iiinova — where your digital self keeps evolving

Stefan Roth @stefanroth.bsky.social · 10/09/2026

I unfortunately cannot make it to #ECCV2026 but our team is in Malmö and is looking forward to welcoming you at our posters & presentations to tell you about some of our latest work. Please stop by if you are around!

0113

Stefan Roth @stefanroth.bsky.social · 06/06/2026

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

0113

Stefan Roth @stefanroth.bsky.social · 06/06/2026

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

062

Stefan Roth @stefanroth.bsky.social · 05/06/2026

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.

093

Reposted by Stefan Roth

Visual Inference Lab @visinf.bsky.social · 04/06/2026

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

176

Stefan Roth @stefanroth.bsky.social · 12/12/2025

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.

062

Reposted by Stefan Roth

Visual Inference Lab @visinf.bsky.social · 04/11/2025

📢🎓 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...

career.tu-darmstadt.de

086

Reposted by Stefan Roth

Visual Inference Lab @visinf.bsky.social · 04/04/2025

📢 #CVPR2025 Highlight: Scene-Centric Unsupervised Panoptic Segmentation 🔥 We present CUPS, the first unsupervised panoptic segmentation method trained directly on scene-centric imagery. Using self-supervised features, depth & motion, we achieve SotA results! 🌎 visinf.github.io/cups

1226

Stefan Roth @stefanroth.bsky.social · 14/12/2024

Starting in about 30 minutes in East A-C

080

Stefan Roth @stefanroth.bsky.social · 23/11/2024

I assume that congratulations are in order!? 😄

030

Stefan Roth @stefanroth.bsky.social · 22/11/2024

I recall there even being a PAMI-TC motion to this effect (though I cannot find it on the list of approved motions). The thing is that our community has gotten too big for this to still work. So it‘s not really implemented (anymore).

030

Stefan Roth @stefanroth.bsky.social · 22/11/2024

Congratulations Dima and thank you very much for your outstanding work as AC!

010

Stefan Roth @stefanroth.bsky.social · 21/11/2024

Hi Kosta, glad to be added. We shall see whether I will use this any more than I have used “the other platform” lately 😉 Hope all is well. Thanks a lot for setting up this list!

000