Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️ bit.ly/433YuBI

Announced by Mark Zuckerberg this morning — today we're releasing DINOv2, the first method for training computer vision models that uses self-supervised learning to achieve results matching or exceeding industry standards. More on this new work ➡️ bit.ly/3GQnIKf

Join us today (May 3) at 11 am (CST) in room 115 at The Web Conference, happening now in Austin, we'll present our work "Mapping Flood Exposure, Damage, and Population Needs Using Remote and Social Sensing: A Case Study of 2022 Pakistan Floods". #WWW Paper: dl.acm.org/doi/10.1145/35…

POMELO is a method that helps improve the quality of existing population data by employing a weakly supervised regression system. In my latest blog post, I delve into the technical details of our "Nature, Scientific Reports" publication. (5min read😉) medium.com/@nandometzger/…

I had the pleasure of presenting our work on “integrating remote sensing and social sensing for disaster response” at the GIS Technology Day event, which received the best GIS presentation award! 🎉 Big congrats to the AIDR team! 👏 QCRI #GISDAY2023 #GISQatar2023

Annual CVPR-TR meetup. Lovely to see old friends and to meet new ones! Gelen herkese tesekkurler! 🫶 #CVPR2023 #CVPRTR @cvpr

I recently had the pleasure of giving an online lecture on using AI and non-traditional data for social good applications. It was great to see so many bright young minds come together in the 4th Annual Nepal AI School organized by Naamii Nepal. Thanks for the opportunity!

Thrilled to see SDGs Today feature our Türkiye earthquake work, a collaboration with UN Development Surge Data Hub team to map missing people, damages, and shelter requests at the district level. Work done at QCRI of جامعة حمد بن خليفة & Qatar Foundation Ahmed Elmagarmid ferda ofli storymaps.arcgis.com/collections/6f…

Reflecting on an incredible collaboration between QCRI and UN DPPA, the fourth 'E-Analytics and Innovation Lab' held in Doha from Jan 22-25 was an exciting journey into technological advancements for global peace efforts Muhammad Imran

It was a pleasure hosting our friends from UN Political and Peacebuilding Affairs at QCRI for the fourth edition of the E-Analytics training course. 35+ UN staff participated in the 4-day event. United Nations Martin Waehlisch Ahmed Elmagarmid ferda ofli Alya Ahmed Saif Al Thani جامعة حمد بن خليفة Qatar Foundation

Today I had the pleasure of participating in the STEM Career Exploration Day at the American School of Doha. Glad to see high-schoolers so passionate about careers in science & technology. Thanks for the invitation and opportunity! American School Doha

Exciting news! Our paper on Flood Insights won the Deployed Application Award at the AAAI-IAAI conference in Vancouver! We fuse remote & social sensing and geospatial data for impact assessments during floods. Kudos to the amazing team: Zainab, Umair, Aya, Rizwan, ferda ofli

Hamad Bin Khalifa University’s Qatar Computing Research Institute #QCRI, together with the Innovation Cell of the Policy and Mediation Division at the United Nations Department of Political and Peacebuilding Affairs #UNDPPA, marked six years of collaboration in pioneering new

📝 New from FAIR: An Introduction to Vision-Language Modeling. Vision-language models (VLMs) are an area of research that holds a lot of potential to change our interactions with technology, however there are many challenges in building these types of models. Together with a set

Getting ready to serve as a judge at the CMUQ LifeLines Hackathon’25: “Hack to save lives.” Looking forward to the presentations. lifelinescmuq.org

If detecting vehicles in high-resolution satellite images is your thing, then this research is for you! nature.com/articles/s4159…

Happy to be recognized as an Outstanding Reviewer for #CVPR2025. Grateful for the opportunity to contribute, and I'll continue doing my best to serve the community at the highest level. #AcademicLife

One of the biggest bottlenecks in deploying visual AI and computer vision is annotation, which can be both costly and time-consuming. Today, we’re introducing Verified Auto Labeling, a new approach to AI-assisted annotation that achieves up to 95% of human-level performance while