Urs Waldmann
@ursnwaldmann.bsky.social
29 followers 50 following 13 posts
Postdoc @liu.se in @liucvl.bsky.social working on 3D motion analysis from video, previously PhD and Postdoc @uni-konstanz.de and @cbehav.bsky.social | Profile pic by Ole Johannsen
Posts Media Videos Starter Packs
Reposted by Urs Waldmann
si-cv-graphics.bsky.social
𝗛𝘂𝗺𝗮𝗻𝟯𝗥: 𝗘𝘃𝗲𝗿𝘆𝗼𝗻𝗲 𝗘𝘃𝗲𝗿𝘆𝘄𝗵𝗲𝗿𝗲 𝗔𝗹𝗹 𝗮𝘁 𝗢𝗻𝗰𝗲
Yue Chen, Xingyu Chen, Yuxuan Xue ... Gerard Pons-Moll
arxiv.org/abs/2510.06219
Trending on www.scholar-inbox.com
Reposted by Urs Waldmann
Reposted by Urs Waldmann
Reposted by Urs Waldmann
elliottwu.bsky.social
The video recording of the #CV4Animals Workshop #CVPR2025 is now available on our website: www.cv4animals.com
ursnwaldmann.bsky.social
Happy to share that I've been selected as an outstanding reviewer for ICCV 2025.
iccv.bsky.social
There’s no conference without the efforts of our reviewers. Special shoutout to our #ICCV2025 outstanding reviewers 🫡

iccv.thecvf.com/Conferences/...
2025 ICCV Program Committee
iccv.thecvf.com
Reposted by Urs Waldmann
si-cv-graphics.bsky.social
𝗣𝗔𝗗𝟯𝗥: 𝗣𝗼𝘀𝗲-𝗔𝘄𝗮𝗿𝗲 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝟯𝗗 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗖𝗮𝘀𝘂𝗮𝗹 𝗩𝗶𝗱𝗲𝗼𝘀
Ting-Hsuan Liao, Haowen Liu, Yiran Xu ... Jia-Bin Huang
arxiv.org/abs/2509.25183
Trending on www.scholar-inbox.com
Reposted by Urs Waldmann
liucvl.bsky.social
𝐖𝐞𝐥𝐜𝐨𝐦𝐞 𝐭𝐨 𝐃𝐨𝐜𝐭𝐨𝐫𝐚𝐥 𝐃𝐞𝐟𝐞𝐧𝐜𝐞 𝐨𝐟 𝐉𝐨𝐡𝐚𝐧 𝐄𝐝𝐬𝐭𝐞𝐝𝐭, 𝐂𝐨𝐦𝐩𝐮𝐭𝐞𝐫 𝐕𝐢𝐬𝐢𝐨𝐧 𝐋𝐚𝐛𝐨𝐫𝐚𝐭𝐨𝐫𝐲, 𝐈𝐒𝐘

𝐓𝐢𝐭𝐥𝐞: Towards the Next Generation of 3D Reconstruction

𝐃𝐚𝐭𝐞: 2025-10-08

𝐓𝐢𝐦𝐞: 9:15

𝐏𝐥𝐚𝐜𝐞: Zero, building Zenit

𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞: English
Reposted by Urs Waldmann
praked.bsky.social
When life gives you a fish, you sail with it. 🐟⛵🤖
Our autonomous sailboat and robotic fish finally met on Lake Constance — and the footage did not disappoint. 🌊
Big thanks to @swarmdynamics.bsky.social , Hun Jang and Liang Li for making this happen.
#robotics #swarm #autonomy #maritime
Reposted by Urs Waldmann
csprofkgd.bsky.social
Thank you for raising this and pushing back. If resources are becoming a limiting factor, we should start exploring alternative ways of accepting papers, such as acceptance without a presentation.
Reposted by Urs Waldmann
zeynepakata.bsky.social
NeurIPS has decided to do what ICLR did: As a SAC I received the message 👇 This is wrong! If the review process cannot handle so many papers, the conference needs yo split instead of arbitrarily rejecting 400 papers.
Reposted by Urs Waldmann
ekazakos.bsky.social
So… I have an idea! For those of us attending ICCV 2025 in Hawaii, I thought it would be very exciting and fun to collect an exotic dataset of tropical plants and animal species.

I’m staying for vacations after the conference, and would like to combine it with the data collection. Who is joining?
Reposted by Urs Waldmann
alexhhchan.bsky.social
New paper out in the lab on collective gaze following in pigeons in iScience!

Coolest experimental design ever🤭
Reposted by Urs Waldmann
invirtuo.bsky.social
[2/3] This Friday, Prof Oliver Deussen (@uni-konstanz.de) is going to talk about how he and his team use VR technology to create a highly controlled environment, in which they research how different animals use visual inputs for movement decisions.

More information in the announcement below 👇
Reposted by Urs Waldmann
cvprconference.bsky.social
Denver, you’re up next! 🌄 See you at #CVPR2026! 👋
Reposted by Urs Waldmann
stojnicv.xyz
Are you at @cvprconference.bsky.social #CVPR2025 ? Come and check out LPOSS.

We show how can graph-based label propagation be used to improve weak, patch-level predictions from VLMs for open-vocabulary semantic segmentation.

📅 June 13, 2025, 16:00 – 18:00 CDT
📍 Location: ExHall D, Poster #421
Reposted by Urs Waldmann
sarameghanbeery.bsky.social
Are you working on instance recognition or personalized computer vision? Are you at @cvprconference.bsky.social? Are you looking for an INTERESTING NEW CHALLENGE??

Come join us today (6/12) at the first EVER Animal Re-Identification Tutorial!!

8:30am-12pm in 202C

sites.google.com/view/animal-...
Reposted by Urs Waldmann
gcpr-by-dagm.bsky.social
🚨 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!
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 .
media.tenor.com
ursnwaldmann.bsky.social
Full house at our @cvprconference.bsky.social workshop #CV4Animals — thank you all for attending! What an amazing community! ❤️
ursnwaldmann.bsky.social
#CV4Animals workshop taking place NOW in 104 C @cvprconference.bsky.social! Amazing keynotes, orals and posters: www.cv4animals.com All about CV and animals 🐦‍⬛🐎🐀 See you there!
Reposted by Urs Waldmann
elliottwu.bsky.social
This is happening at 9:20 tomorrow morning in Room 104C.
elliottwu.bsky.social
Look forward to this annual gathering of the CV4Animals community @cvprconference.bsky.social!

The workshop is starting at 9:20am on Thursday June 12 in Room 104 C. Come join us if you're attending #CVPR2025!

cv4animals.com
🦒🪼🐬🐿️🦩🐢🦘🦜🦥🦋
Reposted by Urs Waldmann
si-cv-graphics.bsky.social
𝗦𝘁𝗿𝗲𝗮𝗺𝗦𝗽𝗹𝗮𝘁: 𝗧𝗼𝘄𝗮𝗿𝗱𝘀 𝗢𝗻𝗹𝗶𝗻𝗲 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝟯𝗗 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗨𝗻𝗰𝗮𝗹𝗶𝗯𝗿𝗮𝘁𝗲𝗱 𝗩𝗶𝗱𝗲𝗼 𝗦𝘁𝗿𝗲𝗮𝗺𝘀
Zike Wu, Qi Yan, Xuanyu Yi ... Renjie Liao
arxiv.org/abs/2506.08862
Trending on www.scholar-inbox.com
Reposted by Urs Waldmann
jbhuang0604.bsky.social
Kullback–Leibler (KL) divergence is a cornerstone of machine learning.

We use it everywhere, from training classifiers and distilling knowledge from models, to learning generative models and aligning LLMs.

BUT, what does it mean, and how do we (actually) compute it?

Video: youtu.be/tXE23653JrU
Reposted by Urs Waldmann
chriswolfvision.bsky.social
DUNE is a great universal image encoder which works for a large class of tasks and beats its teacher MASt3R on map free localization. #cvpr2025

We use it a lot already, I recommend it.

(keynote @ Paris by @dlarlus.bsky.social )