Andre Araujo

Researcher, Google DeepMind

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models

#2606 · Jesimon Barreto, Carlos Caetano, Andre Araujo, William Robson Schwartz

We show that adapting vision foundation models using self-supervised fine-tuning with simple object-centric videos substantially improves representation quality without labels.