Edoardo De Matteis

🎉 Excited to share our latest work, accepted at #WACV25! 🌟 We introduce Social Egocentric Mesh Estimation, a novel task that predicts the 3D pose of a camera wearer using their social interactions and 3D scene context. 🧍‍♂️➡️🧍‍♀️

Excited to share our latest research, TI-PREGO—a follow-up to PREGO, our #CVPR2024 work! 📈 We explore how Chain of Thought and In-context learning can boost mistake detection in procedural videos. Paper: arxiv.org/abs/2411.02570 A good read before the #CVPR2025 deadline! 🚀

We're restyling the PINlab logo! 🦉 The little owl (Athene Noctua) accompanies Minerva, representing wisdom, Sapienza.

📢 Our #CVPR2024 is finally out! "PREGO: online mistake detection in PRocedural EGOcentric videos" We introduce PREGO, a model for detecting procedural errors in egocentric videos as they occur. Paper: arxiv.org/abs/2404.01933 Code: github.com/aleflabo/PREGO (available soon)

Dilly ding dilly ding 🔔 We are in #CVPR2024 🚀 "PREGO: online mistake detection in PRocedural EGOcentric Videos" has been accepted to @CVPR 🍷 Impressive effort from the whole team! @GalassoFab10, @GuidoDamely, @LeonardoPlini, @lu_scofano, @edmatteis, @anfurnari, @GMFarinella

🚀Exciting news! We are thrilled to announce that our work on scene-aware human motion forecasting, "STaged contact-aware global human motion forecasting", will be presented as an oral paper at #BMVC23! 📚 Paper: arxiv.org/abs/2309.08947 🖥️Code: github.com/L-Scofano/STAG

🔬Wrapping Up Summer: PINlab's Adventures!🔬 As summer waves goodbye, here's a quick peek at how we rocked it at PINlab! Check out the highlights of our sun-soaked adventures: p.s. website: pinlab.org github: github.com/PINlabSapienza

We are thrilled to announce that our paper titled "Best practices for 2-body pose forecasting" has received the prestigious best paper award at the #Precognition workshop during #CVPR2023. Made in @SapienzaPINlab

Great news! Our paper "About latent roles in forecasting players in team sports" has been accepted at International AI for Agent-Based Modelling Community - AI4ABM ICLR'23 Workshop!

Exciting news! Our paper "Best Practices for 2-Body Pose Forecasting" has been accepted in the CVPR'23 Precognition workshop! Check out our website for code and paper. Paper: arxiv.org/abs/2304.05758 Github: github.com/edodema/BestPr… Webpage: pinlab.org/bestpractices2… #CVPR23

Presentiamo il più grande LLM italiano realizzato dal gruppo di ricerca RSTLess della Sapienza Università di Roma. Il team di ricerca dietro Fauno comprende @Andrea_Bacciu, @GioTrappolini, Prof @EmanueleRodola , @teelinsan e il Prof @fabreetseo . github.com/RSTLess-resear…

Thread Alert 🚨 Our lab, PIN Lab (Perception and Intelligence Lab) is now live at pinlab.org.

In 1930, the union of American singers spent the equivalent of $10m on a campaign to stop people from listening to recorded music and watching movies with sound. 1/

Delitto e Castigo, Fëdor Dostoevskij