For those going to @iccv.bsky.social, welcome to our RANSAC tutorial on October 2025 with - Daniel Barath - @ericbrachmann.bsky.social - Viktor Larsson - Jiri Matas - and me danini.github.io/ransac-2025-... #ICCV2025

The Visual Recognition Group at CTU in Prague organizes the 50th Pattern Recognition and Computer Vision Colloquium with Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann. On Thursday Oct 9, 11:00-17:00. cmp.felk.cvut.cz/colloquium/

Congratulations to everyone who got their @neuripsconf.bsky.social papers accepted 🎉🎉🎉 At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!

correlation does not equal causality

Interesting graphs from csconferences.org Trying to predict the inflection point of the sigmoid.

Crash test your foundational models for object recognition at its finest granularity. Here are the updated results on our instance-level image retrieval benchmark (ILIAS-CVPR'25). DINOv3 and Perception Encoder (PE) are included, with DINOv3 being the new SoA! Oh, but no, look at this...

Department of War. Now with 100% less euphemism. A moment of clarity for research on DoD grants. For even more clarity, check @davidthewid.bsky.social work

The Colloquium in Pattern Recognition and Computer Vision of the Visual Recognition Group at CTU in Prague has a long tradition dating back to 1998. The list of all speakers is available docs.google.com/spreadsheets.... Enjoy! The 50th edition is coming soon cmp.felk.cvut.cz/colloquium/

Hi friends! I made a computer vision feed that was missing on Bluesky. You can find it here: bsky.app/profile/did:.... Pin it to your profile if you like it. 😉 It filters relevant posts based on regular expressions. But to make sure that your post is included in the feed, add the #skyvision tag.

The hidden flaws in your favorite foundation model: We've uncovered how subtle image metadata (JPEG params, camera type, etc.) systematically biases visual representations and consequently affect the object recognition ability. To be presented at #ICCV2025 as a highlight paper.

🚨 Deadline Extension Instance-Level Recognition and Generation (ILR+G) Workshop at ICCV2025 @iccv.bsky.social 📅 new deadline: June 26, 2025 (23:59 AoE) 📄 paper submission: cmt3.research.microsoft.com/ILRnG2025 🌐 ILR+G website: ilr-workshop.github.io/ICCVW2025/ #ICCV2025 #ComputerVision #AI

When were #CVPR2025 papers available on arXiv? 👇

Unfortunately we have to wait at least until 2032 for CVPR to be outside of USA.

Are you at @cvprconference.bsky.social? Come by our poster! 📅 Sat 14/6, 10:30-12:30 📍 Poster #395, ExHall D

Are you at @cvprconference.bsky.social #CVPR2025 ? Come and check out LPOSS. We show how can graph-based label propagation be used to improve weak, patch-level predictions from VLMs for open-vocabulary semantic segmentation. 📅 June 13, 2025, 16:00 – 18:00 CDT 📍 Location: ExHall D, Poster #421

VRG is presenting 8 papers at #CVPR2025. You can find me and collaborators at the following 4 posters: Fri 10:30-12:30 A Dataset for Semantic Segmentation in the Presence of Unknowns Fri 16:00-18:00 LOCORE: Image Re-ranking with Long-Context Sequence Modeling

solidarity is not a crime, genocide is

Call for Papers update - ILR+G workshop @iccv.bsky.social We will now feature a single submission track with new submission dates. 📅 New submission deadline: June 21, 2025 🔗 Submit here: cmt3.research.microsoft.com/ILRnG2025 🌐 More details: ilr-workshop.github.io/ICCVW2025/ #ICCV2025

is there any human that does not type "ration" 50% of the times they intend to type "ratio"?

VRG from CTU in Prague has 9 of its members listed as outstanding reviewers. Congratulations to @gkordo.bsky.social, @billpsomas.bsky.social , @stojnicv.xyz , Pavel Suma, @ducha-aiki.bsky.social , Miroslav Purkrábek, Tomas Vojir, and Yaqing Ding.

we did a systematic analysis of over 40k CV & CV research based patents and found that the field is not advancing cancer research or anything useful but rather powering surveillance arxiv.org/abs/2309.15084

For years, we have tried to bring together researchers dedicated to the finest granularity of class definition—instance-level analysis. Now in its 7th edition, the event covers both recognition and generation tasks. Check out the call for papers

🚀 Calling all Greeks in AI 🇬🇷🤖 Are you researching Computer Vision, NLP, or anything AI-related — and have Greek roots or connections? Join the Greeks in AI Starter Pack to connect and collaborate. 🧵 Follow here: go.bsky.app/Rakqp7M 💬 Reply or DM if you’d like to be added or suggest others!

"Interpolation in a sufficiently high-dimensional space is indistinguishable from magic" A. Efros at Inria Grenoble on generative models as data storage (somewhat paraphrasing A.C. Clark)

#PAISS2025 summer school in the Alps with amazing speakers, including @dimadamen.bsky.social @arthurgretton.bsky.social @science4all.org @yann-lecun.bsky.social @gabrielpeyre.bsky.social @claireve.bsky.social and many more ▶️ Apply here: paiss.inria.fr/apply-2025/

🚀 Never miss a beat in science again! 📬 Scholar Inbox is your personal assistant for staying up to date with your literature. It includes: visual summaries, collections, search and a conference planner. Check out our white paper: arxiv.org/abs/2504.08385 #OpenScience #AI #RecommenderSystems

Just assembled a slide about local feature training time/dataset size. Anything wrong/missing?

The Visual Recognition Group at CTU in Prague organizes the 49th Pattern Recognition and Computer Vision Colloquium with D. Karatzas, M. Masana, T. Tommasi, P. Mettes @pascalmettes.bsky.social , E. Brachmann @ericbrachmann.bsky.social and V. Stojnic @stojnicv.xyz cmp.felk.cvut.cz/colloquium/#...

Exciting News! Shoutout to @hf.co 🤗 for hosting ILIAS in its full scale! You can now easily download it via: huggingface.co/datasets/vrg... This marks a milestone in i2i and t2i retrieval, paving the way for significant advancements in the field. Huge thanks to @hf.co team for their support!

We are bridging the new (VLMs for open-voc. segmentation) with the old (optimization with unary and binary constraints - a common regularization in classical semantic segmentation). This is performed efficiently via label propagation over an appropriate graph. To be presented at #CVPR2025

A sweet taste of CVPR in Paris. What a great initiative. I wonder if flying from Prague qualifies as sustainable enough.

🚀 Paper Release! 🚀 Curious about image retrieval and contrastive learning? We present: 📄 "All You Need to Know About Training Image Retrieval Models" 🔍 The most comprehensive retrieval benchmark—thousands of experiments across 4 datasets, dozens of losses, batch sizes, LRs, data labeling, and more!

Explaining Human Preferences via Metrics for Structured 3D Reconstruction @jacklangerman.bsky.social Denys Rozumnyi, Yuzhong Huang, @ducha-aiki.bsky.social tl;dr: we asked 3D modelers to rank wireframe reconstructions & compared it to ranking by metrics. Observations🧵 1/ arxiv.org/abs/2503.08208

We have extended the deadline for paper submission for Image Matching Workshop. Anything image matching or 3D reconstruction related is welcomed Now it is March 17 @cvprconference.bsky.social #CVPR2025 image-matching-workshop.github.io

Not sure what to do with all the free time after ICCV deadline?🌴 Are you tired of all the self-driving datasets? Or you just like 🍄? Submit to our FungiCLEF25@CVPR challenge! Just launched, 2 months to go 🏃‍♂️. The task is few-shot recognition of 🍄 observations. More at www.kaggle.com/competitions...

The WACV'25 work of @nikos-efth.bsky.social is on WACV daily - computer vision news.

📢 ‼️ 📢 ‼️ New blog post alert ‼️ 📢 ‼️ 📢 We are finally publishing our blog post: Flaws of ImageNet, Computer Vision's Favorite Dataset. Not only does it have many cute animals 🦦 🐈 🐋 , it also provides an overview of known issues, as well as new insights. klarajanouskova.github.io/ImageNet/

You can find easy cases in older datasets, this one mostly consists of hard examples. We created a new test dataset for instance-level retrieval to better reflect real world challenges. How does your new representation or retrieval model perform on ILIAS with 100m distractors? Accepted at CVPR'25

We created a new channel with daily new vision and graphics papers trending (liked/read) on www.scholar-inbox.com. This is the bsky equivalent of AK on X! Follow now, and never miss a beat again: bsky.app/profile/si-c...

Asking ChatGPT to name a seminal paper on a specific topic. The answer is a paper withdrawn from arxiv 🤯

🚀Exciting news🚀 I’ve been awarded the Marie Skłodowska-Curie Postdoctoral Fellowship (#MCSA-PF) 2024 with 98/100!🎉 🥟My project, RAVIOLI, hosted at CTU in Prague, under @gtolias.bsky.social, integrates retrieval-augmented predictions into vision-language models for open-vocabulary segmentation.

My heart ached when I was reminded that Aaron Swartz was prosecuted for trying to make academic knowledge more accessible to the public. Meta, meanwhile, is doing it for their own bottom line. I'm going to guess that no one at Meta will be looking at spending 35 years in jail for this.

For PhD and MSc students interested in a research visit to Prague/VRG in 2025: we're open to hosting short-term collaborations or internships on a range of computer vision topics. If this sounds exciting, reach out by e-mail! We'd love to discuss potential projects. Some examples 🧵 #Internship #CV

Does anyone believe that CVPR should always be hosted in the USA? If so, what are the reasons for this?

Why does everyone get so excited about performance on some benchmarks when we don't know what the training data is? How do you know that they're not testing on the training set? How do you reject papers that don't tell you the splits but get so excited by these PR announcements?

history

Financial Assistance applications are now open! If you face financial barriers to attending ICLR 2025, we encourage you to apply. The program offers prepay and reimbursement options. Applications are due March 2nd with decisions announced March 9th. iclr.cc/Conferences/...

frustration: a test image needs to be resampled to square size before processing with ViT. double frustration: more reasonable processing that preserves the aspect ratio performs worse.

A late introduction: I am an Associate Professor at CTU in Prague and a computer vision researcher at the Visual Recognition Group (VRG - vrg.fel.cvut.cz). VRG consists of about 40 members and I am leading a small team within VRG. I am made in Greece and exported to France + Czech Republic 🧵⬇️

Image matching and ChatGPT - new post in the wide baseline stereo blog. tl;dr: it is good, even feels like human, but not perfect. ducha-aiki.github.io/wide-baselin...