Some of our IMAGINE members at #CVPR2025

#CVPR2025 Sat June 14 (PM)
🎬 Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs
@lucasventura.com, Antoine Yang, Cordelia Schmid, @gulvarol.bsky.social
📄 pdf: arxiv.org/abs/2504.00072
🌐 webpage: imagine.enpc.fr/~lucas.ventu...
💻 code: github.com/lucas-ventur...

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...

- Novel speech-guided frame selection to caption only what matters! → handles hour-long videos
- Text-only input (ASR + Captions)
- SOTA on VidChapters-7M (45.3 vs 26.7 F1) 📈

Huge shoutout to my amazing supervisors and co-authors: Antoine Yang, Cordelia Schmid, and @gulvarol.bsky.social

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...

🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷

Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa...

Big 🧵👇 with details!

Get to know @gulvarol.bsky.social, Senior Researcher at École des Ponts ParisTech 🇫🇷 She's an ELLIS Scholar, member of ELLIS Unit Paris, former winner of the ELLIS PhD Award. Her research covers computer vision, vision & language, human motion generation & sign languages.

#WomenInELLIS

Starter pack including some of the lab members: go.bsky.app/QK8j87w

🧩 Excited to share our paper "RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges" (arxiv.org/abs/2502.19955) accepted to #CVPR2025! We created a benchmark that systematically evaluates image matching methods across well-defined geometric difficulty levels. 🔍

🌍 Guessing where an image was taken is a hard, and often ambiguous problem. Introducing diffusion-based geolocation—we predict global locations by refining random guesses into trajectories across the Earth's surface!

🗺️ Paper, code, and demo: nicolas-dufour.github.io/plonk

Hi! Can you please add me?

Could you please add me?

🍏 New preprint alert! 🍏
PoM: Efficient Image and Video Generation with the Polynomial Mixer
arxiv.org/abs/2411.12663
This is my latest "summer project" and it was so big I had to call in reinforcements (Thanks @nicolasdufour.bsky.social)

TL;DR Transformers are for boomers, welcome to the future
🧵👇