Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
V-JEPA 2 ViT-G Embeddings provide precomputed video features for a 62-hour subsample of the BEHAVIOR-1K 2025 challenge demonstrations. The dataset, created by quastAI, aims to accelerate downstream experimentation by eliminating repeated video processing. It was last updated on May 22, 2026.
The dataset description includes an 'IMPORTANT: Work in Progress, please wait to use the dataset until this is removed !!' warning.