Our #CVPR2026 poster starts in 30 minutes! Come by Poster Session 2, #333 to learn about VideoCUPS — the first unsupervised video panoptic segmentation method, learning to detect, segment, and track objects in video without human supervision.

Visual Inference Lab@visinf.bsky.social · 2mo ago

📢 [CVPR’26] Can we learn to detect, segment, and track every object in a video without human supervision?  Yes, we introduce VideoCUPS, the first unsupervised video panoptic segmentation (VPS) method: 1. Get pseudo-labels from monocular videos. 2. Train a VPS model on them.

Afterwards, please stop by to see MARCO, our approach for semantic correspondence that generalizes to novel keypoints and categories. 4:12 PM in oral session 4D and later at poster #20. #CVPR2026 github.com/visinf/MARCO

Come see INSID3, in-context segmentation with DINOv3, at 2:00 PM in oral session 4D and later at poster #19. #CVPR2026

Gabriele Trivigno@gabtriv.bsky.social · 4mo ago

🔥 Can in-context segmentation emerge directly from frozen DINOv3 features? At #CVPR2026, we present INSID3: Training-Free In-Context Segmentation with DINOv3 — a collaboration between PoliTo, TU Darmstadt and TU Munich. Check it out: github.com/visinf/INSID3

📢 [CVPR’26] Can we learn to detect, segment, and track every object in a video without human supervision?  Yes, we introduce VideoCUPS, the first unsupervised video panoptic segmentation (VPS) method: 1. Get pseudo-labels from monocular videos. 2. Train a VPS model on them.

[1/6] 📢 We are in Denver at #CVPR2026 presenting 5 papers!

[1/3] Multimodal Knowledge Distillation for Egocentric Action Recognition Robust to Missing Modalities by @dustin-carrion.bsky.social*, Maria Santos-Villafranca*, Alejandro Perez-Yus, Jesus Bermudez-Cameo, Jose J. Guerrero, and @simoneschaub.bsky.social

Today @kyutai-labs.bsky.social and @ellisinsttue.bsky.social launch @kesai.eu! Robot learning is bottlenecked by the cost of physical interaction. Our mission is to advance the efficiency frontier of robust & safe physical AI through fully open and reproducible research. kesai.eu/blog/2026-05...

Kyutai and ELLIS Tübingen launch KE:SAI: A Premier Franco-German Partnership for Open Science in Physical AI

Kyutai and ELLIS Tübingen announce the official launch of KE:SAI – Kyutai ELLIS Scalable Autonomous Intelligence, a non-profit open science lab for physical AI.

kesai.eu

🎉 25 ELLIS Units have been successfully extended! Following our five-year reapplication process, we celebrate the sustained excellence these Units bring to European AI research. Congratulations to all! 👏 📖 Get more details: ellis.eu/news/25-elli...

📢 Call for Papers: #VMV2026 #GCPR2026 is joined by the International Symposium on Vision, Modeling, and Visualization! We invite high-quality submissions across all areas of visual computing. We are excited to see your work! 👉 Learn more & submit: www.gcpr-vmv.de/year/2026/vmv

#GCPR2026 is coming to #Siegen! 🎉 Join us for great research at the beautiful Campus Lower Castle of the University of Siegen, perfectly located just a short walk from the central station and many city hotels. More info: www.gcpr-vmv.de/year/2026/lo...

Got a paper on generative models accepted at CVPR 2026? Share it with us at the 4th Workshop on Generative Models for Computer Vision! generative-vision.github.io/workshop-CVP... You can simply submit your accepted CVPR paper, no need to reformat! Deadline: April 30 (AoE)

🔥 Can in-context segmentation emerge directly from frozen DINOv3 features? At #CVPR2026, we present INSID3: Training-Free In-Context Segmentation with DINOv3 — a collaboration between PoliTo, TU Darmstadt and TU Munich. Check it out: github.com/visinf/INSID3

We are excited to share our call for papers with a submission deadline on May 21st, 2026! We invite submissions of high-quality research papers presenting original contributions in all areas of pattern recognition! Read more: www.gcpr-vmv.de/year/2026/gc... #GCPR2026 #VMV2026

📢🎓 We have open PostDoc positions in Computer Vision & ML at @tuda.bsky.social and @hessianai.bsky.social within the Reasonable AI Cluster of Excellence — supervised by @stefanroth.bsky.social, @simoneschaub.bsky.social and many others! Apply here: www.career.tu-darmstadt.de/tu-darmstadt...

I am one of the potential advisors for this PhD position in our #DAAD funded AI graduate school ELIZA (eliza.school), which connects seven #ELLIS units in Germany. If you are interested in working with one of my colleagues or with me (in computer vision & deep learning), please consider applying.

Zuse School ELIZA@zuseschooleliza.bsky.social · 8mo ago

Are you looking for a PhD in machine learning? 🧠 ELIZA is hiring a Doctoral Researcher at TU Darmstadt! Apply by Jan 5: www.career.tu-darmstadt.de/tu-darmstadt... ℹ️ Learn more about ELIZA: eliza.school @tuda.bsky.social, @cs-tudarmstadt.bsky.social, @ellis.eu, @daadworldwide.bsky.social #AI

📢 NeurIPS 2025 Spotlight 📢 Can we embed motion into image representations? FlowFeat embeds optical flow into pixel-level representations, which results in sharp feature grids, especially for dynamic objects. Project website: tum-vision.github.io/flowfeat With Anna Sonnweber and Daniel Cremers.

📢 Join @tuda.bsky.social as a PhD/Postdoc in the new project HAICC - Human–AI Collaboration for Cybersecurity! Explore how LLM–based AI agents and humans can jointly analyse security data and rethink cybersecurity architectures - supervised by Iryna Gurevych, @stefanroth.bsky.social, and many more!

UKP Lab@ukplab.bsky.social · 8mo ago

🛡️ 𝗪𝗲 𝗮𝗿𝗲 𝗵𝗶𝗿𝗶𝗻𝗴 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗻𝗲𝘄 𝗛𝗔𝗜𝗖𝗖 𝗽𝗿𝗼𝗷𝗲𝗰𝘁 𝗮𝘁 𝗔𝗧𝗛𝗘𝗡𝗘 Do not miss the opportunity for groundbreaking science and get a chance to work together with an amazing diverse team of leading researchers! (1/🧵)

Attending #Neurips2025? Get your personalized Scholar Inbox conference program now to easily navigate the poster sessions and find what you are looking for: www.scholar-inbox.com/conference/n...

@neuripsconf.bsky.social is two weeks away! 📢 Stop missing great workshop speakers just because the workshop wasn’t on your radar. Browse them all in one place: robinhesse.github.io/workshop_spe... (also available for @euripsconf.bsky.social) #NeurIPS #EurIPS

📢🎓 We have open PhD positions in Computer Vision & Machine Learning at @tuda.bsky.social and @hessianai.bsky.social within the Reasonable AI Cluster of Excellence — supervised by @stefanroth.bsky.social, @simoneschaub.bsky.social and many others! www.career.tu-darmstadt.de/tu-darmstadt...

🎉 Today, Simon Kiefhaber will present our ICCV oral paper on how to make optical flow estimators more efficient (faster inference and lower memory usage) with state-of-the-art accuracy: 🌍 visinf.github.io/recover Talk: Tue 09:30 AM, Kalakaua Ballroom Poster: Tue 11:45 AM, Exhibit Hall I #76

Removing Cost Volumes from Optical Flow Estimators

We present ReCoVEr - A training strategy for removing the cost volume from an optical flow estimator during training.

visinf.github.io

Visual Inference Lab@visinf.bsky.social · 10mo ago

[2/8] Removing Cost Volumes from Optical Flow Estimators (Oral) by @skiefhaber.de , @stefanroth.bsky.social @simoneschaub.bsky.social 🌍 visinf.github.io/recover Talk: Tue 09:30 AM, Kalakaua Ballroom 
Poster: Tue 11:45 AM, Exhibit Hall I #76

Interested in 3D DINO features from a single image or unsupervised scene understanding?🦖 Come by our SceneDINO poster at NeuSLAM today 14:15 (Kamehameha II) or Tue, 15:15 (Ex. Hall I 627)! W/ Jevtić @fwimbauer.bsky.social @olvrhhn.bsky.social Rupprecht, @stefanroth.bsky.social @dcremers.bsky.social

[1/8] We are presenting four main conference papers, two workshop papers, and a workshop at @iccv.bsky.social 2025 in Hawaii! 🎉🏝

📢Excited to share our IROS 2025 paper “Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model”! Work by Jannik Endres, @olvrhhn.bsky.social, Charles Cobière, @simoneschaub.bsky.social, @stefanroth.bsky.social and Alexandre Alahi.

🎓 Looking for a PhD position in computer vision? Apply to the European Laboratory for Learning & Intelligent Systems (ELLIS) and work with @stefanroth.bsky.social & @simoneschaub.bsky.social! Join the info session on Oct 1. @ellis.eu @tuda.bsky.social ellis.eu/news/ellis-p...

ELLIS PhD Program: Call for Applications 2025

The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...

ellis.eu

We are presenting five papers at the DAGM German Conference on Pattern Recognition (GCPR, @gcpr-by-dagm.bsky.social) in Freiburg this week!

Some impressions from our VISINF summer retreat at Lizumer Hütte in the Tirol Alps — including a hike up Geier Mountain and new research ideas at 2,857 m! 🇦🇹🏔️

🌟 Keynotes at #GCPR2025 🌟 🎤 Prof. Dima Damen (Uni Bristol & Google DeepMind) 🗓️ Thursday, Sept 25, 2025. 10:30–11:30 Talk:Opportunities in Egocentric Vision Discover new frontiers in egocentric video understanding, from wearable devices to large-scale datasets. 🔗 www.dagm-gcpr.de/year/2025/re...

🚨 Nectar Track @ #GCPR2025 — Call for Submissions! 🧠📢 Have a top-tier paper from the last year (CVPR, NeurIPS, ICLR, ECCV, ICCV, etc.)? Share your work with the vibrant GCPR community! 🗓️ Submission Deadline: July 28, 2025 🔗 Instructions: www.dagm-gcpr.de/year/2025/su...