Gül Varol

Movies are more than just video clips, they are stories! 🎬

We’re hosting the 1st SLoMO Workshop at #ICCV2025 to discuss Story-Level Movie Understanding & Audio Descriptions!

Website: slomo-workshop.github.io
Competition: huggingface.co/spaces/SLoMO...

Some of our IMAGINE members at #CVPR2025

We are about to start with Michael’s talk at Davidson C2 @michael-j-black.bsky.social

Where is the first photo from?? :o

Thu June 12, we are organizing workshops on Sign Language in the morning (Davidson C2), and Transformers for Vision in the afternoon (209 A-C).

June 13-14 afternoons, I will be at our posters on video chaptering and sign language translation.

Also, ask me anything at WiCV and DC mentorship events!

See you at #CVPR2025 in Nashville!

I will be at the AC workshop on Tue June 10.
Wed June 11, you can find me at my 3 workshop talks:
1- Video understanding, 10:30-11:15am (Room Davidson C2).
2- How to stand out, 1:40-2pm (Room 209 A-C).
3- AVA Accessibility, 3:30-4pm (Room 202 C).

#CVPR2025 Paris 🇫🇷 Who says you can’t have CVPR outside of the 🇺🇸 

The sky has a completely different color now ☀️

:( We promised David we’ll come back in one piece.

Imagine retreat 2025 in progress ☀️🏖️

The 4th Workshop on Transformers for Vision (T4V) at @cvprconference.bsky.social is soliciting self-nominations for reviewers.
If you're interested, please fill out this form:
forms.gle/z326LjaFGVQd...

More information can be found on our website:
sites.google.com/view/t4v-cvp...

#CVPR2025 #T4V

Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues Learn about our sign language translation method which incorporates context allowing it to generate more complete and meaningful translations.

#CVPR2025 Fri June 13 PM
🤟 Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues
Youngjoon Jang, Haran Raajesh, Liliane Momeni @gulvarol.bsky.social Andrew Zisserman @oxford-vgg.bsky.social
📄pdf: arxiv.org/abs/2501.09754
🌐webpage: www.robots.ox.ac.uk/~vgg/researc...

We're hiring! IMAGINE @ École des Ponts (Paris area) is opening a 4-year "CV for X" researcher position:
– competitive salary
– no teaching load
– starting pkg ≈ 2 PhDs
– goal: impactful core AI + X (climate, biodiversity, robotics...)
Apply by May 31: imagine-lab.enpc.fr/wp-content/u...

Introducing Chapter-Llama #CVPR2025, a framework for 𝐯𝐢𝐝𝐞𝐨 𝐜𝐡𝐚𝐩𝐭𝐞𝐫𝐢𝐧𝐠 using Large Language Models! 🎬🦙

Check it out:
📄 Paper: arxiv.org/abs/2504.00072
🔗 Project: imagine.enpc.fr/~lucas.ventu...
💻 Code: github.com/lucas-ventur...
🤗 Demo: huggingface.co/spaces/lucas...

Somewhat poorly advertised MS program in Paris: MVA master-mva.com is a 1-year research Master's, with (mostly English) courses across Maths, Vision, Learning, and an internship (that can lead to PhD). Applications open May 1 - June 30 for 2025-2026. Grants possible.

Oh roma bahane invaders sahane

🧵 1/3 Many at #CVPR2024 & #ECCV2024 asked what would be next in our workshop series.

We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup!

🔗 sites.google.com/view/standou...

A glimpse into the most recent ELLIS UnConference, a gathering of ELLIS Fellows and Scholars that took place in a beautiful location in the Black Forest last month

Hello world :) now I know why Zoom was more popular than I expected. So much is happening here.

Hello world :)