@stefanroth

Professor of Computer Science @TUDarmstadt — Computer Vision, Machine Learning, Deep Learning Now on Bluesky: https://xitter.cf/t.co/qlLyANHr8p

 Darmstadt, Deutschland
visinf.tu-darmstadt.de
Joined February 2012
  • Tweets109
  • Following130
  • Followers1.6K
9Media
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!
Visual Inference Lab@visinfSep 8
[1/6] 📢 We are in Malmö at #ECCV2026 presenting 5 papers! 🎉
2
2
29
2,627
Afterwards, please stop by to see MARCO, a generalizable approach for semantic correspondence. 4:12 PM in oral session 4D and later at poster #20. #CVPR2026
Gabriele Trivigno@gabTrivvJun 6
Today! I'm going to present MARCO in Oral Session 4D at 2 pm, and later at poster #20! Don't miss it :)
11
962
Come see INSID3, in-context segmentation with DINOv3, at 2:00 PM in oral session 4D and later at poster 19. #CVPR2026
Claudia Cuttano@ClaudiaCuttanoJun 6
✨ #CVPR2026 Oral ✨ INSID3 turns a frozen DINOv3 into a training-free in-context segmenter across domains and granularities! Excited to present our work today in Oral Session 4D (14:00–15:15). Come by our poster later if you’d like to chat: 📍 Poster #19 🕓 16:00–18:00 See you there!
1
2
23
2,304
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@visinfJun 5
📢 [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.
4
26
1,816
Stefan Roth retweeted
Visual Inference Lab@visinfJun 4
[1/6] 📢 We are in Denver at #CVPR2026 presenting 5 papers!
1
9
29
1,769
📢🎓 We have open PhD positions in Computer Vision & Machine Learning at @TUDarmstadt and hessian.AI within the Reasonable AI Cluster of Excellence — supervised by @stefanroth, @schaub_simone and many others! Apply here: career.tu-darmstadt.de/tu-da…
9
23
1,906
Congratulations to Demis, John, and the whole AlphaFold team! Fantastic achievement!!
Pushmeet Kohli
@pushmeet9 Oct 2024
If AlphaFold was proof of AI’s potential, it is now also prelude – to a future of incredible progress, driven by AI, shaped by human ingenuity, and guided by a collective sense of responsibility and safety. Massive congrats to @demishassabis and John on winning the Nobel Prize!
20
1,994
My warmest congratulations, @geoffreyhinton, for this most wonderful appreciation of your work! As a grad student many years ago, I have been fortunate enough to attend one of the CIFAR summer schools that you organized in the Neural Computation & Adaptive Perception program. 1/2
The Nobel Prize
@NobelPrize8 Oct 2024
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
5
1
29
4,446
Learning from you and witnessing your contagious enthusiasm for research on that occasion (and several since) is surely one of the most cherished memories of my whole research career. Thank you, Geoff, for inspiring so many of us and congratulations once more! Highly deserved 2/2
7
387
Stefan Roth retweeted
Robin Hesse@robinhesse_3 Oct 2023
If you are interested in evaluating explainable AI methods and in our work "FunnyBirds", please join us tomorrow at #ICCV2023 for our talk at 1:30 p.m. or stop by our poster at 2:30 p.m. Looking forward to seeing you! @visinf @stefanroth @schaub_simone
1
5
14
1,910
How can we evaluate explanations? Our #ICCV2023 oral "FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods" by @robinhesse_ @schaub_simone @stefanroth, answers this question. ArXiv: arxiv.org/abs/2308.06248 Video: youtube.com/watch?v=rOc-Wd4F…
1
11
1
44
7,834
#Karrierechance im Bereich #KI: Die @TUDarmstadt sucht eine:n Scientific Coordinator für die #ZuseSchoolELIZA. Du bist engagiert und willst die Ausbildung von #AITalents vorantreiben? Jetzt bis zum 31. Juli 2023 bewerben👉 tu-darmstadt.de/universitaet…
3
4
1,366
Very excited to be traveling to New Orleans to #CVPR2022. Feels weird after 2 years of virtual-only conferences, but also very good at the same time... Looking forward to seeing many friends and colleagues!
1
1
35
Thanks to the in-flight WiFi I can even continue with our conference prep and test-drive one of the Twitter hashtags #CVPR2022O1 for posting questions during the oral sessions 😀
1
7
Stefan Roth retweeted
#CVPR2026@CVPR2 Mar 2022
We have successfully wrapped up the #CVPR2022 decision process with the tremendous effort of our reviewers and area chairs. The list of paper IDs of accepted papers are here: drive.google.com/file/d/15JF… The final reviews and meta reviews will be released in the next day or two. 1/2

accepted_papers.txt

drive.google.com
9
41
32
328
Stefan Roth retweeted
#CVPR2026@CVPR24 Jan 2022
Huge thanks to all reviewers, emergency reviewers, and area chairs for their dedicated contribution to CVPR 2022! 2/2
1
4
31
Stefan Roth retweeted
#CVPR2026@CVPR24 Jan 2022
#CVPR2022 reviews have been released to authors on schedule. Some stats: 8023 papers still under review, >= 3 reviews each, 25801 reviews from 6427 reviewers including 3066 emergency reviews from 2104 emergency reviewers. 1/2
1
7
76
New day, new #NeurIPS2021 paper. Want to learn about computing axiomatic feature attributions for neural networks in a single forward-backward pass? Join us at 9:30 am CET at spot G2 for our presentation. Paper and code: visinf.github.io/fast-axioma… Talk: youtu.be/AHkeeyoNGp8
1
4
20
Interested in efficiently learning dense representations for video object segmentation without supervision? Join us today for #NeurIPS2021 at 5:30pm CET (11:30am ET) at spot C0. Paper and code: github.com/visinf/dense-ulea… Talk: youtu.be/tSBWZ6nYld0 Results: youtu.be/BqVtZJSLOzg
1
21
1
122
Stefan Roth retweeted
#CVPR2026@CVPR20 Nov 2021
Preliminary #CVPR2022 paper stats: Paper IDs registered: 11,083 Actual paper submissions: 8,162 The actual paper submissions are subject to change due to desk rejects. Currently, our program chairs are reviewing the papers for desk rejects.
2
22
5
142
Load more