@chriswolfvision.bsky.social
Principal Scientist at Naver Labs Europe, Lead of Spatial AI team. AI for Robotics, Computer Vision, Machine Learning. Austrian in France. https://chriswolfvision.github.io/www/
Post ECCV Cycling....
07.03.2026 15:45 β π 19 π 0 π¬ 1 π 0We are not all equal...
07.03.2026 11:43 β π 6 π 0 π¬ 0 π 0
Maybe we should stop calling it vibecoding and call it what it is.
Natural language programming.
A publication world model!
06.03.2026 18:37 β π 5 π 0 π¬ 0 π 0I wonder when we will arrive at the part where a horse becomes a senator ...
06.03.2026 18:26 β π 3 π 0 π¬ 2 π 0
Jack Dorsey on how he would run a new company
From: www.wired.com/story/jack-d...
You don't need to go back to 1942. "Fargo" does that as well π. Or any recent Clint Eastwood movie where he acts himself, like "The mule" or "Gran Torino".
06.03.2026 13:44 β π 1 π 0 π¬ 0 π 0Gas prices (πΆ/litre) in Munich: Feb 2 2026 vs today
06.03.2026 10:14 β π 11 π 3 π¬ 1 π 1
"Authors should not use negative v-spaces to change the template layout."
The template layout:
You too, if you submit!
05.03.2026 21:21 β π 2 π 0 π¬ 1 π 0That's why it's given by the snake π
05.03.2026 20:09 β π 1 π 0 π¬ 1 π 0ECCV 2026 deadline push at @naverlabseurope.bsky.social with @dlarlus.bsky.social @weinzaepfelp.bsky.social @mbsariyildiz.bsky.social @bjoernmichele.bsky.social @vincentleroy.bsky.social @rbregier.bsky.social + + + ....
05.03.2026 20:03 β π 25 π 1 π¬ 1 π 1
It's time for this picture again ...
#ECCV2026
J'ai eu un troisieme appel en une semaine, un de plus depuis mon poste. Je demande gentiment de ne plus appeler, et c'est bien free.
05.03.2026 12:33 β π 0 π 0 π¬ 0 π 0Thanks, I didn't know about this!
05.03.2026 08:45 β π 0 π 0 π¬ 1 π 0
Additionally it also plays with the ambiguity of projective geometry. M.C. Escher would love it.
2/2
There is whole comic series called "L'imbattable" on this subject by French artist Pascal Jousselin. It confuses space in the scene, with space in the comic strip itself, as in your examples above.
1/2
I didn't even know this word exists!
05.03.2026 07:40 β π 2 π 0 π¬ 0 π 0Increasing the fonts and changing figures on one of our 2 ECCV submissions right now, since it might be on your desk. Not kidding π
05.03.2026 06:55 β π 2 π 0 π¬ 0 π 0
This is where the comparison breaks down. Your papers are probably more like your grand parents, telling you things you don't want to hear anymore.
"SVMs perform better than neural networks"
"Binarization is an important step in computer vision"
"Global optimization and convexity is necessary"
Happy "at-least-we-can-eat-pizza-together-it-compensates-for-the-stress" day!
Did I get the ajdectivization hyphens right?
LOL, you got me!
I thought that I would get more replies on the semantics of choosing edge detection, not on its syntax ...
I was even considering not re-posting this old post from Twitter ... since nobody requires these hints anymore. You just ask LLM to solve your LaTeX problems π
04.03.2026 22:21 β π 1 π 0 π¬ 1 π 0
TIL that
- "state of the art" is a noun, so we compare to the state of the art
- "state-of-the-art" is an adjective, so we can write about the state-of-the-art model on, say, edge-detection or thresholding or binarization.
I am done with subfigure and raisebox. Placing sub figures with tikz gives me all the flexibility I need, in particular when their sizes are varying.
04.03.2026 19:55 β π 11 π 1 π¬ 1 π 0Authorship is like parenting: you love all your papers the same and you do not prefer one over the others.
04.03.2026 08:54 β π 6 π 0 π¬ 2 π 1
I used the term 'reasoning' a lot in the past but then people exclusively linked it to chain of thought in LLMs and were confused with our work (came to our poster... "but this is not reasoning!").
Soon we will need to abandon the term 'agent' if it does not involve an LLM.
SIGBOVIK has a Bluesky now! Follow to learn more cutting-edge research from the worldβs most comedic and occasionally scientific academic conference
27.02.2026 21:01 β π 64 π 25 π¬ 0 π 2Current state: ECCV
03.03.2026 15:52 β π 10 π 0 π¬ 0 π 0