Lightnews — Scholar-powered news

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Sep 5

• 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.

5

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Sep 5

• 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

1 5

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Sep 5

🔍 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.

1 5

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Sep 5

🚀 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/

1 5 13

Reposted by Giorgos Kordopatis-Zilos

Giorgos Tolias @gtolias.bsky.social · Sep 1

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/

Pattern Recognition and Computer Vision Colloquium - past speakers

docs.google.com

1 8 16

Reposted by Giorgos Kordopatis-Zilos

Dmytro Mishkin @ducha-aiki.bsky.social · Aug 25

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/

1 4 15

Reposted by Giorgos Kordopatis-Zilos

Vladan Stojnić @stojnicv.xyz · Aug 18

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?

1 8 26

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Jun 22

@iccv.bsky.social

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Jun 22

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

1 1

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Jun 22

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 🌺

1 1

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Jun 22

🚨 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

1 10 12

Reposted by Giorgos Kordopatis-Zilos

Spyros Gidaris @spyrosgidaris.bsky.social · Jun 13

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...

sta8is.bsky.social @sta8is.bsky.social · Feb 26

🧵 Excited to share our latest work: FUTURIST - A unified transformer architecture for multimodal semantic future prediction, is accepted to #CVPR2025! Here's how it works (1/n)
👇 Links to the arxiv and github below

2 6

Reposted by Giorgos Kordopatis-Zilos

Vladan Stojnić @stojnicv.xyz · Jun 13

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

1 6 14

Reposted by Giorgos Kordopatis-Zilos

Giorgos Tolias @gtolias.bsky.social · Jun 12

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

1 3 10

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Jun 13

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

9 17

Reposted by Giorgos Kordopatis-Zilos

Noa Garcia @noagarciad.bsky.social · Jun 2

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

cegis

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

sites.google.com

5 11

Giorgos Kordopatis-Zilos @gkordo.bsky.social · May 24

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

8 10

Reposted by Giorgos Kordopatis-Zilos

Giorgos Tolias @gtolias.bsky.social · May 11

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.

#CVPR2026 @cvprconference.bsky.social · May 10

Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers!

cvpr.thecvf.com/Conferences/...

3 17

Giorgos Kordopatis-Zilos @gkordo.bsky.social · May 7

🚨 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

ILR+G 2025

The Official Site of ICCV 2025 Workshop, Instance-Level Recognition and Generation Workshop

ilr-workshop.github.io

7 14

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Mar 28

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

2

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Mar 28

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!

1 8 30

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Feb 28

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.

2

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Feb 28

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.

1 1

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Feb 27

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

1 1

Giorgos Kordopatis-Zilos @gkordo.bsky.social · Feb 27

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

5