🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

How to get unstuck? "It doesn't work." 🤷‍♀️🤷‍♂️ In most research projects, ~99% of the time your experiments DO NOT work. What should we do to get ourselves unstuck? 🤔 Sharing some tips I found useful. 🧵

#ECCV2024 is encouraging potential reviewers and area chairs to self-nominate. If you know of someone who would be a great reviewer or AC, encourage them to self-nominate by filling the form. Area Chair form: forms.gle/VkgbRU573wVLtg… Reviewer form: forms.gle/cuY6oiBv8JTjvR…

Very happy to be in such a brilliant team 🪩

Thank you Jiri Matas & @giotolias for the invitation! It was a great day with very insightful talks & discussions with VRG students/researchers. Prague is still just as welcoming even under the snow ❄️

Victor Letzelter Mathieu Fontaine Mickael Chen POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images by Antonín Vobecký Oriane Siméoni D.Hurych Spyros Gidaris Andrei Bursuc P.Pérez, J.Sivic tl;dr: open-vocab 3D semantic occupancy maps from multi-cam inputs w/ tri-modal self-supervised learning #neurips2023 vobecant.github.io/POP3D/

🍾POP-3D NeurIPS Conference If you want to discuss open-vocabulary 3D occupancy prediction from images only, reach out to Antonín Vobecký who will present the poster on Thursday: Poster #115 @🗺️Great Hall & Hall B1+B2 (level 1) ⏲️Th. 14 Dec. 10:45 a.m. CST — 12:45 p.m. CST

We are presenting our poster on links between GANs and Diffusion at Neurips. Don't be scared by the formalism, ⁦Jean-Yves Franceschi⁩ is awesome and will explain everything intuitively!

We strengthen MaskCLIP features w. a simple weighted aggregation strategy w. weights learnt using self-sup. DINO🦖 ➡️patch-level CLIP abilities 🧪SoTA in open-voc sem. seg. 🚀pass in CLIP & new conv 3x3 Check out CLIP-DINOiser 📜 arxiv.org/abs/2312.12359 🖥️github.com/wysoczanska/cl…

Are motion forecasting models ready for deployment? 🤔 In this new #ICRA2024 paper, we reveal several challenges that forecasting models face (and show they are not ready 🤫) 📜: arxiv.org/abs/2306.09281 💻: github.com/valeoai/MFEval 🧵🔽

Last December Antonín Vobecký presented our POP-3D model which generates 3D occupancy with open-vocabulary representation from images only, trained w/o annotation. We also proposed a new small benchmark for open-voc. 3D-occupancy w/ natural language queries. More details below ⬇️

How to to obtain high-quality 3D representation from 2D self-supervised backbones? #CVPR2024 Check-out ScaLR which narrows down from 30 to 10pts the difference to fully-supervised models with our homemade WaffleIron model github.com/valeoai/Waffle…. Both works led by Gilles Puy👏.

Super excited to be ✈️#CVPR2025 next week to present our recent works. On the menu: images, point clouds, and language in generative, distillation, self-supervised, sparse, forecasting, generalization, and unsupervised settings... Find out more 👇 and come meet us at #CVPR2024

Excited to be at Deep Learning Indaba in Dakar and to take part tomorrow in the 3rd Weakly Sup. Computer Vision workshop organized by R. de Charette & co. 💬 I will give a talk about one of my favorite subjects: using the power of self-sup. features for object localization. Come say hi!

The link to the workshop: wscv-indaba.github.io/2024 which will start at 8:30 🕗

Our, now annual, Weakly Supervised Computer Vision workshop Deep Learning Indaba turned out great! Thanks to the participants, amazing speakers and contributors, dream team organizers led by Raoul de Charette. Really happy to be part of this. See you next time! wscv-indaba.github.io/2024

Poster #72 #ECCV2024 is already up and running with Monika Wysoczańska Michaël Ramamonjisoa Andrei Bursuc. Come by if you want to talk about open-vocabulary semantic segmentation at low cost!

They did the pointer meme!!

🔥Our team working on unsupervised deep learning is looking for a PhD intern for 2025. We are looking for deep learning / machine learning PhD students! If you are interested, you can apply here: metacareers.com/jobs/843046771… Don't hesitate to reach out!

Stop by the CVPR poster for more eye-candy results. We will be there with Dahyun Kang, Oriane Siméoni, and Federico Baldassarre. Happy to answer any questions! [7/N] 📅 Sunday, June 15 🕥 10:30 - 12:30 📍 Poster 370

Tomorrow morning we will present dino.txt and show how to efficiently align text to frozen DINOv2 features. And no need to choose between image- and patch-level alignement, we show a simple strategy to do both at once! Come by for discussion, poster 370