Ivan Martinović

StreamMAE unlocks self-supervised learning on continuous video streams, matching i.i.d. MAE performance by tackling intra-batch similarity with novel regularization.

EAST's innovative sampling strategy enables models to excel at early action prediction, achieving unprecedented accuracy across multiple benchmarks.

Achieve state-of-the-art open-vocabulary segmentation by distilling a sliding-window ViT into a single-pass architecture, enabling efficient high-resolution reasoning.