iiinova — where your digital self keeps evolving

Reposted by Vladan Stojnić

Dominik Schnaus @schnaus.bsky.social · 5h

DINOv2 has never seen a caption, and Qwen3 has never seen an image. We still aligned their embedding spaces without a single image-caption pair. It even works when the images and the captions come from different datasets. Project page: dominik-schnaus.github.io/unpaired-rosetta ⬇️

16415

Reposted by Vladan Stojnić

Klara Janouskova @klara-cz.bsky.social · 06/10/2026

A spotlight at NeurIPS is awesome and I am super proud of the guys for pulling this off! But only one of the authors being able to attend the conference because registrations sold out and there is no priority for other authors is a bit... anticlimactic, after so much effort from everyone involved.

1114

Vladan Stojnić @stojnicv.xyz · 06/09/2026

Workshops 🗓️ September 8, 2026 🕒 15:40 - 16:10: @gtolias.bsky.social will be at the 2nd Workshop on Benchmarking Evidence‑Aligned Multimodal Reasoning. Main Conference Poster 🗓️ September 11, 2026 🕒 10:30 - 12:30 📍 ExHall #34 @gkordo.bsky.social @noagarciad.bsky.social @gtolias.bsky.social

031

Vladan Stojnić @stojnicv.xyz · 06/09/2026

Workshops 🗓️ September 8, 2026 🕒 15:00 - 16:00: I will be at the E.T.: Empirical Theory in Representation Learning workshop poster session. 🕒 15:30 - 16:00: @noagarciad.bsky.social will be at the 5th Workshop on Uncertainty Quantification for Computer Vision.

130

Vladan Stojnić @stojnicv.xyz · 06/09/2026

Attending #ECCV2026? Want to know why your favorite vision models learn to encode camera acquisition and processing traces? Come meet our team! 👇 @eccv.bsky.social

2197

Reposted by Vladan Stojnić

Giorgos Tolias @gtolias.bsky.social · 04/09/2026

📢 The Instance-Level Recognition and Generation (ILR+G) Workshop is happening at ECCV'26! 🗓️ Sep 8, 8:30am–12:30pm (CEST) 📍 Room 306 A If you work on computer vision at its finest class-wise granularity, i.e. recognizing, localizing, and synthesizing particular objects, come join us.

162

Reposted by Vladan Stojnić

Giorgos Tolias @gtolias.bsky.social · 04/09/2026

CV4GOOD — Computer Vision for Humanitarian Action ECCV 2026 workshop, first edition. Malmö, Tuesday 8 September, 14:00 to 18:00. Room Malmömässan D2 If you work on computer vision and care about where it can do good, come join us. cv4good.thegoodailab.org @eccv.bsky.social #ECCV2026

cv4good.thegoodailab.org

CV4GOOD — Computer Vision for Humanitarian Action

ECCV 2026 workshop in Malmö, Sweden on Tuesday, September 8, 2026, pairing CV researchers with humanitarian practitioners from MSF.

1125

Vladan Stojnić @stojnicv.xyz · 03/09/2026

It’s really hard! But why do I fee like option 2 is kind of easy (I immediately went there without paying attention to the examples), did I see too many ImageNet examples 😂

020

Reposted by Vladan Stojnić

Klara Janouskova @klara-cz.bsky.social · 03/09/2026

🐕 🍄 🎻 🚜 ReImageNet is out. 🚜 🎻🍄� We reannotated the whole ImageNet-1k val set from scratch: 50,000 images, multilabel, 96,051 bounding boxes, new definitions for all 1,000 classes, five semantic attributes. Browse every annotation: vrg.fel.cvut.cz/reimagenet Paper: arxiv.org/abs/2608.13783

2248

Reposted by Vladan Stojnić

Evangelos Kazakos @ekazakos.bsky.social · 02/09/2026

Welcome to the ECCV 2026 feed! Post and discuss ECCV 2026 papers, workshops, tutorials, talks, and social events. Use #ECCV2026 to make sure your post appears (other variants work too, e.g. #eccv). Link: bsky.app/profile/ekaz.... Please pin 📌 and share! Thanks! Made by @ekazakos.bsky.social.

295

Reposted by Vladan Stojnić

Feyza Yavuz @fyavuz1.bsky.social · 01/09/2026

Excited to share our work, IDeaL! Big thanks to @mbsariyildiz.bsky.social and @dlarlus.bsky.social for the guidance and support from day one. At ECCV? We're in Poster Session 2, Thu Sep 10. Come say hi! Paper: arxiv.org/abs/2608.24759 Project page: blisgard.github.io/ideal_project/

0165

Reposted by Vladan Stojnić

Giorgos Tolias @gtolias.bsky.social · 25/08/2026

Your camera leaves fingerprints on every photo. Vision encoders learned to read them. Read about the bad and the good sides of it. "Invisible Shortcuts: Why Vision Encoders Know Your Camera" has been accepted at ECCV 2026. Paper: arxiv.org/pdf/2608.05424 @eccv.bsky.social #ECCV2026

52712

Reposted by Vladan Stojnić

Dmytro Mishkin @ducha-aiki.bsky.social · 21/08/2026

Doomed to Re-Annotate, Forever: The ImageNet Story Illia Volkov, Nikita Kisel, Tetiana Mishkina, @klara-cz.bsky.social Jiri Matas tl;dr: ImageNet val annotation with all bboxes, careful study of concepts, attributes (is drawing of a cat, a cat?) Year of efforts. 1/ arxiv.org/abs/2608.13783

1195

Reposted by Vladan Stojnić

Klara Janouskova @klara-cz.bsky.social · 07/08/2026

We needed region annotations. We looked at what already existed… and we decided to build our own dataset. Meet STRAP 🎉 🤗 huggingface.co/datasets/vrg-prague/STRAP 🔗 klarajanouskova.github.io/STRAP Region–text annotations for 2M web images, from a single pass of a frozen open MLLM. 🧵

165

Reposted by Vladan Stojnić

Diane Larlus @dlarlus.bsky.social · 04/08/2026

Our #ECCV2026 Whareformer paper tackles long-term object tracking in Egocentric videos 🎓https://arxiv.org/abs/2607.08537 see Dima's thread below 🔽 joint work w Jacob Chalk, @saptarshisinha.bsky.social @dimadamen.bsky.social from Bristol & @skamalas.bsky.social from @naverlabseurope.bsky.social

1194

Reposted by Vladan Stojnić

Diane Larlus @dlarlus.bsky.social · 03/08/2026

We just released our #ECCV2026 paper on Model Merging for Computer Vision 🎓 arxiv.org/abs/2604.12935 Joint work w @pdejorge.bsky.social Cesar De Souza @bjoernmichele.bsky.social @mbsariyildiz.bsky.social @weinzaepfelp.bsky.social Florent Perronnin & @skamalas.bsky.social See Pau's thread below 🔽

1135

Reposted by Vladan Stojnić

Giorgos Kordopatis-Zilos @gkordo.bsky.social · 01/08/2026

📢 Deadline Extended! We have extended the Student Support Grant application deadline for the ILR+G Workshop @eccv.bsky.social by 2 days. If you haven't applied yet, there's still time! 🗓️ New deadline: August 2, 2026 📝 Apply now: forms.gle/qvqn2LyWXCvN... We look forward to seeing you in Malmö!

forms.gle

064

Reposted by Vladan Stojnić

Yannis Kalantidis @skamalas.bsky.social · 27/07/2026

Check out Pau's thread on our new #ECCV2026 paper! 🧵 We propose a proxy for making model merging scalable for real-world computer vision tasks (merging encoders across diverse domains like 2D, 3D, and human understanding)

0123

Reposted by Vladan Stojnić

Pau de Jorge @pdejorge.bsky.social · 27/07/2026

1/6 Excited to share that our paper on model merging was accepted at ECCV 2026! 🎉 We introduce an efficient, decoder-free proxy that makes model selection faster, simpler and practical across vision tasks. 📄 arxiv.org/abs/2604.12935 🌐 europe.naverlabs.com/task-alignment 🧵👇

1146

Reposted by Vladan Stojnić

Giorgos Kordopatis-Zilos @gkordo.bsky.social · 26/07/2026

🎓 Student Support Grants are now available! Are you a student working on instance-level recognition and generation? We offer Student Support Grants for participants attending the ILR+G Workshop @eccv.bsky.social 📅 Application deadline: July 31, 2026 📝 Apply here: forms.gle/qvqn2LyWXCvN...

forms.gle

095

Reposted by Vladan Stojnić

Bill Psomas @billpsomas.bsky.social · 06/06/2026

🚨 Presenting today at #CVPR2026! Our highlight ⭐ paper Retrieve and Segment (RNS) asks a simple question: Can a few examples bridge the supervision gap in open-vocabulary segmentation? ✅ Turns out they can. 📍 Poster #578 ⏰ 16:45–18:45 📄 arxiv.org/abs/2602.23339

0103

Reposted by Vladan Stojnić

Giorgos Tolias @gtolias.bsky.social · 03/06/2026

𝑹𝒆𝒕𝒓𝒊𝒆𝒗𝒆 𝒂𝒏𝒅 𝑺𝒆𝒈𝒎𝒆𝒏𝒕 (𝑹𝑵𝑺) at CVPR 2026 — selected as a 🌟 𝑯𝒊𝒈𝒉𝒍𝒊𝒈𝒉𝒕 🌟 (top ~4% of submissions)! 𝗪𝗵𝗲𝗿𝗲 𝘁𝗼 𝗳𝗶𝗻𝗱 𝘂𝘀 𝗮𝘁 𝗖𝗩𝗣𝗥 𝟮𝟬𝟮𝟲 (𝗗𝗲𝗻𝘃𝗲𝗿): 🔹 𝑴𝒂𝒊𝒏 𝑪𝒐𝒏𝒇𝒆𝒓𝒆𝒏𝒄𝒆 Poster Session 4 (#578) — June 6, 16:45–18:45 🔹 𝑾𝒉𝒂𝒕 𝒊𝒔 𝑵𝒆𝒙𝒕 𝒊𝒏 𝑴𝒖𝒍𝒕𝒊𝒎𝒐𝒅𝒂𝒍 𝑭𝒐𝒖𝒏𝒅𝒂𝒕𝒊𝒐𝒏 𝑴𝒐𝒅𝒆𝒍𝒔? Workshop — June 3, 14:30–16:00

185

Reposted by Vladan Stojnić

Giorgos Tolias @gtolias.bsky.social · 31/05/2026

Vision Transformers are brittle to variable input resolutions. In dense prediction tasks, the standard fix is sliding-window inference with heavy overlap, which is effective but painfully slow. SPAR (Single-Pass Any-Resolution ViT), takes a different approach.

1143

Reposted by Vladan Stojnić

Giorgos Kordopatis-Zilos @gkordo.bsky.social · 25/05/2026

🚨 Call for Papers 🚨 8th Instance-Level Recognition and Generation (ILR+G) Workshop at @eccv.bsky.social 📍 Malmö, Sweden 📅 September 8–9, 2026 🌐 ilr-workshop.github.io/ECCVW2026/ Submission deadline: June 26, 2026 Notification of acceptance: July 24, 2026 #ECCV2026 #ComputerVision

1124

Reposted by Vladan Stojnić

Giorgos Tolias @gtolias.bsky.social · 22/05/2026

Do vision and vision-language foundation models suffer from shortcut learning? Is this only a curse or also a blessing? I'm excited to discuss our recent work at the AMD AI Research Club session with Pier Luigi Dovesi. 📅 May 28, 2026 — 2PM Prague time Register here 👇 amd.zoom.us/webinar/regi...

amd.zoom.us

Welcome! You are invited to join a webinar: Invisible Shortcuts: Why Vision Encoders Know Your Camera | AMD AI Research Club. After registering, you will receive a confirmation email about joining the...

Join us for the third session of the AMD AI Research Club, a peer-to-peer paper spotlight series connecting AI researchers, engineers, and practitioners shaping the future of AI. In this session, Gio...

161

Reposted by Vladan Stojnić

Bill Psomas @billpsomas.bsky.social · 24/04/2026

🇧🇷 Presenting our ICLR 2026 paper “Efficient Probing” (EP) today! ❓What if linear probing is asking the wrong question? 🥳 EP is a lightweight attention probing method that better evaluates local, patch-level representations from models like MIM. 📍Friday 24 April, P4-#3713, 15:15–17:45

0157

Reposted by Vladan Stojnić

Pavel Suma @psuma.bsky.social · 23/04/2026

🚨 Efficient Local Visual Similarity (ELViS) @ #ICLR 2026 🇧🇷 ELViS is a fast, lightweight, and interpretable module for estimating image-to-image similarity that generalizes well to many image domains. Paper: arxiv.org/abs/2603.28603 Code: github.com/pavelsuma/ELViS Come see poster today @ P4-#3715

1147

Reposted by Vladan Stojnić

Giorgos Tolias @gtolias.bsky.social · 23/04/2026

The Visual Recognition Group at CTU in Prague organizes the 51st Pattern Recognition and Computer Vision Colloquium with Roman Bednarik, István Sárándi, Andreas Geiger, Jan Škvrna, Yuki Asano and Dániel Baráth. cmp.felk.cvut.cz/colloquium/#... Happening today, Thursday Apr 23, 11:00-17:00.

1152

Vladan Stojnić @stojnicv.xyz · 09/03/2026

Got a few labeled images lying around? You can use them to drastically improve your open-vocabulary segmentation! Check out RnS, which boosts OVS baselines by up to 34%. 📈👇

040

Reposted by Vladan Stojnić

Dmytro Mishkin @ducha-aiki.bsky.social · 27/02/2026

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? Tilemachos Aravanis @stojnicv.xyz @billpsomas.bsky.social Nikos Komodakis @gtolias.bsky.social tl;dr: almost yes if use 1-3 images, no if more(fig 6) arxiv.org/abs/2602.23339 #CVPR2026

073

Reposted by Vladan Stojnić

Tong Wei @weitong8591.bsky.social · 26/02/2026

Excited to share that our paper "Global-Aware Edge Prioritization for Pose Graph Initialization" has been accepted to CVPR 2026! #CVPR2026 See you soon in Denver!🥳🥳 Code is coming soon🚧 ❓How would you do an accurate and efficient pose graph initialization in a global manner? arxiv.org/abs/2602.21963

arxiv.org

Global-Aware Edge Prioritization for Pose Graph Initialization

The pose graph is a core component of Structure-from-Motion (SfM), where images act as nodes and edges encode relative poses. Since geometric verification is expensive, SfM pipelines restrict the pose...

193

Reposted by Vladan Stojnić

Bill Psomas @billpsomas.bsky.social · 20/02/2026

1/n Attention, Please! 🚀 Our work “Revisiting Attentive Probing Through the Lens of Efficiency” has been accepted at #ICLR2026. We introduce Efficient Probing (EP) — a lightweight, multi-query attentive probing method for frozen encoders. Paper + code at the end 👇

1124

Reposted by Vladan Stojnić

Christoffer Koo Øhrstrøm @chrisohrstrom.bsky.social · 04/02/2026

What if position encodings were designed for vision from scratch? We introduce PaPE—Parabolic Position Encoding. Outperforms RoPE on 7/8 datasets and extrapolates to higher resolutions without fine-tuning or position interpolation. Paper, code, and website in thread 🧵

3367

Vladan Stojnić @stojnicv.xyz · 13/01/2026

Sorry for that. Should be allowed now

000

Vladan Stojnić @stojnicv.xyz · 13/01/2026

I would like to try it if possible?

100

Reposted by Vladan Stojnić

Giorgos Tolias @gtolias.bsky.social · 08/01/2026

I have an opening for a two years post-doc position on instance-level (personalized) visual generation. Eligibility: (i) <=7 years from Ph.D. (ii) studies or 1 year outside of Czechia (ii) >=3 journal with IF or CORE A*/A conference papers. Deadline: 15 Feb. Details: www.euraxess.cz/jobs/399390

euraxess.cz

Postdoctoral research position in Instance-level visual generation

Czech Technical University in Prague (CTU) offers a fellowship program, the CTU Global Postdoc Fellowship. This new and attractive two-year fellowship-program offers excellent researchers who have rec...

21210

Reposted by Vladan Stojnić

Bill Psomas @billpsomas.bsky.social · 27/12/2025

1/n REGLUE Your Latents! 🚀 We introduce REGLUE: a unified framework that entangles VAE latents ➕ Global ➕ Local semantics for faster, higher-fidelity image generation. Links (paper + code) at the end👇

1144

Reposted by Vladan Stojnić

Noa Garcia @noagarciad.bsky.social · 16/12/2025

Announcing the first AI for Peace Workshop @ ICLR 2026. The workshop aims to provide a forum for examining the relationship between AI research and its military, surveillance, and conflict-related applications. aiforpeaceworkshop.github.io

aiforpeaceworkshop.github.io

Home

Building Bridges, Not Weapons: AI for Peaceful Progress

23411

Vladan Stojnić @stojnicv.xyz · 09/12/2025

I guess it is related to this email from few days ago. However, it seems someone forgot to close the access as stated in the email, so we are seeing things as changes are happening.

010

Reposted by Vladan Stojnić

Klara Janouskova @klara-cz.bsky.social · 23/11/2025

Are you at BMVC tomorrow and interested in VLMs? Come see our poster "Image Recognition with Vision and Language Embeddings of VLMs". 👁️📕 TLDR: We benchmark VLMs on language- and vision-based classification, and propose a simple, training-free vision-language fusion. Link: arxiv.org/pdf/2509.09311

131

Reposted by Vladan Stojnić

Oisin Mac Aodha @oisinmacaodha.bsky.social · 21/11/2025

We have PhD opportunity (start date Sep 2026) at the University of Edinburgh at the intersection of biodiversity mapping and zoonotic disease prediction. It is part of the UKRI AI Centre for Doctoral Training in Biomedical Innovation based in the School of Informatics: ai4bi-cdt.ed.ac.uk

152

Reposted by Vladan Stojnić

Evangelos Kazakos @ekazakos.bsky.social · 23/10/2025

23rd of October. @iccv.bsky.social We present our work on “Large-scale Pretraining for Grounded Video Caption Generation” with Cordelia Schmid and @josef-sivic.bsky.social at Exhibit Hall I #434 on the morning session. We’ll have a search demo for our dataset as well! See you there!! 🚀

0122

Vladan Stojnić @stojnicv.xyz · 21/10/2025

We show that representations from some foundation models, especially CVLs like CLIP, encode information about image metadata. More surprisingly we show that such metadata traces can even affect the performance on semantic downstream tasks.

110

Vladan Stojnić @stojnicv.xyz · 21/10/2025

Are you at @iccv.bsky.social #ICCV2025? Come by our poster. 📅 October 22, 2025, 14:30 – 16:30 HST 📍 Location: Exhibit Hall I, Poster #207

2125

Vladan Stojnić @stojnicv.xyz · 21/10/2025

100

Reposted by Vladan Stojnić

Giorgos Kordopatis-Zilos @gkordo.bsky.social · 15/10/2025

🌺 Just 4 days to go! Join us in Honolulu for the Instance-Level Recognition and Generation Workshop at #ICCV2025 🏝 🗓️ Oct 19, 8:30am–12:30pm 📍 Room 306 A We’ll have amazing keynotes, plus oral and poster sessions featuring accepted and invited papers. Don’t miss it! ilr-workshop.github.io/ICCVW2025/

195