About me

I am the research lead and applied researcher at V7 Labs, focusing on innovative projects in advanced AI, including generative models. Before this, I worked as a senior research scientist at Naver Labs Europe.

My academic journey includes a Ph.D. in Computer Vision from the Universitat Autonoma de Barcelona, under the supervision of Ernest Valveny, and a postdoc at Xerox under the supervision of Florent Perronnin. My research interests lie in the fields of computer vision and machine learning, currently with a focus on representation learning, multi-modal generative models, and self-supervised problems.

Outside of work, I enjoy videogames, cinema, and surfing.

For more information on my professional work, you can view my publications on my Google Scholar profile or check out some of my projects on my GitHub page.

Selected publications

• Flexible Visual Prompts for In-Context Learning in Computer Vision. Foster T., Croitoru I., Dorfman R., Edlund C., Varsavsky T., Almazán J., R0-FoMo workshop NeurIPS 2023 [Paper] [Post]
• TLDR: Twin Learning for Dimensionality Reduction. Kalantidis Y., Lassance C., Almazán J., Larlus D., TMLR 2022. [Paper] [Github]
• Granularity-aware Adaptation for Image Retrieval over Multiple Tasks. Almazán J., Ko B., Gu G., Larlus D., Kalantidis Y., ECCV 2022. [Paper] [Project Page]
• Learning with Average Precision: Training Image Retrieval with a Listwise Loss. Revaud J., Almazán J., Rezende R., de Souza C., ICCV 2019 [Paper] [Github]
• End-to-end Learning of Deep Visual Representations for Image Retrieval. Gordo A., Almazán J., Revaud J., Larlus D., IJCV 2017 [Paper] [Github]