Giorgos Kordopatis-Zilos

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...

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

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!! 🚀

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

🎙️ Come and meet our amazing keynote speakers
Sara Beery - Assistant Professor at MIT CSAIL
@sarameghanbeery.bsky.social

Matej Kristan - Full professor at the University of Ljubljana
www.vicos.si/people/matej...

Mark Boss - Co-Head of 3D & Image at Stability AI
@markboss.bsky.social

🌺 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/

• SigLIP2 → still the best for text-to-image retrieval.
– Unlike SigLIP models, PE shows a large gap between its image-to-image and text-to-image performance.

• PE → achieves state-of-the-art in image-to-image retrieval with linear adaptation.
  – Gains +12% performance from adaptation.
  – Outperforms SigLIP2 (previous best) by +2%.
  – DINOv3 lags behind, gaining less than +2% from adaptation

🔍 Key results from our new evaluation on ILIAS:

• DINOv3 → sets a new state-of-the-art in image-to-image retrieval without linear adaptation
  – The large variant outperforms all other models by a significant margin.
  – The base outperforms the large variants of other model series.

🚀 new state-of-the-art on ILIAS dataset!

Curious how well the latest models can recognize particular objects?
We evaluated the base and large variants of DINOv3 and Perception Encoder (PE) on instance-level image retrieval.

See the results 👉 vrg.fel.cvut.cz/ilias/

Pattern Recognition and Computer Vision Colloquium - past speakers

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/

Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

@ryan-ramos.bsky.social @stojnicv.xyz @gkordo.bsky.social Yuta Nakashima @gtolias.bsky.social
@noagarciad.bsky.social
tl;dr: CLIP sees difference DSLR vs iphone, DINO doesn't.
arxiv.org/abs/2508.10637
1/

Have you ever asked yourself how much your favorite vision model knows about image capture parameters (e.g., the amount of JPEG compression, the camera model, etc.)? Furthermore, could these parameters influence its semantic recognition abilities?

@iccv.bsky.social

Topics:
- IL object classification, detectection, segmentation, and pose estimation
- particular object and event retrieval
- personalized image/video generation
- cross/multi-modal recognition at IL
- image matching, place recognition, video tracking
- other ILR+G applications
- ILR+G datasets

We invite papers on topics related to instance-level recognition and/or generation. We extend the submission deadline to give the authors of related papers that didn't make it to ICCV 2025 a chance to still join us in Hawaii 🌺

🚨 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

I am at #CVPR2025 this week in Nashville!

Presenting "Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers" on multi-modal semantic future prediction.

Come discuss!

Fri 13 Jun 10:30-12:30, poster #345
bsky.app/profile/sta8...

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

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

cegis 2nd workshop on critical evaluation of generative models and their impact on society 19 or 20 October 2025 at ICCV 2025, Honolulu, Hawaii

The 2nd CEGIS workshop on visual generative models evaluation is back at #ICCV2025!!

Submit your contributions:
- Deadline: June 26th 2025
- Notification: July 10th, 2025
- Camera-ready: August 18th, 2025

See you in Honolulu!

sites.google.com/view/cegis-w...

@iccv.bsky.social

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

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.

🚨 Call for Papers!

7th Instance-Level Recognition and Generation (ILR+G) Workshop at @iccv.bsky.social

📍 Honolulu, Hawaii 🌺
📅 October 19–20, 2025
🌐 ilr-workshop.github.io/ICCVW2025/

in-proceedings deadline: June 7
out-of-proceedings deadline: June 30

#ICCV2025

also, thanks to @nielsrogge.bsky.social for the initial contact for hosting ILIAS on @hf.co

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!

yes, we plan to release the top-1k shortlist of SigLIP, which will be used in the evaluation code. But we can provide it for any benchmarked model if useful for someone.

correct, it is not that VLMs perform well. Much better compared with older models, but still performance is very low. SigLIP mAP@10=0.28, so no significant difference.

Yeap, until the introduction of VLMs, global representation models would really struggle to perform well. But they are steadily getting better the last years.

Huge thanks to all the co-authors @stojnicv.xyz @annetka.bsky.social @psuma.bsky.social @nikosips.bsky.social @nikos-efth.bsky.social Zakaria Laskar Jiří Matas Ondřej Chum @gtolias.bsky.social