paper about CLIP for zero-shot image retrieval was accepted to the main track at ECIR 2022.
(Jun 2020) Our paper 'Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers' accepted at SIGIR 2020 Workshop on eCommerce.

Milestones & Activities

(Sep 2024) Started a research internship at Microsfot Research Cambridge with the Game Intelligence team.
(Apr 2024) Started a research internship at Google Zurich with the Gemini team.
(Mar 2024) Attended the ELLIS Winter School on Foundation Models.
(Jul 2023) Started a research internship at Bloomberg AI in London.
(Nov 2022) Started a research internship at Alexa, Amazon Science in London.
(Jun 2022) Gave a talk on ‘Extending CLIP for Category-to-Image Retrieval in E-commerce’ at Amazon Luxembourg.
(Apr 2020) Attended MLSS 2020.

Research

	Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning. Maurits Bleeker, Mariya Hendriksen, Andrew Yates, Maarten de Rijke (co-first author) TMLR, 2024 arXiv / bibtex / Github We propose a framework to examine the shortcut learning problem in the context of Vision-Language contrastive representation learning with multiple captions per image. We show how this problem can be partially mitigated using a form of text reconstruction and implicit feature modification.
	Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control. Thong Nguyen, Mariya Hendriksen, Andrew Yates, Maarten de Rijke (co-first author) ECIR, 2024 arXiv / Github We propose a framework for multimodal learned sparse retrieval.
	Scene-Centric vs. Object-Centric Image-Text Cross-Modal Retrieval: A Reproducibility Study. Mariya Hendriksen, Svitlana Vakulenko, Ernst Kuiper, Maarten de Rijke ECIR, 2023 arXiv / Github
	Extending CLIP for Category-to-Image Retrieval in E-commerce . Mariya Hendriksen, Maurits Bleeker, Svitlana Vakulenko, Nanne van Noord, Maarten de Rijke ECIR, 2022 arXiv / Github
	Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers . Mariya Hendriksen, Ernst Kuiper, Pim Nauts, Sebastian Schelter, Maarten de Rijke SIGIR eCom, 2020 arXiv

Thanks to Jon Barron for the template :)