Antonino Furnari
@antoninofurnari.bsky.social
770 followers 120 following 110 posts
Associate Professor at University of 📍Catania, Sicily, Italy🇮🇹 Interested in Computer Vision and Egocentric Vision. Member of @ellis.eu, part of the #EPIC-KITCHENS, #EGO4D, #EGO-EXO4D teams. 🔗 https://antoninofurnari.it
Posts Media Videos Starter Packs
antoninofurnari.bsky.social
We're excited to share our group's contributions at #ICIAP2025 this week! A whole lot of new work in Egocentric Vision, from interaction prediction to episodic memory. 🤖🧠

A huge shoutout to all the amazing students and coauthors involved!

Full schedule below👇
antoninofurnari.bsky.social
Our crew has landed at #ICIAP2025 in Rome! 🇮🇹

Really excited for a great week of science and catching up with everyone. If you see us around, come say hi!

We'd love to chat and maybe grab a coffee ☕
antoninofurnari.bsky.social
A bit late to the party, but thrilled to share that we got three papers accepted at #WACV2026!

It looks like acceptance rate in the first round was very low, so I'm incredibly proud and truly honoured to work with my brilliant co-authors.

Titles here: antoninofurnari.github.io/news/papers_...
antoninofurnari.bsky.social
Thrilled to start my journey as an Associate Professor at the University of Catania.

A huge thank you to all the mentors, coauthors, and colleagues who supported me along the way.

Now, I'll be building my own research group focusing on Video Understanding and Egocentric Vision. Stay tuned!
antoninofurnari.bsky.social
Still buzzing from a great week in Madrid! 🇪🇸

It was a pleasure to give a week-long seminar on Video Understanding to PhD students Signal Processing and Communications Engineering at @uc3m.

Big thanks to Fernando Diaz and Ivan Gonzalez for the invitation and the fantastic hospitality.
antoninofurnari.bsky.social
Enjoyed a fantastic deep dive into generative models with Vittorio Ferrari on day 3 of #ICVSS2025! A great lecture covering the evolution from fundamental diffusion models to the latest in controllable image and video generation like ControlNet.
antoninofurnari.bsky.social
#ICVSS2025 getting intense!

Yesterday, two great lectures by Leonidas Guibas on foundation models for 3D/4D modeling and Daniel Cremers on 3D computer vision in the age of deep learning.

Then, nice aperitif and dinner 😄

Now an excing day 3 is ahead!
antoninofurnari.bsky.social
Kicking off the day at #ICVSS2025 with a thought-provoking talk by Andrea Vedaldi on Spatial Intelligence as new frontier of Computer Vision.

Great to see ML-compatible building 3D blocks such as VGGT appearing - then on to dynamic reconstruction and 3D priors in latent space!
antoninofurnari.bsky.social
Great talk yesterday by @dimadamen.bsky.social on the past, present, and future of egocentric video!

Video understanding out of the frame was especially exciting, pushing us to consider the 3D world beyond the camera's view.

Now on to day 2! #ICVSS2025
antoninofurnari.bsky.social
Great reminder from Christoph Feichtenhofer at #ICVSS2025 that the "secret sauce" of models like CLIP is the strong supervision from training data, not just novel architectures.

Insightful to see a dissection of how CLIP pretraining works and what it can enable beyond classification.
antoninofurnari.bsky.social
Great talk by @ajdavison.bsky.social on the journey from SLAM to Spatial AI at #ICVSS2025!

A compelling argument for the power of dynamic, updatable 3D representations and their direct impact on the future of robotics and wearable devices.

And nice insights for spatial AI researchers!
antoninofurnari.bsky.social
Here we are! #ICVSS2025 has officially started!

Looking forward to the great talks ahead!
antoninofurnari.bsky.social
🚀 And the tour goes on! I'll be at #ICVSS2025 all week!

Leaning back in full learning mode and looking forward to meeting old and new friends!

If you're here, feel free to ping me!
antoninofurnari.bsky.social
✈️On my way to Rome for IJCNN where I’ll give a talk at the Eyes of the Future workshop (sites.google.com/view/iaise-i...).

I’ll be around all day, feel free to ping me for a chat if you are around!
antoninofurnari.bsky.social
⏰ Few days left to submit to ACVR@#ICCV2025!

That paper on assistive technology you worked so hard on? Maybe it wasn't "rejected," it was just destined for a more appreciative audience. 😉 Give your brilliant work the spotlight it deserves!

DL: June 30

iplab.dmi.unict.it/acvr2025/
antoninofurnari.bsky.social
Yesterday, I completed my two-week long visit in the US giving a talk at the #EgoAct RSS workshop.

Great to talk and learn how robotics and (egocentric) vision are converging!

Thanks organisers for inviting!
antoninofurnari.bsky.social
Rewarding days! Post-#CVPR, productive visit 6 talk at UPenn's GRASP Lab.

Thanks @dineshjayaraman.bsky.social‬ for hosting, & great chats with faculty staff! Always inspiring.

Explored Philly & worked from cool spots too :)

✈️ Next: LA for @roboticsscisys.bsky.social‬ WS & #EgoAct talk. 💪
antoninofurnari.bsky.social
Last week I gave a talk on future predictions in egovision at the Precognition workshop at #CVPR2025, covering short-term predictions and how they enable a better understanding of procedural activities and prediction of mistakes.

If you missed it: antoninofurnari.it/downloads/ta...
antoninofurnari.bsky.social
A post-hoc correction of our group's contribution to #CVPR2025!
antoninofurnari.bsky.social
Almost ready for our poster on gaze-based procedural mistake detection at 16.00, poster 281 #CVPR2025

See you there!
antoninofurnari.bsky.social
Going to give a talk on future predictions in egocentric vision at the Precognition WS in room 107A in half an hour at 16.00 #CVPR2025.

I'll cover short-term predictions and how precognition can enable a better understanding of procedural activities and prediction of mistakes!
antoninofurnari.bsky.social
Kris Kitani's talk in a few minutes at the #EGOVIS workshop in Grand B1 at #CVPR2025.
antoninofurnari.bsky.social
Full day today at #CVPR2025 for the group with a keynote talk (room 107A - 16.00), a workshop (#EGOVIS - Room B1, full day), organisation of challenges and oral/poster presentations. See below for details!
antoninofurnari.bsky.social
Siyu Tang on "Towards an egocentric multimodal foundation model" now at the #EGOVIS workshop at #CVPR2025!