Silvio Giancola

🚀🌟 The 4th official task of #SoccerNetChallenges 2026 is here!

⚽4⃣ Player-Centric Ball Action Spotting
A new vision challenge that not only detects what and when an event happens, but also who performs it.

Check all SoccerNet 2026 tasks: soccernet.org/challenges/2...
👇

Excited to launch the 3rd task of our SoccerNet challenges 2026! In this task, you’ll have to answer generic knowledge questions about football 🧠 will your AI be able to answer them? :)

Excited to see our 2nd SoccerNet Challenge 2026 task go live! ⚽🔮
Ball Action Anticipation - predict what happens next on the pitch, 5 seconds into the future.
Proud of the amazing teamwork ArturXarles Mohamad Dalal! 🙌
Join the challenge 👉 soccer-net.org/challenges/2...
#AI #CV

🚀🌟 We’re excited to kick off #SoccerNet Challenges 2026 with our first official task!

⚽️1⃣ Spiideo SoccerNet SynLoc.

Details of the first version of this task are available at soccer-net.org/challenges/2...

Our newest SoccerNet challenge on Monocular Depth Estimation is up and running! 🥳
Our world is 3D, football games are too, do you have what it takes to lift football analysis from 2D to 3D? 🏟️⚽️

The SoccerNet challenge on Foul Recognition is up and running! Can you beat our AI referee? ;)

@cvprconference.bsky.social #cvpr #cvsports #soccernet

AI and Stress 200Bn Weights of Responsibility The Stress of Working in Modern AI Felix Hill, Oct 2024 The field of AI has changed irrevocably in the last 2 years. ChatGPT is approaching 200m monthly users. Gemin...

A nice text on AI and stress, worth reading and spreading around.
Sharing is caring, stay safe y’all! 🤗

docs.google.com/document/u/1...

That’s the second edition of our SoccerNet challenge on “Game State Reconstruction”.

Reconstruct a top view representation of the game, with players ID and position on the field, in time.

2⃣🚀 #SoccerNet2025 Let's present our Challenge #2: “Game State Reconstruction”

🏟 Reconstruct a schematic state of the game over time, capturing key player positions and overall game dynamics!
🔗 soccer-net.org/challenges/2...

#AIChallenge #SportsAnalytics @cvprconference.bsky.social

1⃣ 🚀 #SoccerNet2025 Introducing our first challenge: “Ball Action Spotting”

⚽ Spot 12 ball events with 1 second precision and assign each action to the correct team!
Are you ready to raise the bar? 📈

@cvprconference.bsky.social @silviogiancola.bsky.social
@janheld.bsky.social @soccernet.bsky.social

@rohanpaul_ai https://x.com/rohanpaul_ai/status/1864111751845040538 #x-rohanpaul_ai 🎥



Move over Gaussians, convex shapes are the new kings of 3D

Paper: "3D Convex Splatting: Better Radiance Fields with Fewer Primitives"

→ Introduces 3D Convex Splatting (3DCS) - uses smooth convex sh...

Jan Held, Renaud Vandeghen, Abdullah Hamdi, Adrien Deliege, Anthony Cioppa, Silvio Giancola, Andrea Vedaldi, Bernard Ghanem, Marc Van Droogenbroeck
3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
https://arxiv.org/abs/2411.14974

Heading to the Holodeck.

First it looked like NeRF's would be the way. Then Gaussian Splats.

Now Convex Splatting is coming on the scene to build 3D experiences with better quality.

Things in the AI industry change so fast.

If you review for a #ML conference like @iclr-conf.bsky.social or @neuripsconf.bsky.social, YOU HAVE A RESPONSIBILITY TO REPLY TO THE AUTHORS.

If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.

I say this as an AC.

#MLSky

⚽️🤖🚀 We’re ready for the 𝘬𝘪𝘤𝘬-𝘰𝘧𝘧 of the 5th edition of the 𝐒𝐨𝐜𝐜𝐞𝐫𝐍𝐞𝐭 𝐂𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞!
🌍✨Join us in the 2025 edition of this amazing community where AI meets soccer. Stay tuned for exciting updates!
discord.com/invite/cPbqf...
#SoccerNet2025 #ComputerVision

🚀 🌟 SoccerNet Challenges 2025 is here! In this 5th edition, we’re excited to unveil four diverse tasks!

⚽️ Check the deadline, there’s plenty of time to craft a groundbreaking solution and rise to the top of the leaderboard! 🏆

🔥Let the Challenges begin! #SoccerNet #AI 🔃

🚀🔥 Get ready! This year, we’re coming stronger than ever! 💪⚽️
🎥✨ Take a peek behind the scenes of our upcoming #SoccerNet 2025 video!

Dive into the 4 thrilling challenges of soccer analytics 2025! 🎬 Stay tuned for the full video—it’s going to be epic! 🌟
#CVPR2025⚡️🌍

⚽️🏟️🎥 Greetings from an iconic location that will be featured in our #SoccerNet Challenges 2025 video!🌟

Can you name this legendary stadium? 👀
Hint: It’s currently in the final stages of its reconstruction! 🚧✨🇪🇸

#SoccerAnalytics #CVPR2025 #AI #ComputerVision

Our paper "𝟑𝐃 𝐂𝐨𝐧𝐯𝐞𝐱 𝐒𝐩𝐥𝐚𝐭𝐭𝐢𝐧𝐠: 𝐑𝐚𝐝𝐢𝐚𝐧𝐜𝐞 𝐅𝐢𝐞𝐥𝐝 𝐑𝐞𝐧𝐝𝐞𝐫𝐢𝐧𝐠 𝐰𝐢𝐭𝐡 𝟑𝐃 𝐒𝐦𝐨𝐨𝐭𝐡 𝐂𝐨𝐧𝐯𝐞𝐱𝐞𝐬” is now available on Arxiv!

💻Project page for some cool visualizations: convexsplatting.github.io
📓 Paper: arxiv.org/abs/2411.14974

🏟️⚽ The SoccerNet Challenges 2025 are here!
This 5th edition brings FOUR exciting tasks that redefine the game in sports AI and computer vision.

🌐 Compete until April 24, 2025!
Details: www.soccer-net.org/challenges/2...

#SoccerNet #CVsports

#KAUST's Center of Excellence for #GenAI is hosting the 4th Rising Stars in AI #Symposium on Apr 7-10, 2025! Proud to lead this event for the 4th time, gathering emerging researchers in AI.
Are you a #RisingStar in #AI? Apply before Dec 18 to be a speaker www.kaust.edu.sa/en/news/risi...

The #SoccerNet challenge is up and running!
More info👇
www.soccer-net.org/challenges/2...
#CVPR #CVsports

Check out our new paper on arxiv!
TLDR; convexes are better primitives to splat than gaussians for novel view synthesis

Our SoccerNet challenges are back!! More info on our website : soccer-net.org/challenges/2...
Follow us for updates!

🚀 🌟 #SoccerNet Challenges 2025 are here! In this 5th edition, we’re excited to unveil four diverse tasks!

⚽️ Check the deadline, there’s plenty of time to craft a groundbreaking solution and rise to the top of the leaderboard! 🏆

🔥Let the Challenges begin! #CVPR2025

3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes

Jan Held, Renaud Vandeghen, Abdullah Hamdi, Adrien Deliege, Anthony Cioppa, @silviogiancola.bsky.social, Andrea Vedaldi, Bernard Ghanem, Marc Van Droogenbroeck

tl;dr: 3D smooth convexes->primitives

arxiv.org/abs/2411.14974