Romaric Audigier

Researcher, CEA

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

CaMiT: A Time-Aware Car Model Dataset for Classification and Generation

#4914 · Frédéric Lin, Biruk Abere Ambaw, Adrian Popescu, Hejer AMMAR, Romaric Audigier, Hervé Le Borgne

We introduce CaMiT, a large-scale, time-aware dataset of 5.9M car samples (labeled and unlabeled) from 2005–2023, enabling research on temporal shift modeling in fine-grained classification, continual learning, and time-aware image generation.