Yankun Wu

This is very disappointing and should not happen. Decisions on the paper or workshop proposal should be based only on the submission itself. It is unacceptable to reject the paper due to the "lack of capacity" of the conference (or some other reasons that we never know).

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?

🚨Deadline extension!!

The 2nd CEGIS workshop on visual generative models evaluation at #ICCV2025 #ICCV @iccv.bsky.social

🌴 New deadline: July 2nd 2025 (11:59 pm, Pacific Time)
📝 Submission site: cmt3.research.microsoft.com/CEGIS2025
🏁 Check details at: sites.google.com/view/cegis-w...

🚨 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

Computer Vision – ECCV 2024 Workshops The ECCV 2024 Workshops' proceedings deal with up to date topics in research and applications in computer vision.

#ECCV2024 Workshop Proceedings are now available which includes the VISART papers on #computervision, #arthistory and #culturalheritage link.springer.com/book/10.1007...

Thank you Vangelis!

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

Thank you very much Noa sensei!!

I finished my PhD defense! Thank my dearest supervisors Prof. @noagarciad.bsky.social and Prof. Yuta Nakashima for their consistent support during this journey. I am grateful for being their student ✨ Also thank Prof. @gtolias.bsky.social for his support during our collaboration! 💪

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

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

🌴 Deadline: June 26th 2025
📝 Submission site: cmt3.research.microsoft.com/CEGIS2025
🏁 Check details at: sites.google.com/view/cegis-w...

See you in Honolulu!

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

The instance-level recognition workshop is back! This year also including instance level generation.

Submit your in-proceedings papers by June 7, or out-of-proceedings by June 30.

See you in Honolulu! 🏝️

#iccv2025 @iccv.bsky.social

Gender inequality in Japanese academia
www.nature.com/articles/s44...

ILIAS is a large-scale test dataset for evaluation on Instance-Level Image retrieval At Scale. It is designed to support future research in image-to-image and text-to-image retrieval for particular objects and serves as a benchmark for evaluating foundation models and retrieval techniques.

Congratulations!!!

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

It is amazing working with you and celebrating Christmas day together! Let’s make a better year ahead! 💕🩷

This work includes a reality check for single-source domain generalization. Were prior method tuned properly on the validation set? Possible not, because an appropriate validation set did not exist until now. #WACV2025 paper.

Excited to present UDON at NeurIPS '24 tomorrow (Thursday 12/12)! If you are interested in a scalable training method for multi-domain image embeddings, come to poster #1410 in the East Exhibit Hall A-C of the Vancouver Convention Center from 11 am to 2 pm (PST) to discuss!

Beyond fairness in computer vision or why addressing bias as a technical problem is not enough

by @timnitgebru.bsky.social and Remi Denton

My first PhD paper at Osaka University! Very very very thankful for my wonderful collaborators and advisors!

Introducing a new composed (image + text query) image retrieval method that enables domain conversion—style, context, or background—of objects.

A must-read post on bias and why training data isn't the sole culprit