Timothée Darcet

机构：Meta, Inria · 主页：https://tim.darcet.fr

发表论文 7 篇 · 总被引 10586 次 · h-index 7

代表论文

DINOv2: Learning Robust Visual Features without Supervision (2023 · Trans. Mach. Learn. Res. · 被引 9587)
DINOv3 (2025 · 被引 1205)
Vision Transformers Need Registers (2023 · International Conference on Learning Representations · 被引 938)
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment (2024 · Computer Vision and Pattern Recognition · 被引 98)
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach (2024 · Trans. Mach. Learn. Res. · 被引 59)
Cluster and Predict Latent Patches for Improved Masked Image Modeling (2025 · arXiv.org · 被引 19)