This dataset is frequently cited in computer vision and machine learning literature focused on urban safety and automated monitoring systems. Video Dataset - Hugging Face
: Often stands for "Cross-Scene" or refers to a specific viewing angle or sensor configuration (like a fixed camera) used in that subset. SAME-038-CS.mp4
. Key Details About the Paper and Dataset: This dataset is frequently cited in computer vision
: The dataset was created to support research in situational awareness , particularly for understanding complex interactions between people, objects, and vehicles in "mixed environments" (e.g., smart cities, industrial sites, or traffic scenarios). Key Details About the Paper and Dataset: :
To do so, your dataset directory should have the following structure (see File names and splits for more information): Copied. my_ Hugging Face A dataset of labelled objects on raw video sequences
The filename is a specific video sample from the SAME (Situational Awareness for Mixed Environments) dataset . The corresponding research paper that introduced this dataset is: