Something-Something v-2

The Something-Something dataset (version 2) is a collection of 220,847 labeled video clips of humans performing pre-defined, basic actions with everyday objects. It is designed to train machine learning models in fine-grained understanding of human hand gestures like putting something into something, turning something

Papers using Something-Something v-2 (2)

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning2025 · 3 citesMultimodal Knowledge Distillation for Egocentric Action Recognition Robust to Missing Modalities2025