A RANSAC-based geometric gate routes regions to homography or optical flow warping before SSP fusion, improving mIoU by 4.24-4.91% on synthetic UAVid with only 211K added parameters to frozen backbones.
Hiera: A hierarchical vision transformer without the bells-and-whistles
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.
citing papers explorer
-
Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation
A RANSAC-based geometric gate routes regions to homography or optical flow warping before SSP fusion, improving mIoU by 4.24-4.91% on synthetic UAVid with only 211K added parameters to frozen backbones.
-
Revisiting Feature Prediction for Learning Visual Representations from Video
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.