CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones Paper • 2504.16570 • Published Apr 23
One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework Paper • 2510.02898 • Published Oct 3 • 4
Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation Paper • 2411.19331 • Published Nov 28, 2024 • 5