Nikolaos-Antonios Ypsilantis

True multimodal AI needs to understand the world spatially 🎯 🚀 Excited to release #CVPR2026 TIPSv2 from @GoogleDeepMind, a foundational image-text encoder with spatial awareness, leading to strong overall results and massive gains on patch-text alignment. 🔥 1/N

🚀 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/

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?

Call for Papers update - ILR+G workshop @ICCVConference 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

🚨 Call for Papers! 7th Instance-Level Recognition and Generation Workshop (ILR+G) at @ICCVConference 📍 Honolulu, Hawaii 🌺 📅 October 19–20, 2025 🌐 ilr-workshop.github.io/ICCVW2025/ in-proceedings deadline: June 7 out-of-proceedings deadline: June 30 #ICCV2025

Excited to release a super capable family of image-text models from our TIPS #ICLR2025 paper! github.com/google-deepmin… We have models from ViT-S to -g, with spatial awareness, suitable to many multimodal AI applications. Can’t wait to see what the community will build with them!

ILIAS: Instance-Level Image retrieval At Scale @g_kordo, @stojnvla , Anna Manko, Pavel Šuma, @YpsilantisNikos , Nikos Efthymiadis, Zakaria Laskar, Jiří Matas, Ondřej Chum, Giorgos Tolias tl;dr: new retrieval dataset with guaranteed GT. SigLIP rules. arxiv.org/abs/2502.11748 1/

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!

1/ 🎉 Excited to share our work, "Composed Image Retrieval for Training-Free Domain Conversion", accepted at WACV 2025! 🚀

Want some TIPS? Well, then check out “Text-Image Pretraining with Spatial awareness” :) TIPS is a general-purpose image-text encoder, for off-the-shelf dense and image-level prediction. Finally image-text pretraining with spatially-aware representations! arxiv.org/abs/2410.16512

#ECCV2024 Our Instance-Level Recognition workshop is tomorrow morning (Monday 9am at Amber 5)! Great keynotes (@CordeliaSchmid, @jampani_varun, @g_kordo), accepted papers and invited papers from the main conference. Don't miss it! ilr-workshop.github.io/ECCVW2024/

Excited to share that UDON will be presented in NeurIPS'24! I am very grateful to my advisor, Prof. Ondrej Chum, and my collaborators @andrefaraujo and @kfrancischen !

AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval @SumaPavel @g_kordo @ahmetius @giotolias tl;dr: global+local similarity via transformer->binarize descrs+distill. Crucial:train with random number of descriptors. arxiv.org/abs/2408.03282

Excited to release UDON, our latest & greatest universal image embedding! Effective and efficient multi-teacher distillation to improve performance across different fine-grained domains. Code coming soon! arxiv.org/abs/2406.08332 with @YpsilantisNikos, @kfrancischen, Ondřej Chum

Announcing the #ECCV2024 workshop on Instance-Level Recognition (ILR)! This is the 6th edition in our workshop series, with amazing keynote speakers: @CordeliaSchmid, @jampani_varun and @g_kordo. Call for papers now open! All information on our website: ilr-workshop.github.io/ECCVW2024/

We are happy to share ZLaP, "Label Propagation for Zero-shot Classification with Vision-Language Models", that will be presented at #CVPR2024. Work done with @skamalas and @giotolias .

We are running the Vision and Sports Summer school again this year! Prague, July 22-27. We offer a broad-range of lectures on state-of-the-art Computer Vision techniques, as well as exciting sport activities, such as Volleyball, Frisbee and Table Tennis. cmp.felk.cvut.cz/summerschool20…

Excited to share that SPOT is accepted to #CVPR2024. SPOT advances unsupervised object-centric learning with attention-based self-training & patch-order permutation, achieving state-of-the-art results. - Paper: arxiv.org/abs/2312.00648 - Code: github.com/gkakogeorgiou/…

We are happy to share that our work titled "Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning" will be presented at #WACV2024. It is a joint work with Zakaria Laskar and @giotolias. If you will be at #WACV2024, visit our poster on January 4th.

If you are interested in Image Representations that work across diverse fine-grained and instance-level domains for image search, visit our Poster today at @ICCVConference , room “Foyer Sud”, poster 138, from 10:30 am to 12:30 pm. #ICCV2023