Excited to have DCBMs at #ICCV2025 - come by ballroom A tomorrow to meet @shashank-agnihotri.bsky.social presenting our joint work with @patrickknab.bsky.social @smarton.bsky.social Christian Bartelt @margretkeuper.bsky.social @keuper-labs.bsky.social #UniMa
19.10.2025 11:41 — 👍 2 🔁 3 💬 0 📌 0
📢 Last extension for submissions to our Learning to Sense (L2S) Workshop @ NeurIPS 2025!
🗓 Deadline: 11 Sept, AoE
📍 San Diego (NeurIPS 2025), Dec 6/7
Topics: sensor-model co-design, robustness, benchmarks, low-bit sensing, and more.
🌐 Details: sites.google.com/view/l2s-wor...
08.09.2025 13:21 — 👍 0 🔁 0 💬 0 📌 0
🎉Our TMLR paper FlowBench is out!
Optical flow keeps getting better on benchmarks, but reliability and generalization remain a challenge for safety-critical tasks.
FlowBench provides the most comprehensive robustness benchmark to date.
📄 openreview.net/forum?id=Kh4...
💻 github.com/shashankskag...
27.08.2025 16:14 — 👍 6 🔁 1 💬 0 📌 0
🚨 Deadline Extended!
Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖
📝 New Deadline: Sept 2 (AoE)
📅 Dec 6/7 | San Diego, USA
🎤 Invited speakers from UC Berkeley, Sony AI, SNU, Linköping Univ, York Univ
🌐 CFP: sites.google.com/view/l2s-wor...
#NeurIPS2025 #NeurIPSWorkshop
25.08.2025 14:47 — 👍 0 🔁 0 💬 0 📌 0
🌟 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...
21.08.2025 16:48 — 👍 10 🔁 4 💬 0 📌 0
I am looking forward to this amazing talk!
For further details on the keynotes, please refer to:
www.dagm-gcpr.de/year/2025/pr...
See you at #GCPR2025!
20.08.2025 14:55 — 👍 0 🔁 0 💬 0 📌 0
🚨 10 days left! Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖
📅 Dec 6/7, San Diego, USA
🎤 Invited speakers from academia & industry
🌐 Details & CFP: sites.google.com/view/l2s-wor...
Let’s shape the future of how machines sense!
#L2S #NeurIPS2025 #NeurIPSWorkshop
13.08.2025 10:16 — 👍 4 🔁 4 💬 0 📌 0
Excited to see the final Nectar Track decisions for #GCPR2025!
Looking forward to the amazing discussions these papers will spark at the conference 🔥🧠
08.08.2025 17:08 — 👍 0 🔁 0 💬 0 📌 0
Looking forward to the engaging discussions that the Nectar Track papers will inspire at GCPR 2025, alongside the broader program of exciting contributions across all tracks!
28.07.2025 12:22 — 👍 1 🔁 0 💬 0 📌 0
a cartoon character with a ponytail and the words `` what a drag '' written on the bottom .
ALT: a cartoon character with a ponytail and the words `` what a drag '' written on the bottom .
Just wondering… why release reviews on a Thursday evening instead of a Monday morning?
Feels like an unspoken test of who is willing to spend the weekend rebutting.
That said, review quality looks solid this year, so there is that!
But still...
#NeurIPS2025
24.07.2025 16:05 — 👍 0 🔁 0 💬 0 📌 0
People often use synthetic corruptions to test model robustness, but do these reflect real-world challenges?
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
24.07.2025 09:16 — 👍 1 🔁 1 💬 0 📌 0
DAGM GCPR (Accepted Papers)
🎉 Congratulations to all authors of accepted papers at GCPR 2025!
The full list is now live:
🔗 www.dagm-gcpr.de/year/2025/ac...
Missed the deadline but would to present at GCPR2025?
No worries, submit your top-tier work to the Nectar Track by July 28!
👉 www.dagm-gcpr.de/year/2025/su...
23.07.2025 15:17 — 👍 5 🔁 1 💬 0 📌 0
🩻 Can AI models offer faithful, interpretable, and artifact-free explanations for chest X-ray diagnosis?
📢 Meet Anti-Aliased B-cos Networks
✔️ Multi-label support
✔️ High-fidelity saliency maps
✔️ Clinical relevance
by: @margretkeuper.bsky.social
📄 arxiv.org/abs/2507.16761
#MedAI #XAI #ChestXray
23.07.2025 09:19 — 👍 1 🔁 0 💬 0 📌 0
Can MLLMs reason over images beyond the RGB domain? 🔍
We (@margretkeuper.bsky.social) explore In-Context Learning with VLMs for THz imaging to detect concealed threats, no training or finetuning in Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging.
arxiv.org/abs/2507.15576
22.07.2025 17:51 — 👍 2 🔁 1 💬 0 📌 0
An amazing opportunity to share and discuss your top-tier work with an audience of top researchers!
22.07.2025 15:46 — 👍 1 🔁 1 💬 0 📌 0
Looking forward to this amazing tutorial at GCPR2025!!
Registrations are open: www.dagm-gcpr.de/year/2025/re...
Do not miss out!
15.07.2025 16:51 — 👍 1 🔁 0 💬 0 📌 0
DAGM GCPR (Call for Papers)
🚨 Deadline Extended ! 🗓️
Due to a technical hick-up and popular demand, the #GCPR2025 FastTrack submission will remain open until July 19th, 2025 11:59 CEST!
There’s still time to be part of this year’s exciting program! 🔥
👉 www.dagm-gcpr.de/year/2025/su...
08.07.2025 08:24 — 👍 3 🔁 2 💬 0 📌 0
DAGM GCPR (Call for Papers)
🚨Final Call! Fast Review Track submissions for #GCPR2025 close tonight (July 7, 11:59 CEST)!
Dejected by reviews at CVPR, ICCV, BMVC, or other top-tier venues?
Give it a second chance!🚀
Any paper rejected from a peer-reviewed venue since July 2024 is eligible.
www.dagm-gcpr.de/year/2025/su...
07.07.2025 07:48 — 👍 2 🔁 1 💬 0 📌 1
📢On popular demand, the Fast Review Track deadline is now extended to 7th July, 11:59 CEST!⏳
Got a paper rejected from a top-tier venue (CVPR, ICLR, NeurIPS, RSS, etc.) in the past year? Give it a second chance at #GCPR2025 with fast reviews and official proceedings!📄✨
30.06.2025 21:20 — 👍 3 🔁 2 💬 0 📌 0
Was your strong paper rejected at ICCV or CVPR?!
The Fast Review track lets you revise and resubmit with decisions within 3 weeks!
Looking forward to your submissions!
26.06.2025 07:35 — 👍 0 🔁 0 💬 0 📌 0
🚨 Calling all Vision and ML researchers! 🚨
Missed the regular GCPR deadline?
No worries, the Fast Review Track deadline is July 1, 2025 (11:59 PM CEST).
Polish up that revision from a previous submission and submit now! 🔄✍️
#GCPR2025 #ComputerVision #AIResearch
21.06.2025 12:19 — 👍 3 🔁 3 💬 0 📌 0
a man and a woman are jumping in the air in a living room .
ALT: a man and a woman are jumping in the air in a living room .
🚨 Big News! GCPR 2025 has received a record number of submissions this year!🎉
⏰ Reminder: The supplementary deadline is tonight at 11:59 PM CEST.
Good luck to all the authors wrapping things up! 💪✨ #GCPR2025 #ComputerVision
Looking forward to the Fast Review Track submissions. Deadline: 1st July!
12.06.2025 14:24 — 👍 7 🔁 3 💬 0 📌 0
Presenting now (12-2pm) at poster #226
11.06.2025 16:38 — 👍 1 🔁 1 💬 0 📌 0
2/ 🧵 Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
By: S. Agnihotri, D. Schader, N. Sharei, M.E. Kaçar, M. Keuper
🔍 Investigating if synthetic corruptions can be a reliable proxy for real-world ones, and understanding their limitations.
📚https://www.arxiv.org/abs/2505.04835
11.06.2025 20:44 — 👍 4 🔁 1 💬 1 📌 0
1 / 🧵 ...
Workshop: Synthetic Data for Computer Vision @ CVPR 2025
📱 @shashank-agnihotri.bsky.social @margretkeuper.bsky.social @keuper-labs.bsky.social
11.06.2025 20:44 — 👍 4 🔁 1 💬 1 📌 0
Corner Cases - How Size and Position of Objects Challenge ImageNet-Trained Models openreview.net/forum?id=B6l...
M. Fatima, S. Jung, @margretkeuper.bsky.social
11.06.2025 10:19 — 👍 4 🔁 1 💬 1 📌 0
Announcing our amazing Keynote Speakers for #GCPR2025:
Venkatesh Babu Radhakrishnan, IISc
Dima Damen, University of Bristol @dimadamen.bsky.social
Efstratios Gavves, University of Amsterdam @egavves.bsky.social
Stefanie Jegelka, MIT EECS and TU Munich @tum.de
Alex Kolesnikov, OpenAI @kolesnikov.ch
27.05.2025 12:00 — 👍 9 🔁 5 💬 0 📌 1
Do what excites ✨ Exploring the robustness of ML models and reading about Space 💫
Trending papers in Vision and Graphics on www.scholar-inbox.com.
Scholar Inbox is a personal paper recommender which keeps you up-to-date with the most relevant progress in your field. Follow us and never miss a beat again!
Ph.D. Student | valeo.ai | IRISA OBELIX | Interested in the intersection of computer vision and frugal learning.
Website: bjoernmichele.com
PhD Candidate @ AI in Medicine Lab at Technical University of Munich
Ph.D. student @ ETH Zürich
Machine Learning Explainability
@Detesia/CISPA
@Max Planck Institute for Informatics
https://www.linkedin.com/in/shrebox/
PhD student @ TUM with Daniel Cremers
PhD Student in #ComputerVision at the University of Bologna and Verizon Connect. Entre Firenze e Compostela.
PhD Student at IMAGINE (ENPC)
Working on camera pose estimation
thibautloiseau.github.io
Assistant Professor at the Department of Computer Science, University of Liverpool.
https://lutzoe.github.io/
PhD Student @ Max Planck Institute for Informatics
PhD student @ Uni Tübingen and IMPRS-IS, working on 3D vision
patriciagschossmann.github.io
PhD Candidate at the Max Planck ETH Center for Learning Systems working on 3D Computer Vision.
https://wimmerth.github.io
Head of Generative Intelligence Lab @cispa.de
We teach AI how to see and model the visual world
DFG #EmmyNoether AI Fellow
Previously @mpi-inf.mpg.de @uni-freiburg.de @jhu.edu @unibas.ch
https://genintel.mpi-inf.mpg.de
ML Researcher, Qualcomm AI Research
Postdoc, University of British Columbia
Vector Institute
PhD, TU Darmstadt
The German Conference on Pattern Recognition (GCPR) is the annual symposium of the German Association for Pattern Recognition (DAGM). It is the national venue for recent advances in image processing, pattern recognition, and computer vision.
Professor at University of Mannheim and Researcher at MPII
