Skip to content

Latest commit

 

History

History
5 lines (3 loc) · 434 Bytes

File metadata and controls

5 lines (3 loc) · 434 Bytes

SSD - Spatial Scene Dataset & Video Dataset Toolkit

This task involves generating detailed descriptions for high-quality videos across various categories. The primary focus is on capturing spatial relationships, object positioning, and scene dynamics, particularly from a first-person perspective.

Hugging Face