📢 Check out our work on Snuffy: Efficient Whole Slide Image Classifier 💉🔬, where we addressed computational efficiency, accuracy, and robustness in processing Whole Slide Pathology Images, presented at #ECCV2024! 🔍 Abstract: WSI classification faces computational and

European Conference on Computer Vision #ECCV2026 our third keynote speaker in our non-Euclidean workshop Carl Vondrick

Quite cool video (Carl Vondrick)

What novel ideas can we expect in the exploration phase of #computer_vision? Join us tomorrow morning at European Conference on Computer Vision #ECCV2026 2024 MELEX workshop on More Exploration, Less Exploitation! With an amazing set of speakers: Dima Damen @ICVSS2025, Vassia Simaiaki, Bjorn Ommer, and Bill Freeman!

Stop by the OoD-CV workshop tomorrow to help us understand what "out of distribution generalisation" means in the era of web-scale pretraining. Monday, 9am-1pm, Brown 1. Sad I can't attend in person!

Why do we have issues in our community?

Bill Freeman talking now!

🌟 Workshop Starting at 2 PM! 🌟 Join #WiCV at European Conference on Computer Vision #ECCV2026 in the Panorama Lounge (6th floor). Take the elevator at the end of the workshop hall (above the lunch area) to reach us! Program: tinyurl.com/3m6wz5rk See you soon! 🇮🇹 #ECCV2024 #Mentorship #Networking #WomenInCV

If joining European Conference on Computer Vision #ECCV2026, don’t miss WiCV happening now! First keynote was a great talk by Dima Damen 🤩

The #MCML offers fully funded #PhD positions in any field of research within the domains of machine learning! The Online Application System is open from 15 October 2024 until 14 November 2024! The position starts on 1 July 2025 Further information: mcml.ai/opportunities/…

🚀 Excited to present our work on Self-Expertise at #ECCV2024 in Milan! Join us at poster #89 on Friday, Oct 4 at 10:30 AM to see how self-expertise outperforms self-supervision in tackling unknown data in open-world settings! 🌍 #SelfSupervision #GeneralizedCategoryDiscovery

Next: Stella X. Yu, a distinguished professor in EECS department at the University of Michigan. She is talking about Unscripted Grounded Visual Learning.

Now we have an exciting panel session with Hedvig Kjellström, and our keynote speakers Dima Damen, Fatma Guney, Stella Yu! „What was a pivotal moment that shaped your career and approach?“

Google Photos reminded me that I was last in Italy 12 years ago, for ECCV 2012, Florence. My paper's code was written in Matlab and ran on my MacBook. Some guy named Alex won the ImageNet workshop using a neural network and a GPU. The keynote fit into a regular-sized room.

It was a great opportunity to join Doctoral Consortium at #ECCV2024, thanks for organising!

Stop by today and discuss our European Conference on Computer Vision #ECCV2026 paper (SelEx) with me, Hazel Doughty, and Cees Snoek! 🎉 We present self-expertise—an alternative to self-supervision for learning from unlabelled data with fine-grained distinctions and unknown categories. 📍 Poster #89 🕥 10:30 AM

Don't treat the language of biology as natural language! Biology speaks in hierarchical patterns that natural language models don't fully capture. Meet HELM: a novel approach to train LMs that aligns with the intrinsic hierarchy of mRNA sequences. arxiv.org/abs/2410.12459 1/5

Parameterized Transforms 🚀 Here is a new tool that provides a modular and extendable implementation of torchvision-based image augmentations that provides access to their parameterization. [1/5]

Flow Matching (FM) is one of the hottest ideas in generative AI - and it’s everywhere at #ICML2025. But what is it? And why is it so elegant? 🤔 This thread is an animated, intuitive intro into (Variational) Flow Matching - no dense math required. Let's dive in! 🧵👇